Electronic device and method for recognizing speaker by using external electronic device

Abstract

This electronic device may comprise: a memory storing instructions; a communication circuit; a microphone; and at least one processor. The instructions may, when executed individually or collectively by the at least one processor, cause the electronic device to: obtain a speech or voice signal; generate, from the speech or voice signal including a wake-up word, a first recognition result for the wake-up word; transmit the first recognition result to a server connected to one or more external electronic devices capable of recognizing the wake-up word; receive, from the server, a second recognition result for a user who has uttered the wake-up call; and execute, on the basis of the second recognition result, a designated function in the electronic device with respect to the user. The second recognition result may include identification information indicating the user, obtained from an external electronic device, in which the user is registered, among the one or more external electronic devices.

Description

Electronic device and method for recognizing a speaker using an external electronic device

[0001] The descriptions below relate to electronic devices and methods for recognizing a speaker using an external electronic device.

[0002] An electronic device can acquire a sound signal from an external source via a microphone. For example, the sound signal may include speech or voice uttered by a speaker. For example, the electronic device can recognize the speaker based on the sound signal.

[0003] The above information may be provided as background art to aid in understanding the present disclosure. No claim or determination is made as to whether any of the above is applicable as prior art related to the present disclosure.

[0004] An electronic device may include a communication circuit. The electronic device may include a microphone. The electronic device may include at least one processor. The at least one processor may be configured to acquire a voice signal through the microphone. The at least one processor may be configured to generate a first recognition result for a wake-up word from the voice signal including the wake-up word. The at least one processor may be configured to transmit the first recognition result to a server connected to one or more external electronic devices capable of recognizing the wake-up word. The at least one processor may be configured to receive, from the server, a second recognition result for a user who uttered the wake-up word. The at least one processor may be configured to execute a designated function within the electronic device with respect to the user based on the second recognition result. The second recognition result may include identification information indicating the user, obtained from an external electronic device in which the user is registered among the one or more external electronic devices.

[0005] A method performed by an electronic device may include an operation of acquiring a voice signal. The method may include an operation of generating a first recognition result for a wake-up word from the voice signal including the wake-up word. The method may include an operation of transmitting the first recognition result to a server connected to one or more external electronic devices capable of recognizing the wake-up word. The method may include an operation of receiving, from the server, a second recognition result for a user who uttered the wake-up word. The method may include an operation of executing a designated function within the electronic device with respect to the user based on the second recognition result. The second recognition result may include identification information indicating the user, which is acquired from an external electronic device in which the user is registered among the one or more external electronic devices.

[0006] A non-transitory computer-readable storage medium may store one or more programs comprising instructions that, when executed by at least one processor of an electronic device including a communication circuit and a microphone, cause the device to acquire a voice signal through the microphone. The non-transitory computer-readable storage medium may store one or more programs comprising instructions that, when executed by the at least one processor, cause the device to generate a first recognition result for a wake-up word from the voice signal including the wake-up word. The non-transitory computer-readable storage medium may store one or more programs comprising instructions that, when executed by the at least one processor, cause the device to transmit the first recognition result to a server connected to one or more external electronic devices capable of recognizing the wake-up word. The non-transitory computer-readable storage medium may store one or more programs comprising instructions that, when executed by the at least one processor, cause the device to receive, from the server, a second recognition result for a user who uttered the wake-up word. The non-transitory computer-readable storage medium may store one or more programs including instructions that, when executed by the at least one processor, cause the electronic device to execute a designated function with respect to the user based on the second recognition result. The second recognition result may include identification information indicating the user obtained from an external electronic device in which the user is registered among the one or more external electronic devices.

[0007] An electronic device may include a communication circuit. The electronic device may include a microphone. The electronic device may include at least one processor. The at least one processor may be configured to acquire a voice signal through the microphone. The at least one processor may be configured to generate a first recognition result for a wake-up word from the voice signal including the wake-up word. The at least one processor may be configured to broadcast the first recognition result to one or more external electronic devices capable of recognizing the wake-up word. The at least one processor may be configured to receive a second recognition result for the wake-up word broadcast from an external electronic device in which the user is registered among the one or more external electronic devices, and a third recognition result for the user who uttered the wake-up word. The at least one processor may be configured to execute a designated function within the electronic device with respect to the user based on the third recognition result. The third recognition result may include identification information indicating the user.

[0008] A method performed by an electronic device may include an operation of acquiring a voice signal. The method may include an operation of generating a first recognition result for a wake-up word from the voice signal including the wake-up word. The method may include an operation of broadcasting the first recognition result to one or more external electronic devices capable of recognizing the wake-up word. The method may include an operation of receiving a second recognition result for the wake-up word broadcast from an external electronic device in which the user is registered among the one or more external electronic devices and a third recognition result for a user who uttered the wake-up word. The method may include an operation of executing a designated function within the electronic device with respect to the user based on the third recognition result. The third recognition result may include identification information indicating the user.

[0009] A non-transitory computer-readable storage medium may store one or more programs comprising instructions that, when executed by at least one processor of an electronic device including a communication circuit and a microphone, cause the device to acquire a voice signal through the microphone. The non-transitory computer-readable storage medium may store one or more programs comprising instructions that, when executed by the at least one processor, cause the device to generate a first recognition result for a wake-up word from the voice signal including the wake-up word. The non-transitory computer-readable storage medium may store one or more programs comprising instructions that, when executed by the at least one processor, cause the device to broadcast the first recognition result to one or more external electronic devices capable of recognizing the wake-up word. The non-transitory computer-readable storage medium may store one or more programs including instructions that, when executed by the at least one processor, cause the electronic device to receive a second recognition result for the call word broadcast from an external electronic device in which the user is registered among the one or more external electronic devices and a third recognition result for the user who uttered the call word. The non-transitory computer-readable storage medium may store one or more programs including instructions that, when executed by the at least one processor, cause the electronic device to execute a designated function with respect to the user based on the third recognition result. The third recognition result may include identification information indicating the user.

[0010] An electronic device may include a communication circuit. The electronic device may include a microphone. The electronic device may include at least one processor. The at least one processor may be configured to acquire a voice signal through the microphone. The at least one processor may be configured to identify a user who utters the voice signal, including a wake-up word, from the voice signal. The at least one processor may be configured to transmit a signal including a first recognition result for the wake-up word and a second recognition result for the user to a server connected to one or more external electronic devices capable of recognizing the wake-up word, based on identifying the user as a user registered with the electronic device. The first recognition result may include at least one of a recognition accuracy value of the wake-up word in the voice signal identified by the electronic device, a sound power level of the voice signal including the wake-up word, a signal-to-noise ratio (SNR) of the voice signal, or a timing at which the wake-up word is acquired. The second recognition result may include at least one of the identification information of the user who uttered the call word, group information including the user, or the recognition accuracy value of the user.

[0011] A method performed by an electronic device may include an operation of acquiring a voice signal. The method may include an operation of identifying a user who utters the voice signal, from the voice signal including a wake-up word. The method may include an operation of transmitting a signal including a first recognition result for the wake-up word and a second recognition result for the user, based on identification of the user as a user registered with the electronic device, to a server connected to one or more external electronic devices capable of recognizing the wake-up word. The first recognition result may include at least one of a recognition accuracy value of the wake-up word in the voice signal identified by the electronic device, a sound power level of the voice signal including the wake-up word, a signal-to-noise ratio (SNR) of the voice signal, or a timing of acquiring the voice signal. The second recognition result may include at least one of identification information of the user who uttered the wake-up word, group information including the user, or a recognition accuracy value of the user.

[0012] A non-transitory computer-readable storage medium may store one or more programs comprising instructions that, when executed by at least one processor of an electronic device including a communication circuit and a microphone, cause the electronic device to acquire a voice signal through the microphone. The non-transitory computer-readable storage medium may store one or more programs comprising instructions that, when executed by the at least one processor, cause the electronic device to identify a user who utters the voice signal from the voice signal including a wake-up word. The non-transitory computer-readable storage medium may store one or more programs comprising instructions that, when executed by the at least one processor, cause the electronic device to transmit a signal including a first recognition result for the wake-up word and a second recognition result for the user to a server connected to one or more external electronic devices capable of recognizing the wake-up word, based on identifying that the user is a user registered in the electronic device. The first recognition result may include at least one of a recognition accuracy value of the call word in the voice signal identified by the electronic device, a sound power level of the voice signal including the call word, a signal to noise ratio (SNR) of the voice signal, or a timing at which the voice signal was acquired. The second recognition result may include at least one of the identification information of the user who uttered the call word, group information including the user, or a recognition accuracy value of the user.

[0013] FIG. 1 is a block diagram of an electronic device within a network environment according to various embodiments.

[0014] Figure 2a illustrates an example of a method for recognizing a wake up word and a speaker based on a voice signal.

[0015] Figure 2b illustrates an example of a method for registering a speaker based on a voice signal.

[0016] FIG. 2c illustrates an example of a method in which multiple electronic devices acquire a voice signal and share recognition results for the acquired voice signal.

[0017] Figure 3 illustrates an example of how an electronic device recognizes a speaker using an external electronic device.

[0018] FIG. 4 illustrates an example of a multiple device wake-up (MDW) environment including an electronic device and one or more external electronic devices.

[0019] FIG. 5 illustrates an example of an operational flow for a method in which an electronic device including a speaker recognition model recognizes a wake word in a voice signal.

[0020] FIG. 6 illustrates an example of an operational flow for a method for an electronic device that does not include a speaker recognition model to recognize a wake word in a voice signal.

[0021] Figure 7 illustrates an example of an operational flow for how an electronic device generates a speaker recognition model.

[0022] Figure 8 illustrates an example of an operational flow for a method in which an electronic device recognizes a speaker using an external electronic device.

[0023] FIG. 9 is a block diagram illustrating an integrated intelligence system according to various embodiments.

[0024] FIG. 10 is a diagram showing the form in which relationship information between concepts and operations according to various embodiments is stored in a database.

[0025] FIG. 11 is a diagram illustrating a screen for processing voice input received through an intelligent app by an electronic device according to various embodiments.

[0026] The terms used in this disclosure are used only to describe specific embodiments and may not be intended to limit the scope of other embodiments. The singular expression may include plural expressions unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as commonly understood by those of ordinary skill in the art described in this disclosure. Terms defined in general dictionaries among the terms used in this disclosure may be interpreted as having the same or similar meaning in the context of the relevant technology, and shall not be interpreted in an idealized or overly formal sense unless explicitly defined in this disclosure. In some cases, even if a term is defined in this disclosure, it cannot be interpreted to exclude embodiments of the present disclosure.

[0027] The various embodiments of the present disclosure described below illustrate a hardware-based approach as an example. However, since the various embodiments of the present disclosure include techniques utilizing both hardware and software, the various embodiments of the present disclosure do not exclude a software-based approach.

[0028] In addition, in the present disclosure, expressions such as "more than" or "less than" may be used to determine whether a specific condition is satisfied or fulfilled. However, this is merely a description for expressing an example and does not exclude descriptions such as "more than" or "less than." Conditions described as "more than" may be replaced with "more than," conditions described as "less than," and conditions described as "more than and less than" may be replaced with "more than and less than." In addition, hereinafter, "A" to "B" mean at least one of the elements from A (including A) to B (including B).

[0029] FIG. 1 is a block diagram of an electronic device within a network environment according to various embodiments.

[0030] Referring to FIG. 1, in a network environment (100), an electronic device (101) may communicate with an electronic device (102) via a first network (198) (e.g., a short-range wireless communication network), or may communicate with at least one of an electronic device (104) or a server (108) via a second network (199) (e.g., a long-range wireless communication network). According to one embodiment, the electronic device (101) may communicate with the electronic device (104) via the server (108). According to one embodiment, the electronic device (101) may include a processor (120), a memory (130), an input module (150), an audio output module (155), a display module (160), an audio module (170), a sensor module (176), an interface (177), a connection terminal (178), a haptic module (179), a camera module (180), a power management module (188), a battery (189), a communication module (190), a subscriber identification module (196), or an antenna module (197). In some embodiments, the electronic device (101) may omit at least one of these components (e.g., the connection terminal (178)), or may have one or more other components added. In some embodiments, some of these components (e.g., the sensor module (176), the camera module (180), or the antenna module (197)) may be integrated into one component (e.g., the display module (160)).

[0031] The processor (120) may, for example, execute software (e.g., a program (140)) to control at least one other component (e.g., a hardware or software component) of the electronic device (101) connected to the processor (120) and perform various data processing or calculations. According to one embodiment, as at least a part of the data processing or calculations, the processor (120) may store commands or data received from other components (e.g., a sensor module (176) or a communication module (190)) in a volatile memory (132), process the commands or data stored in the volatile memory (132), and store result data in a non-volatile memory (134). According to one embodiment, the processor (120) may include a main processor (121) (e.g., a central processing unit or an application processor) or a secondary processor (123) (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor)) that can operate independently or together therewith. For example, if the electronic device (101) includes a main processor (121) and a secondary processor (123), the secondary processor (123) may be configured to use less power than the main processor (121) or to be specialized for a specified function. The secondary processor (123) may be implemented separately from the main processor (121) or as a part thereof.

[0032] The auxiliary processor (123) may control at least a portion of functions or states associated with at least one component (e.g., a display module (160), a sensor module (176), or a communication module (190)) of the electronic device (101), for example, on behalf of the main processor (121) while the main processor (121) is in an inactive (e.g., sleep) state, or together with the main processor (121) while the main processor (121) is in an active (e.g., application execution) state. In one embodiment, the auxiliary processor (123) (e.g., an image signal processor or a communication processor) may be implemented as a part of another functionally related component (e.g., a camera module (180) or a communication module (190)). In one embodiment, the auxiliary processor (123) (e.g., a neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. The artificial intelligence models may be generated through machine learning. This learning can be performed, for example, on the electronic device (101) itself where the artificial intelligence model is executed, or can be performed through a separate server (e.g., server (108)). The learning algorithm can include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model can include multiple artificial neural network layers.The artificial neural network may be one of a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to, or alternatively to, a hardware structure, an artificial intelligence model may include a software structure.

[0033] The memory (130) can store various data used by at least one component (e.g., processor (120) or sensor module (176)) of the electronic device (101). The data can include, for example, software (e.g., program (140)) and input data or output data for commands related thereto. The memory (130) can include volatile memory (132) or non-volatile memory (134).

[0034] The program (140) may be stored as software in the memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0035] The input module (150) can receive commands or data to be used in a component of the electronic device (101) (e.g., a processor (120)) from an external source (e.g., a user) of the electronic device (101). The input module (150) can include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0036] The audio output module (155) can output audio signals to the outside of the electronic device (101). The audio output module (155) can include, for example, a speaker or a receiver. The speaker can be used for general purposes, such as multimedia playback or recording playback. The receiver can be used to receive incoming calls. In one embodiment, the receiver can be implemented separately from the speaker or as part of the speaker.

[0037] The display module (160) can visually provide information to an external party (e.g., a user) of the electronic device (101). The display module (160) may include, for example, a display, a holographic device, or a projector and a control circuit for controlling the device. In one embodiment, the display module (160) may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of a force generated by the touch.

[0038] The audio module (170) can convert sound into an electrical signal, or vice versa, convert an electrical signal into sound. According to one embodiment, the audio module (170) can acquire sound through the input module (150), output sound through the sound output module (155), or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphone) directly or wirelessly connected to the electronic device (101).

[0039] The sensor module (176) can detect the operating status (e.g., power or temperature) of the electronic device (101) or the external environmental status (e.g., user status) and generate an electrical signal or data value corresponding to the detected status. According to one embodiment, the sensor module (176) can include, for example, a gesture sensor, a gyro sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0040] The interface (177) may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device (101) with an external electronic device (e.g., the electronic device (102)). In one embodiment, the interface (177) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0041] The connection terminal (178) may include a connector through which the electronic device (101) may be physically connected to an external electronic device (e.g., electronic device (102)). According to one embodiment, the connection terminal (178) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0042] A haptic module (179) can convert electrical signals into mechanical stimuli (e.g., vibration or movement) or electrical stimuli that a user can perceive through tactile or kinesthetic sensations. In one embodiment, the haptic module (179) can include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0043] The camera module (180) can capture still images and videos. According to one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0044] The power management module (188) can manage power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented, for example, as at least a part of a power management integrated circuit (PMIC).

[0045] A battery (189) may power at least one component of the electronic device (101). In one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0046] The communication module (190) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device (101) and an external electronic device (e.g., electronic device (102), electronic device (104), or server (108)), and the performance of communication through the established communication channel. The communication module (190) may operate independently from the processor (120) (e.g., application processor) and may include one or more communication processors that support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module (190) may include a wireless communication module (192) (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (194) (e.g., a local area network (LAN) communication module, or a power line communication module). Among these communication modules, the corresponding communication module can communicate with an external electronic device (104) via a first network (198) (e.g., a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network (199) (e.g., a long-range communication network such as a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a LAN or WAN)). These various types of communication modules can be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module (192) can verify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) by using subscriber information (e.g., an international mobile subscriber identity (IMSI)) stored in the subscriber identification module (196).

[0047] The wireless communication module (192) can support 5G networks and next-generation communication technologies following the 4G network, such as NR access technology (new radio access technology). The NR access technology can support high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and connection of multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low-latency communications)). The wireless communication module (192) can support, for example, a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate. The wireless communication module (192) can support various technologies for securing performance in a high-frequency band, such as beamforming, massive multiple-input and multiple-output (MIMO), full dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large scale antenna. The wireless communication module (192) can support various requirements specified in the electronic device (101), an external electronic device (e.g., the electronic device (104)), or a network system (e.g., the second network (199)). According to one embodiment, the wireless communication module (192) can support a peak data rate (e.g., 20 Gbps or more) for eMBB realization, a loss coverage (e.g., 164 dB or less) for mMTC realization, or a U-plane latency (e.g., 0.5 ms or less for downlink (DL) and uplink (UL), or 1 ms or less for round trip) for URLLC realization.

[0048] The antenna module (197) can transmit or receive signals or power to or from an external device (e.g., an external electronic device). In one embodiment, the antenna module (197) may include an antenna including a radiator formed of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). In one embodiment, the antenna module (197) may include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network, such as the first network (198) or the second network (199), may be selected from the plurality of antennas by, for example, the communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device through the selected at least one antenna. In some embodiments, in addition to the radiator, another component (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module (197).

[0049] According to various embodiments, the antenna module (197) may form a mmWave antenna module. According to one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent a first side (e.g., a bottom side) of the printed circuit board and capable of supporting a designated high-frequency band (e.g., a mmWave band), and a plurality of antennas (e.g., an array antenna) disposed on or adjacent a second side (e.g., a top side or a side side) of the printed circuit board and capable of transmitting or receiving signals in the designated high-frequency band.

[0050] At least some of the above components can be interconnected and exchange signals (e.g., commands or data) with each other via a communication method between peripheral devices (e.g., a bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)).

[0051] According to one embodiment, commands or data may be transmitted or received between the electronic device (101) and an external electronic device (104) via a server (108) connected to a second network (199). Each of the external electronic devices (102 or 104) may be the same or a different type of device as the electronic device (101). According to one embodiment, all or part of the operations executed in the electronic device (101) may be executed in one or more of the external electronic devices (102, 104, or 108). For example, when the electronic device (101) is to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device (101) may, instead of or in addition to executing the function or service itself, request one or more external electronic devices to perform the function or at least a part of the service. One or more external electronic devices that receive the request may execute at least a portion of the requested function or service, or an additional function or service related to the request, and transmit the result of the execution to the electronic device (101). The electronic device (101) may process the result as is or additionally and provide it as at least a portion of a response to the request. For this purpose, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used, for example. The electronic device (101) may provide an ultra-low latency service by using distributed computing or mobile edge computing, for example. In another embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server utilizing machine learning and / or a neural network. According to one embodiment, the external electronic device (104) or the server (108) may be included in the second network (199).The electronic device (101) can be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology.

[0052] Figure 2a illustrates an example of a method for recognizing a wake-up word and a speaker based on a voice signal.

[0053] FIG. 2A illustrates an example (200) of a method in which an electronic device (101) performs recognition of a call word and recognition of a speaker based on a voice signal (210). The electronic device (101) of FIG. 2A may represent an example of the electronic device (101) of FIG. 1.

[0054] Referring to example (200), the electronic device (101) can obtain a voice signal (210). For example, the electronic device (101) can obtain the voice signal (210) from outside the electronic device (101) through a microphone (hereinafter, microphone) (e.g., input module (150) of FIG. 1). For example, the voice signal (210) can include speech. For example, the voice signal (210) can also include the voice, noise, or background sound. For example, the voice can be spoken by a user of the electronic device (101) or an external electronic device (e.g., electronic devices (102, 104) of FIG. 1). For example, the voice signal (210) can be referred to as a sound signal, a signal, a speech signal, a wake-up signal, an external sound, or a user signal.

[0055] Referring to example (200), the electronic device (101) can perform feature extraction (215) for a voice signal (210). For example, the electronic device (101) can extract a plurality of feature values ​​for the voice signal (210). Although not shown in example (200), the electronic device (101) can enhance the voice feature of the voice signal (210) before performing feature extraction (215) for the voice signal (210). For example, the operation of enhancing the voice feature can include at least one of operations of removing noise from the voice signal (210), enhancing the voice portion of the voice signal (210), and normalizing the volume of the voice portion. After enhancing the voice feature, the electronic device (101) can obtain the plurality of feature values ​​for the voice signal (210). For example, the electronic device (101) can obtain the plurality of feature values ​​based on an MFCC (mel frequency cepstral coefficient) transformation algorithm. The electronic device (101) can obtain a spectrum by applying a fast-Fourier transform (FFT) for each frame to the voice signal (210). The electronic device (101) can obtain the spectrum for the frequency domain by applying the FFT to the voice signal (210). The electronic device (101) can obtain a mel spectrum by applying a mel filter bank to the spectrum. The electronic device (101) can obtain the mel spectrum based on a mel scale that represents the relationship between the frequency domain and a low frequency band recognized by an actual human.The electronic device (101) can obtain MFCCs by applying cepstral analysis to the mel spectrum. The MFCCs can be referred to as the feature values. For example, the electronic device (101) can obtain the feature values, which are a portion of the total feature values, which are peaks obtained based on the cepstral analysis.

[0056] Referring to example (200), the electronic device (101) can recognize a wake-up word from a voice signal (210) through a wake-up word recognition engine (220). For example, the electronic device (101) can recognize the wake-up word through the wake-up word recognition engine (220) based on the plurality of feature values. For example, the wake-up word recognition engine (220) can be implemented by hardware, software, or a combination of hardware and software for recognizing the wake-up word. For example, the electronic device (101) can identify the wake-up word included in the voice signal (210) using the wake-up word recognition engine (220) and the wake-up word recognition model (223). For example, the wake-up word recognition model (223) can include a statistical model trained to identify (or recognize) the wake-up word. For example, the statistical model may include an artificial neural network model, a hidden markov model (HMM), a Gaussian mixture model (GMM), a support vector machine (SVM), and a vector quantizer (VQ). For example, the electronic device (101) may implement the call word recognition engine (220) and the speaker recognition engine (225) as a single recognition algorithm (e.g., speaker-dependent speech recognition). The electronic device (101) may perform the speaker-dependent speech recognition that does not distinguish between call word recognition and speaker recognition by using the speaker-dependent speech recognition model. For example, based on the speaker-dependent speech recognition, the electronic device (101) may obtain call word recognition information (e.g., a first recognition result hereinafter) and speaker recognition information (e.g., a second recognition result hereinafter). For example, the call word may include a designated word or sentence used to indicate a specific electronic device.The above-described wake word may be used to execute a voice recognition function of the indicated specific electronic device. For example, the electronic device (101) may recognize that the user is calling (or instructing) the electronic device (101) based on identifying that the wake word is included in the voice signal (210). For example, the wake word may be preset in the electronic device (101) or may be set by the user. For example, the electronic device (101) may generate (or obtain) a recognition result for the wake word in the voice signal (210) based on the wake word recognition engine (220) and the wake word recognition model (223). Hereinafter, the recognition result for the wake word may be referred to as a first recognition result, a wake word recognition result, wake word recognition information, or wake word information. The first recognition result may be defined as shown in the table below.

[0057]

[0058] Referring to the above table, the first recognition result may include a recognition score, volume (speech power, loudness, sound pressure level), signal-to-noise ratio (SNR), and time. However, the embodiments of the present disclosure are not limited thereto. For example, the first recognition result may include only the volume. Alternatively, for example, the first recognition result may include information regarding priorities between electronic devices in addition to the information exemplified in the above table. For example, the priority may indicate the priority for responding to the wake word. For example, the priority may be set by a user of the electronic device.

[0059] For example, the recognition score may represent recognition information for the call word. For example, the electronic device (101) may obtain the recognition score, which represents the degree of recognition of the call word in the voice signal (210) as a probability value. For example, the electronic device (101) may obtain the recognition score based on the call word recognition engine (220). The recognition score may be referred to as the reliability (or recognition reliability) of the call word, or a recognition accuracy value.

[0060] For example, the volume may represent the sound power level of the speech signal (210). For example, the electronic device (101) may identify the level of the speech signal (210). The volume or sound power level may be used to identify (or recognize) the electronic device that is located closest to the user who uttered the speech signal (210). For example, the volume may be referred to as speech power, sound power, or sound power level.

[0061] For example, the SNR may represent a ratio between a signal (e.g., the voice) within a voice signal (210) and the noise. For example, the electronic device (101) may identify the noise level of the environment (or space) in which the voice signal (210) was uttered based on the SNR. For example, the time may represent the timing at which the voice signal (210) was acquired.

[0062] For example, the electronic device (101) may generate device information associated with the first recognition result. The device information may include information about the electronic device (101) that acquired the first recognition result. For example, the device information may include a device name, a device type, a device identity (device ID), a wake-up word, and an IP (internet protocol address) of the device. For example, the device name may include a model name of the electronic device (101). For example, the device type may include a type of the electronic device (101) (e.g., TV). For example, the device identifier may include a unique identification number of the electronic device (101). For example, the wake-up word may include a name of a wake-up word set for the electronic device (101). The contents of the above-described table are merely examples for the convenience of explanation, and embodiments of the present disclosure are not limited thereto. For example, the device information may be transmitted or received (i.e., shared) together with the first recognition result.

[0063] Referring to example (200), the electronic device (101) can recognize the speaker (or user) who uttered the voice signal (210) through the speaker recognition engine (225). For example, the speaker recognition engine (225) can be implemented by hardware, software, or a combination of hardware and software for recognizing the speaker. For example, the electronic device (101) can identify the speaker using the speaker recognition engine (225) and the speaker recognition model (228). For example, the speaker recognition model (228) can include a statistical model trained to identify (or recognize) the speaker. For example, the statistical model can include an artificial intelligence model (AI model) or an artificial neural network model. For example, the speaker can represent a user registered with the electronic device (101). For example, the electronic device (101) may register the speaker based on a plurality of voice signals uttered by the speaker. The registration may include storing information about the speaker within the electronic device (101). Specific details related thereto are described below in FIG. 2B. For example, the electronic device (101) may generate (or obtain) a recognition result for the speaker. Hereinafter, the recognition result for the speaker may be referred to as a second recognition result. For example, the second recognition result may be referred to as a speaker recognition result, speaker recognition information, or speaker information.

[0064] Referring to example (200), the electronic device (101) can generate a recognition result (230). The recognition result (230) can include the first recognition result and the second recognition result. However, the embodiments of the present disclosure are not limited thereto. For example, if the electronic device (101) does not include a speaker recognition engine (225), the recognition result (230) can include only the first recognition result. For example, the electronic device (101) can implement the call word recognition engine (220) and the speaker recognition engine (225) as a single recognition algorithm (e.g., speaker-dependent speech recognition). In the case of an electronic device (101) that uses a single speaker-dependent speech recognition, the first recognition result can include speaker recognition information (i.e., the second recognition result). In FIG. 2A, an example (200) of an electronic device (101) generating (or obtaining) a recognition result (230) is illustrated, but the embodiments of the present disclosure are not limited thereto. For example, the electronic device (101) may share the generated recognition result (230) with one or more external electronic devices. For example, the sharing may include transmitting (or broadcasting) information about the recognition result (230) to the one or more external electronic devices and receiving the recognition result of the one or more external electronic devices from the one or more external electronic devices. Specific details related thereto are described below in FIG. 2C.

[0065] Figure 2b illustrates an example of a method for registering a speaker based on a voice signal.

[0066] FIG. 2b illustrates an example (240) of a method for an electronic device (101) to register a speaker based on a voice signal (210). The electronic device (101) of FIG. 2b may represent an example of the electronic device (101) of FIG. 1.

[0067] Referring to example (240), the electronic device (101) may obtain a voice signal (210) and perform feature extraction (215) on the obtained voice signal (210). For specific details related thereto, the contents of FIG. 2A may be substantially identically referenced. For example, the electronic device (101) may obtain multiple voice signals (210) including the same word or sentence from the user. For example, the same word or sentence may represent a wake word. Referring to example (240), the electronic device (101) may perform model training (245) based on multiple feature values ​​obtained from the voice signal (210). For example, the model training (245) may include training a statistical model (e.g., an artificial intelligence model) for registering the speaker with respect to the electronic device (101). For example, the electronic device (101) may register the speaker corresponding to the account information by performing model training (245) on the account information based on the plurality of feature values. For example, the account information may include information for identifying the speaker.

[0068] Referring to example (240), the electronic device (101) can register the speaker by performing model training (245) using a specified number of voice signals including a voice signal (210). The registration of the speaker can indicate that the electronic device (101) that has acquired the voice signal (210) uttered by the speaker can recognize the speaker based on the voice signal (210). Although example (240) describes an example in which the model training (245) is performed based on the specified number of voice signals, the embodiments of the present disclosure are not limited thereto. For example, the electronic device (101) can also perform model training (245) based on a voice signal of a specified length of time.

[0069] FIG. 2c illustrates an example of a method in which multiple electronic devices acquire a voice signal and share recognition results for the acquired voice signal.

[0070] FIG. 2C illustrates an example (250) of a method in which each of a plurality of electronic devices (260) acquires a voice signal (210) and shares the recognition results for the acquired voice signal (210). The electronic device (101) of FIG. 2C may represent an example of the electronic device (101) of FIG. 1.

[0071] Referring to example (250), each of the plurality of electronic devices (260) can obtain a voice signal (210). For example, the plurality of electronic devices (260) can include a first electronic device (261), a second electronic device (262), and an Nth electronic device (263). For example, the first electronic device (261) can represent an example of the electronic device (101) of FIG. 1. The plurality of electronic devices (260) can represent electronic devices located within the same space. For example, the same space can be defined based on a distance that is connected to the same access point (AP) or connectable based on short-range communication (e.g., Bluetooth or Wi-Fi). For example, the plurality of electronic devices (260) can include electronic devices connected to the same AP or electronic devices connectable based on short-range communication. The plurality of electronic devices (260) can have the same wake word set (or used). For example, the above call word may represent a call word included in a voice signal (210).

[0072] Referring to example (250), a plurality of electronic devices (260) can share a recognition result for a voice signal (210). For example, the recognition result can include the first recognition result. Or, for example, the recognition result can include the first recognition result and the second recognition result. Referring to example (250), a first electronic device (261) can obtain a voice signal (210) uttered by a speaker (or user) and generate a recognition result (271) based on the obtained voice signal (210). The first electronic device (261) can transmit (or broadcast) the recognition result (271) to a second electronic device (262) and an Nth electronic device (263). The second electronic device (262) and the Nth electronic device (263) can receive (or obtain) the recognition result (271). In addition, referring to example (250), the second electronic device (262) can obtain a voice signal (210) uttered by a speaker (or user) and generate a recognition result (272) based on the obtained voice signal (210). The second electronic device (262) can transmit (or broadcast) the recognition result (272) to the first electronic device (261) and the Nth electronic device (263). The first electronic device (261) and the Nth electronic device (263) can receive (or obtain) the recognition result (272). In addition, referring to example (250), the Nth electronic device (263) can obtain a voice signal (210) uttered by a speaker (or user) and generate a recognition result (273) based on the obtained voice signal (210). The Nth electronic device (263) can transmit (or broadcast) the recognition result (273) to the first electronic device (261) and the second electronic device (262). The first electronic device (261) and the second electronic device (262) can receive (or obtain) the recognition result (273).

[0073] For example, each of the plurality of electronic devices (260) can identify the electronic device indicated by the voice signal (210) based on the acquired recognition results. For example, each of the plurality of electronic devices (260) can identify the electronic device with the highest volume level of the voice signal (210) as the electronic device indicated by the voice signal (210) based on the acquired recognition results. The volume level can be compared through a corrected (or processed) value for the voice signal (210) acquired by each of the plurality of electronic devices (260). The electronic device indicated by the voice signal (210) can indicate the electronic device that the speaker who uttered the voice signal (210) intends to execute the function.

[0074] Referring to FIGS. 2A to 2C , the electronic device (101) may acquire a voice signal, and based on processing the acquired voice signal, recognize a call word and identify whether the speaker is a registered speaker. However, in one example, in the case of an electronic device (101) that does not include a speaker recognition module (e.g., the speaker recognition engine (225) and the speaker recognition model (228) of FIG. 2A) or in which an acoustic model for registering a speaker has not been created, it may be difficult for the electronic device (101) to identify whether the speaker is a registered speaker. In the electronic device and method according to embodiments of the present disclosure, when a plurality of electronic devices using the same call word exist in the same space (e.g., a range of influence of a call word spoken by a user, a range of activation of a device (e.g., the electronic device (101)) by a call word spoken by a user), some of the electronic devices may provide a speaker recognition-based service based on a recognition result (e.g., a second recognition result) of the speaker who spoke the call word. For example, the speaker recognition-based service may include the execution of a designated function, such as an application executed for a specific speaker or a specific UI display. For example, the application executed for the specific speaker may include a software application requiring authentication of the speaker. However, the embodiments of the present disclosure are not limited thereto. For example, the speaker recognition-based service may include the execution of at least one instruction stored in the electronic device (101), the execution of an arbitrary operation, or the execution of a function set by the user.For example, when a plurality of electronic devices using the same call word exist in the same space, an electronic device among the plurality of electronic devices, in which registration of a speaker who uttered the call word has been completed, shares speaker information (e.g., the second recognition result) recognized by the electronic device among the plurality of electronic devices with another electronic device other than the electronic device, thereby providing the speaker recognition-based service through the other electronic device. The other electronic device may be an electronic device in which registration of the speaker has not been completed or which does not include a speaker recognition module (e.g., a speaker recognition engine and an acoustic model).

[0075] Figure 3 illustrates an example of how an electronic device recognizes a speaker using an external electronic device.

[0076] FIG. 3 illustrates an example (300) of a method in which an electronic device (101) recognizes a speaker (310) using an external electronic device (103). The electronic device (101) of FIG. 3 may represent an example of the electronic device (101) of FIG. 1.

[0077] Referring to example (300), the external electronic device (103) can obtain a voice signal (315) uttered by a speaker (310). For example, the external electronic device (103) can obtain a voice signal (315) including a "call word." In example (300), the "call word" is described, but the embodiments of the present disclosure are not limited thereto. For example, the "call word" can include a word or sentence designated for the electronic device (101) and the external electronic device (103). In addition, for example, the voice signal (315) can include a command word in addition to the call word. For example, the call word can be used to execute a voice recognition function of the electronic device (101) or the external electronic device (103). For example, the command may be used to command a specified function according to the command within a state in which the voice recognition function of the external electronic device (103) or the electronic device (101) is activated.

[0078] Referring to example (300), the external electronic device (103) can recognize the call word and the speaker (310) based on the voice signal (315). For example, the external electronic device (103) can generate a first recognition result for the call word based on the voice signal (315). In addition, for example, the external electronic device (103) can generate a second recognition result for the speaker (310) based on the voice signal (315). At this time, the external electronic device (103) can represent an electronic device in which the speaker (310) is registered (i.e., a speaker recognition model is generated and information about the speaker (310) is stored). The external electronic device (103) can transmit a recognition result (320) including the first recognition result and the second recognition result to the electronic device (101). In the example (300) of FIG. 3, an example is shown in which an external electronic device (103) transmits a recognition result (320) to an electronic device (101), but the embodiments of the present disclosure are not limited thereto. For example, the electronic device (101) may acquire a voice signal (315) uttered by a speaker (310) and generate a recognition result based on the acquired voice signal (315). The electronic device (101) may transmit the recognition result to the external electronic device (103). Accordingly, the external electronic device (103) may receive the recognition result. In other words, in the example (300) of FIG. 3, the external electronic device (103) and the electronic device (101) may share the recognition result. In this case, the recognition result transmitted by the electronic device (101) may only include a first recognition result for the wake word. This may be because the electronic device (101) does not include a speaker recognition module or is an electronic device in which the speaker is not registered.

[0079] According to one embodiment, the external electronic device (103) can identify whether the electronic device that the speaker (310) calls is the external electronic device (103) based on the recognition result (320). The target can be referred to as an indication target. For example, the external electronic device (103) can identify whether the electronic device that the speaker (310) wants to recognize through the call word is the external electronic device (103) based on the first recognition result of the recognition result (320). At this time, the external electronic device (103) can identify whether the target is the external electronic device (103) based on the recognition result received from the electronic device (101) together with the first recognition result of the recognition result (320). In the example (300) of FIG. 3, it is assumed that the target that the speaker (310) calls is the electronic device (101). Accordingly, the external electronic device (103) can identify that the target is not the external electronic device (103) based on the first recognition result of the recognition result (320) and the recognition result received from the electronic device (101).

[0080] According to one embodiment, the electronic device (101) can identify whether the target is the electronic device (101) based on the first recognition result of the recognition result (320) and the recognition result generated by the electronic device (101). For example, the electronic device (101) can identify the electronic device with the maximum volume level based on the first recognition result received from the external electronic device (103) and the recognition result identified by the electronic device (101). In the example (300) of FIG. 3, the electronic device with the maximum volume level may be the electronic device (101).

[0081] According to one embodiment, the electronic device (101) can identify whether the recognition result (320) includes the second recognition result. For example, if the recognition result (320) includes the second recognition result, the electronic device (101) can provide a speaker recognition service. According to one embodiment, the electronic device (101) can execute a designated function. For example, the designated function can be included in the speaker recognition service. For example, the electronic device (101) can display a user interface (UI) (330) as the designated function. For example, the UI (330) can include a visual object representing the sentence "Hello, user." The user can refer to the speaker (310).

[0082] Referring to example (300), the electronic device (101) may provide the speaker recognition service based on speaker information received from an external electronic device (103), even though the electronic device does not include a speaker recognition module (or speaker recognition model) for recognizing a speaker (310) or is an electronic device in which information about the speaker (310) is not registered. Referring to the above, the speaker recognition service may be provided even in the electronic device (101) that is available to multiple users, not just a device used by a specific user. For example, the device available to multiple users may be referred to as a public device or a shared device. For example, the device used only by the specific user may be referred to as a personal device. However, the embodiments of the present disclosure are not limited thereto. For example, even if the device is used only by the specific user, the embodiments of the present disclosure may be applied even when registering other users and providing a speaker recognition service for the other users.

[0083] FIG. 4 illustrates an example of a multiple device wake-up (MDW) environment including an electronic device and one or more external electronic devices.

[0084] FIG. 4 illustrates an example of an MDW environment (400) including an electronic device (101), an external electronic device (103), and an external electronic device (105). For example, the MDW environment (400) may represent a case where multiple electronic devices are configured (or used) with the same wake word. For example, the multiple electronic devices may be capable of recognizing the wake word. For example, the multiple electronic devices may include the electronic device (101), the external electronic device (103), and the external electronic device (105). The MDW environment (400) of FIG. 4 is merely an example for convenience of explanation, and embodiments of the present disclosure are not limited thereto. For example, the MDW environment (400) may include a greater number of electronic devices, or may include only two electronic devices.

[0085] Referring to FIG. 4, according to one embodiment, the MDW environment (400) may include an electronic device (101), an external electronic device (103), an external electronic device (105), and a server (107). For example, the electronic device (101) may represent an example of a device that does not include a speaker recognition module. For example, the external electronic device (103) may represent an example of a device that includes the speaker recognition module and in which speaker registration has been completed. For example, the external electronic device (105) may represent an example of a device that includes the speaker recognition module but in which speaker registration has not been completed. The device in which speaker registration has been completed may represent a device in which a speaker recognition model for the speaker has been created. For example, the server (107) may represent an example of an external electronic device that is connected to the electronic device (101), the external electronic device (103), and the external electronic device (105), and manages the electronic device (101), the external electronic device (103), and the external electronic device (105). For example, the server (107) may collect recognition results received from each of the electronic device (101), the external electronic device (103), and the external electronic device (105), and provide information about the recognition results to a specific electronic device that is a target of instruction based on the collected recognition results. In the above example, an example in which the server (107) provides the information to the specific electronic device that is a target of instruction is described, but the embodiments of the present disclosure are not limited thereto. For example, the server (107) may also provide information about the recognition results to all electronic devices connected to the server (107). According to one embodiment, the information on the recognition result provided by the server (107) may include at least one of a first recognition result for a call word received from each of the electronic devices connected to the server (107) and a second recognition result for a speaker.For example, the server (107) may obtain a first recognition result received from the electronic device (101), a first recognition result and a second recognition result received from the external electronic device (103), and a first recognition result received from the external electronic device (105), and provide the information including the obtained recognition results.

[0086] According to one embodiment, the electronic device (101) may include a microphone (411), a preprocessing unit (413), a call word recognition engine (415), and an MDW manager (417). Although not shown in FIG. 4, the electronic device (101) may include at least one processor and at least one communication circuit. For example, the at least one processor may control the at least one communication circuit, the microphone (411), the preprocessing unit (413), the call word recognition engine (415), and the MDW manager (417). For example, the at least one communication circuit may be used for the electronic device (101) to communicate with external electronic devices (103, 105) and the server (107). However, the embodiments of the present disclosure are not limited thereto. For example, the electronic device (101) may further include other components in addition to the microphone (411), the preprocessing unit (413), the call word recognition engine (415), the MDW manager (417), the at least one processor, and the at least one communication circuit.

[0087] According to one embodiment, the at least one processor of the electronic device (101) may include a hardware component for processing data based on one or more instructions. The hardware component for processing data may include, for example, an arithmetic and logic unit (ALU), a floating point unit (FPU), and a field programmable gate array (FPGA). As an example, the hardware component for processing data may include a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP), and / or a neural processing unit (NPU). The at least one processor may include at least a part of the processor (120) of FIG. 1.

[0088] For example, the at least one processor of the electronic device (101) may include various processing circuits and / or multiple processors. For example, the term "processor" as used herein, including in the claims, may include various processing circuits including at least one processor, one or more of which may be configured to individually and / or collectively perform the various functions described below in a distributed manner. As used herein, when "processor," "at least one processor," and "one or more processors" are described as being configured to perform various functions, these terms encompass, for example, and without limitation, situations where one processor performs some of the recited functions and other processor(s) perform other parts of the recited functions, and also situations where one processor may perform all of the recited functions. Additionally, the at least one processor may include a combination of processors that perform the various functions enumerated / disclosed, for example, in a distributed manner. At least one processor is capable of executing program instructions to accomplish or perform various functions.

[0089] For example, the electronic device (101) can acquire a voice signal from an external source through the microphone (411). For example, the voice signal may include a wake word. Or, for example, the voice signal may include the wake word and a command. The wake word may include a designated word or sentence registered in the electronic device (101).

[0090] For example, the electronic device (101) may perform processing on the voice signal through the preprocessing unit (413). For example, the electronic device (101) may extract a plurality of feature values ​​for the voice signal through the preprocessing unit (413) and enhance the features of the voice portion of the voice signal. The specific details related thereto may be substantially identically applied to the contents of FIG. 2A.

[0091] For example, the electronic device (101) can identify (or recognize) a call word included in the voice signal based on the call word recognition engine (415). For example, the electronic device (101) can generate a first recognition result for the call word identified based on the call word recognition engine (415).

[0092] For example, the electronic device (101) can share the first recognition result through the MDW manager (417). For example, the electronic device (101) can identify external electronic devices (103, 105) within the MDW environment (400) through the MDW manager (417). For example, the electronic device (101) can transmit (or provide) the first recognition result to the external electronic devices (103, 105). In addition, for example, the electronic device (101) can receive (or obtain) the recognition result from each of the external electronic devices (103, 105) through the MDW manager (417). Or, for example, the electronic device (101) can transmit (or provide) the first recognition result to the server (107) within the MDW environment (400) through the MDW manager (417). Additionally, for example, the electronic device (101) can receive (or acquire) information about recognition results of external electronic devices (103, 105) from a server (107) within the MDW environment (400) through the MDW manager (417).

[0093] For example, the electronic device (101) may deactivate the voice service until the device that is the target of the instruction within the MDW environment (400) is determined through the MDW manager (417). Alternatively, for example, the electronic device (101) may deactivate the voice service if another device (e.g., an external electronic device (103) or an external electronic device (105)) within the MDW environment (400) is not determined as the target of the instruction within the MDW environment (400). In other words, the electronic device (101) may be controlled to wait without activating the voice service before the target of the instruction is determined. For example, if the electronic device (101) within the MDW environment (400) is determined as the target of the instruction within the MDW manager (417), the electronic device (101) may activate the voice service and process a command included in a voice signal that is subsequently input.

[0094] Although not illustrated in FIG. 4, the electronic device (101) according to one embodiment may further include a memory. The memory may include a hardware component for storing data and / or instructions input to and / or output from the at least one processor. The memory may include, for example, a volatile memory such as a random-access memory (RAM), and / or a non-volatile memory such as a read-only memory (ROM). The volatile memory may include, for example, at least one of a dynamic RAM (DRAM), a static RAM (SRAM), a cache RAM, and a pseudo SRAM (PSRAM). The non-volatile memory may include, for example, at least one of a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), a flash memory, a hard disk, a compact disc, and an embedded multimedia card (eMMC). The above memory may include at least a portion of the memory (130) of FIG. 1.

[0095] Although not illustrated in FIG. 4, according to one embodiment, one or more instructions (or commands) representing operations and / or actions to be performed on data by the processor (501) of the electronic device (101) may be stored within the memory of the electronic device (101). A set of one or more instructions may be referred to as a program, firmware, an operating system, a process, a routine, a sub-routine, and / or an application. Hereinafter, when an application is installed within the electronic device (e.g., the electronic device (101)), it may mean that one or more instructions provided in the form of an application are stored within the memory, and that the one or more applications are stored in a format executable by the processor of the electronic device (e.g., a file having an extension designated by the operating system of the electronic device (101)).

[0096] According to one embodiment, the external electronic device (103) may include a microphone (431), a preprocessing unit (433), a call word recognition engine (435), a speaker recognition engine (437), a speaker registration module (439), and an MDW manager (441). Although not shown in FIG. 4, the external electronic device (103) may include a memory, at least one processor, and at least one communication circuit. For example, the at least one processor may control the at least one communication circuit, the microphone (431), the preprocessing unit (433), the call word recognition engine (435), the speaker recognition engine (437), the speaker registration module (439), and the MDW manager (441). For example, the at least one communication circuit may be used for the external electronic device (103) to communicate with the electronic device (101), the external electronic device (105), and the server (107). However, the embodiments of the present disclosure are not limited thereto. For example, the external electronic device (103) may further include a microphone (431), a preprocessor (433), a call word recognition engine (435), a speaker recognition engine (437), a speaker registration module (439), an MDW manager (441), and other components other than the at least one processor and the at least one communication circuit.

[0097] For example, the external electronic device (103) can obtain a voice signal from the outside through the microphone (431). For example, the voice signal may include a wake word. Or, for example, the voice signal may include the wake word and a command. The wake word may include a designated word or sentence registered in the external electronic device (103).

[0098] For example, the external electronic device (103) may perform processing on the voice signal through the preprocessing unit (433). For example, the external electronic device (103) may extract a plurality of feature values ​​for the voice signal through the preprocessing unit (433) and enhance the features of the voice portion of the voice signal. The specific details related thereto may be substantially identically applied to the contents of FIG. 2A.

[0099] For example, the external electronic device (103) can identify a call word included in the voice signal based on the call word recognition engine (435). For example, the external electronic device (103) can generate a first recognition result for the call word identified based on the call word recognition engine (435). The example in Table 1 may be referenced for the first recognition result.

[0100] For example, the external electronic device (103) can recognize the speaker who uttered the voice signal based on the speaker recognition engine (437). FIG. 4 illustrates the external electronic device (103) including the speaker recognition engine (437), but the embodiments of the present disclosure are not limited thereto. For example, the speaker recognition engine (437) may include a speaker recognition model trained for a specific speaker, such as the speaker recognition model (461) of the external electronic device (105). For example, the speaker may include a speaker registered based on the speaker registration module (439) included in the external electronic device (103). For example, the registered speaker may include at least one user. For example, the registered speaker may be registered in a state linked to account information. For example, the account information may be provided to the speaker registration module (439) from an account manager (not shown). For example, the account information may include an account identifier (or ID) of the user. For example, the external electronic device (103) can identify whether the speaker who uttered the voice signal is the registered speaker. For example, the external electronic device (103) can generate (or obtain) a second recognition result for the speaker through the speaker recognition engine (437). The second recognition result can be defined as shown in the table below.

[0101]

[0102] Referring to the table above, the second recognition result may include a speaker group, a speaker identifier, and a confidence score. However, the embodiments of the present disclosure are not limited thereto. For example, the second recognition result may include only the speaker identifier. Alternatively, for example, the first recognition result may include information regarding priorities between electronic devices in addition to the information exemplified in the table above.

[0103] For example, the speaker identifier may represent an identifier for identifying the speaker who uttered the voice signal. For example, the speaker identifier may be set to an encrypted value or a designated value provided by the server (107). For example, the speaker identifier may be referenced as a speaker account or speaker identification information. For example, the speaker group may represent a group to which the speaker is included. For example, the speaker group may include a group to which the speaker identifier belongs (e.g., family, friends).

[0104] For example, the confidence score may represent recognition information about the speaker. For example, the external electronic device (103) may obtain the confidence score, which represents the degree of recognition of the speaker in the voice signal as a probability value. For example, the external electronic device (103) may obtain the confidence score based on the speaker recognition engine (437). The confidence score may be referred to as the speaker's reliability.

[0105] Referring to the above-described table, the external electronic device (103) can generate the first recognition result and device information together with the second recognition result. For example, the first recognition result may include a recognition score, speech power, signal-to-noise ratio (SNR), and time. For example, the device information may include information about the external electronic device (103) that acquired the first recognition result. For example, the device information may include a device name, a device type, a device identity (device ID), a wake-up word, and an Internet protocol address (IP) of the device. Specific details related thereto may be substantially identically applied to the contents of FIG. 2A.

[0106] For example, the external electronic device (103) can share the first recognition result and the second recognition result through the MDW manager (441). For example, the external electronic device (103) can identify the electronic device (101) and the external electronic device (105) within the MDW environment (400) through the MDW manager (441). For example, the external electronic device (103) can transmit (or provide) the first recognition result and the second recognition result to the electronic device (101) and the external electronic device (105). In addition, for example, the external electronic device (103) can receive (or obtain) the recognition result from each of the electronic device (101) and the external electronic device (105) through the MDW manager (441). Alternatively, for example, the external electronic device (103) may transmit (or provide) the first recognition result and the second recognition result to the server (107) within the MDW environment (400) through the MDW manager (441). In addition, for example, the external electronic device (103) may receive (or obtain) information about the recognition results of the electronic device (101) and the external electronic device (105) from the server (107) within the MDW environment (400) through the MDW manager (441).

[0107] According to one embodiment, the external electronic device (105) may include a microphone (451), a preprocessing unit (453), a call word recognition engine (455), a speaker recognition engine (457), a speaker registration module (459), a speaker recognition model (461), and an MDW manager (463). Although not shown in FIG. 4, the external electronic device (105) may include a memory, at least one processor, and at least one communication circuit. For example, the at least one processor may control the at least one communication circuit, the microphone (451), the preprocessing unit (453), the call word recognition engine (455), the speaker recognition engine (457), the speaker registration module (459), the speaker recognition model (461), and the MDW manager (463). For example, the at least one communication circuit may be used for the external electronic device (105) to communicate with the electronic device (101), the external electronic device (103), and the server (107). However, the embodiments of the present disclosure are not limited thereto. For example, the external electronic device (105) may further include a microphone (451), a preprocessing unit (453), a call word recognition engine (455), a speaker recognition engine (457), a speaker registration module (459), a speaker recognition model (461), an MDW manager (463), and other components other than the at least one processor and the at least one communication circuit.

[0108] For example, the external electronic device (105) can obtain a voice signal from the outside through the microphone (451). For example, the voice signal may include a wake word. Or, for example, the voice signal may include the wake word and a command. The wake word may include a designated word or sentence registered in the external electronic device (105).

[0109] For example, the external electronic device (105) may perform processing on the voice signal through the preprocessing unit (453). For example, the external electronic device (105) may extract a plurality of feature values ​​for the voice signal through the preprocessing unit (453) and enhance the features of the voice portion of the voice signal. The specific details related thereto may be substantially identically applied to the contents of FIG. 2A.

[0110] For example, the external electronic device (105) can identify a call word included in the voice signal based on the call word recognition engine (455). For example, the external electronic device (105) can generate a first recognition result for the call word identified based on the call word recognition engine (455).

[0111] For example, the external electronic device (105) can identify whether a speaker recognition model (461) has been generated. For example, the external electronic device (105) can identify whether a speaker recognition model (461) has been generated through the speaker registration module (459). For example, the speaker recognition model (461) can be generated in conjunction with account information. For example, the speaker recognition model (461) can be generated for a specific user (or speaker).

[0112] For example, if the external electronic device (105) identifies that a speaker recognition model (461) has been generated for the speaker who uttered the voice signal, the external electronic device (105) may recognize the speaker who uttered the voice signal based on the speaker recognition engine (457) that utilizes the speaker recognition model (461). For example, the speaker may include a speaker registered based on a speaker registration module (459) included in the external electronic device (105). For example, the registered speaker may include at least one user. For example, the registered speaker may be registered in a state linked to account information. For example, the account information may be provided to the speaker registration module (459) from an account manager (not shown). For example, the account information may include an account identifier (or ID) of the user. For example, the external electronic device (101) may identify whether the speaker who uttered the voice signal is the registered speaker. For example, the external electronic device (101) can generate (or obtain) a second recognition result for the speaker through the speaker recognition engine (457). The contents of Table 2 described above can be applied substantially identically to the second recognition result.

[0113] In contrast, for example, if the external electronic device (105) identifies that a speaker recognition model (461) for the speaker who uttered the speech signal has not been generated, the external electronic device (105) may train the speaker recognition model (461). For example, the external electronic device (105) may train the speaker recognition model (461) based on a recognition result obtained through the MDW manager (463). For example, the external electronic device (105) may generate a speaker recognition model (461) for the speaker who uttered the speech signal by performing training of the speaker recognition model (461). The recognition result obtained through the MDW manager (463) may include speaker information (e.g., the second recognition result) identified by the external electronic device (103). The external electronic device (105) may identify the speaker who uttered the speech signal based on the speaker information. The external electronic device (105) may train the speaker recognition model (461) based on the voice signal acquired by the external electronic device (105) for the identified speaker. In other words, the external electronic device (105) may use the second recognition result recognized by the external electronic device (103) to identify the speaker who uttered the voice signal, and may train the speaker recognition model (461) for the speaker based on the voice signal acquired directly by the external electronic device (105). For example, the training may be performed based on a specified number of voice signals or a voice signal having a specified time length. In other words, the external electronic device (105) may identify that the speaker recognition model (461) has not been generated if the speaker recognition model (461) is trained using a smaller number of voice signals than the specified number of voice signals or is trained using a voice signal shorter than the specified time length.

[0114] For example, the external electronic device (105) can share the first recognition result (or the first recognition result and the second recognition result) through the MDW manager (463). For example, the external electronic device (105) can identify the electronic device (101) and the external electronic device (103) within the MDW environment (400) through the MDW manager (463). For example, the external electronic device (105) can transmit (or provide) the first recognition result to the electronic device (101) and the external electronic device (103). Alternatively, when the speaker recognition model (461) is generated, the external electronic device (105) can transmit (or provide) the first recognition result and the second recognition result to the electronic device (101) and the external electronic device (103) within the MDW environment (400) through the MDW manager (463). In addition, for example, the external electronic device (105) can receive (or obtain) the recognition results from each of the electronic device (101) and the external electronic device (103) through the MDW manager (463). Or, for example, the external electronic device (105) can transmit (or provide) the first recognition result to the server (107) within the MDW environment (400) through the MDW manager (463). Or, when the speaker recognition model (461) is generated, the external electronic device (105) can transmit (or provide) the first recognition result and the second recognition result to the server (107) within the MDW environment (400) through the MDW manager (463). Additionally, for example, an external electronic device (105) can receive (or acquire) information about recognition results of the electronic device (101) and the external electronic device (103) from a server (107) within the MDW environment (400) through the MDW manager (463).

[0115] According to one embodiment, the server (107) may generate information about the recognition result based on the recognition result obtained from each of the electronic device (101), the external electronic device (103), and the external electronic device (105). For example, the server (107) may obtain the first recognition result generated by the electronic device (101) from the electronic device (101). In addition, for example, the server (107) may obtain the first recognition result and the second recognition result generated by the external electronic device (103) from the external electronic device (103). In addition, for example, the server (107) may obtain the first recognition result generated by the external electronic device (105) from the external electronic device (105). In one embodiment, the server (107) may identify the object indicated by the voice signal (i.e., the indicated object) based on the obtained recognition results. For example, the server (107) can identify the target device by comparing the sound levels of the recognition results. For example, the server (107) can provide the information to the identified device (e.g., the electronic device (101)). For example, the information can include at least some of the recognition results. However, the embodiments of the present disclosure are not limited thereto. According to one embodiment, the server (107) can also transmit the information including the recognition results to all of the electronic device (101), the external electronic device (103), and the external electronic device (105) connected to the server (107).

[0116] According to one embodiment, the server (107) may identify electronic devices included in the MDW environment (400) based on the recognition results, and may share information about the identified devices with the electronic devices within the MDW environment (400).

[0117] According to one embodiment, when the server (107) includes an MDW manager, the target device can be identified based on the call word recognition results received from each of the MDW managers (417, 441, 463). Conversely, when the server (107) does not include an MDW manager, each of the MDW managers (417, 441, 463) can identify the target device based on the call word recognition results obtained directly and the call word recognition results received. For example, the device with the highest SNR (signal to noise ratio) included in the call word recognition results can be identified as the target device.

[0118] FIG. 5 illustrates an example of an operational flow for a method in which an electronic device including a speaker recognition model recognizes a wake word in a voice signal.

[0119] At least some of the methods of FIG. 5 may be performed by the external electronic device (103) of FIG. 4. For example, at least some of the methods may be controlled by at least one processor of the external electronic device (103). In the following embodiments, the operations may be performed sequentially, but are not necessarily performed sequentially. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0120] In operation (500), an external electronic device (103) may acquire a voice signal. For example, the external electronic device (103) of FIG. 5 may represent a device in which a speaker recognition model for a speaker who uttered the voice signal is generated, as described in FIG. 4. For example, the external electronic device (103) may acquire the voice signal through a microphone (431).

[0121] In operation (505), the external electronic device (103) can identify whether the voice signal includes a wake word. For example, the external electronic device (103) can extract feature values ​​of the voice signal and identify whether the voice signal includes the wake word based on the extracted feature values. For example, the wake word can represent a wake word commonly set for the external electronic device (103) and devices within the MDW environment. For example, the MDW environment can include the external electronic device (103) and the electronic device (101). However, the embodiments of the present disclosure are not limited thereto. For example, the MDW environment can further include the external electronic device (103), the electronic device (101), and another external electronic device (105).

[0122] In operation (505), if the voice signal includes the call word, the external electronic device (103) may perform operation (510). Conversely, in operation (505), if the voice signal does not include the call word, the external electronic device (103) may perform operation (500) again.

[0123] In operation (510), the external electronic device (103) can identify whether the speaker is a registered speaker. For example, the external electronic device (103) can identify whether the speaker who uttered the voice signal is the registered speaker for the external electronic device (103). For example, the external electronic device (103) can identify whether the speaker is the registered speaker by comparing the feature values ​​for the voice signal with information about the registered speaker.

[0124] In operation (510), if the speaker who uttered the voice signal is the registered speaker, the external electronic device (103) may perform operation (515). Conversely, in operation (510), if the speaker who uttered the voice signal is not the registered speaker, the external electronic device (103) may perform operation (500) again.

[0125] In operation (515), the external electronic device (103) can identify whether it is an MDW environment. For example, the external electronic device (103) can identify one or more connectable devices based on at least one communication circuit included in the external electronic device (103) to identify whether it is an MDW environment. For example, the one or more connectable devices may represent devices to which the wake word is set. Alternatively, for example, the external electronic device (103) can identify whether it is an MDW environment based on information obtained from a server for the MDW environment (e.g., server (107) of FIG. 4). For example, the information may include information about one or more devices managed by the server. For example, the non-MDW environment may indicate a case where the only device capable of obtaining the voice signal is the external electronic device (103) or the only device to which the wake word is set is the external electronic device (103). When the device capable of acquiring the voice signal is an external electronic device (103), this may include a state in which there are no other devices in the vicinity or a state in which the signal cannot be acquired (e.g., a state in which the power is off). Referring to the above, the MDW environment may include a plurality of devices including the external electronic device (103) for which the call word is set, or may include the plurality of devices for which the call word is set and the server for the plurality of devices. For the convenience of explanation, the MDW environment including the server is described as an example in the following examples, but the embodiments of the present disclosure are not limited thereto.

[0126] In the example of FIG. 5, the external electronic device (103) is described as performing operation (515) after operation (510), but the embodiments of the present disclosure are not limited thereto. According to one embodiment, the external electronic device (103) may repeatedly perform operation (515) at designated time points. For example, the external electronic device (103) may repeatedly identify whether the environment is an MDW environment at designated time points. For example, the designated time points may be set periodically or aperiodically.

[0127] In operation (515), if the external electronic device (103) identifies that it is the MDW environment, the external electronic device (103) may perform operation (520). Conversely, in operation (515), if the external electronic device (103) identifies that it is not the MDW environment, the external electronic device (103) may perform operation (530).

[0128] In operation (520), the external electronic device (103) may share the recognition results. For example, the external electronic device (103) may generate a first recognition result and a second recognition result for the voice signal. For example, the first recognition result may represent a recognition result for a wake word included in the voice signal. For example, the second recognition result may represent a recognition result for the speaker who uttered the voice signal.

[0129] According to one embodiment, the external electronic device (103) may provide (or transmit) the recognition result to the server connected to the external electronic device (103). In addition, the external electronic device (103) may obtain (or receive) information about the recognition result of one or more devices from the server. Alternatively, the external electronic device (103) may provide (or transmit) the recognition result to the identified one or more devices. In addition, the external electronic device (103) may obtain (or receive) the recognition result of one or more devices from the one or more devices.

[0130] In operation (525), the external electronic device (103) can identify whether the call word is the target of the instruction. For example, the external electronic device (103) can identify whether the call word is the target of the instruction. In other words, the external electronic device (103) can identify whether the device that responds to the call word (or executes a function) is the external electronic device (103).

[0131] According to one embodiment, the external electronic device (103) can identify whether the target of the call word is the external electronic device (103) based on the recognition result generated by the external electronic device (103) and the recognition result of the one or more devices shared through the operation (520). For example, the external electronic device (103) can identify the target of the call based on the sound level. For example, the device that has identified the maximum sound level among the sound levels included in the recognition result generated by the external electronic device (103) and the recognition result of the one or more devices shared through the operation (520) can be identified as the target of the call.

[0132] In operation (525), the external electronic device (103) may perform operation (530) based on identifying that the target of the instruction is the external electronic device (103). Alternatively, the external electronic device (103) may perform operation (500) based on identifying that the target of the instruction is not the external electronic device (103).

[0133] In operation (530), the external electronic device (103) may execute a mode for receiving a voice signal. For example, the external electronic device (103) may execute the mode for waiting for reception of the voice signal. For example, the mode may include a state in which the microphone (e.g., the microphone (431) of FIG. 4) included in the external electronic device (103) is activated. The voice signal received in the state in which the mode is executed may include a command word. For example, the external electronic device (103) may expect that the voice signal including the command word will be received based on processing the voice signal including the wake word identified in operation (505).

[0134] Although not illustrated in FIG. 5, the external electronic device (103) may provide a speaker recognition service based on recognizing the voice signal uttered by the registered speaker and including the call word. For example, the external electronic device (103) may execute a designated function. For example, the designated function may be included in the speaker recognition service. For example, the external electronic device (103) may include, as the designated function, displaying a designated user interface (UI) (e.g., UI (330) of FIG. 3) or executing an application allowed for a specific speaker (e.g., when the voice signal includes the call word and a command for executing the application). For example, the application allowed for the specific speaker may include a software application that requires authentication of the speaker. However, the embodiments of the present disclosure are not limited thereto.

[0135] FIG. 6 illustrates an example of an operational flow for a method for an electronic device that does not include a speaker recognition model to recognize a wake word in a voice signal.

[0136] At least some of the methods of FIG. 6 may be performed by the electronic device (101) of FIG. 4. For example, at least some of the methods may be controlled by at least one processor of the electronic device (101). However, the embodiments of the present disclosure are not limited thereto. At least some of the methods may be performed by the external electronic device (105) of FIG. 4. For example, at least some of the methods may be controlled by at least one processor of the external electronic device (105). In the following embodiments, the operations may be performed sequentially, but are not necessarily performed sequentially. For example, the order of the operations may be changed, and at least two operations may be performed in parallel. The following describes the method performed by the electronic device (101), but it may be substantially equally applied to the external electronic device (105).

[0137] In operation (600), the electronic device (101) may obtain a voice signal. For example, the electronic device (101) of FIG. 6 may represent an electronic device that does not include a speaker recognition model for recognizing a speaker who has uttered the voice signal, as described in FIG. 4. Alternatively, for example, the external electronic device (105) of FIG. 6 may represent an electronic device that includes a speaker recognition model for recognizing a speaker who has uttered the voice signal, as described in FIG. 4, but in which the speaker who has uttered the voice signal is not registered. For example, the electronic device (101) may obtain the voice signal through a microphone (411).

[0138] In operation (605), the electronic device (101) can identify whether the voice signal includes a wake word. For example, the electronic device (101) can extract feature values ​​of the voice signal and identify whether the voice signal includes the wake word based on the extracted feature values. For example, the wake word can represent a wake word commonly set for the electronic device (101) and devices within the MDW environment. For example, the MDW environment can include the electronic device (101) and one or more external electronic devices (e.g., the external electronic device (103) of FIG. 4 or the external electronic device (105) of FIG. 4). However, the embodiments of the present disclosure are not limited thereto.

[0139] In operation (605), if the voice signal includes the call word, the electronic device (101) may perform operation (610). Conversely, in operation (605), if the voice signal does not include the call word, the electronic device (101) may perform operation (600) again.

[0140] In operation (610), the electronic device (101) can identify whether it is an MDW environment. For example, the electronic device (101) can identify whether it is an MDW environment by identifying one or more connectable devices based on at least one communication circuit included in the electronic device (101). For example, the one or more connectable devices may indicate a device to which the wake word is set. Alternatively, for example, the electronic device (101) can identify whether it is an MDW environment based on information obtained from a server for the MDW environment (e.g., server (107) of FIG. 4). For example, the information may include information about one or more devices managed by the server. For example, the non-MDW environment may indicate a case where the electronic device (101) is the only device capable of obtaining the voice signal, or the electronic device (101) is the only device to which the wake word is set. In the case where the device capable of acquiring the above-mentioned voice signal is an electronic device (101), it may include a state in which there are no other devices in the vicinity or a state in which the signal cannot be acquired (e.g., a state in which the power is turned off).

[0141] In the example of FIG. 6, the electronic device (101) is described as performing operation (610) after operation (605), but the embodiments of the present disclosure are not limited thereto. According to one embodiment, the electronic device (101) can repeatedly perform operation (610) at designated time points. For example, the electronic device (101) can repeatedly identify whether the environment is an MDW environment at designated time points. For example, the designated time points can be set periodically or aperiodically.

[0142] In operation (610), if the electronic device (101) identifies that it is the MDW environment, the electronic device (101) may perform operation (615). Conversely, in operation (610), if the electronic device (101) identifies that it is not the MDW environment, the electronic device (101) may perform operation (635).

[0143] In operation (615), the electronic device (101) may share a recognition result. For example, the electronic device (101) may generate a first recognition result for the voice signal. For example, the first recognition result may represent a recognition result for a call word included in the voice signal.

[0144] According to one embodiment, the electronic device (101) may provide (or transmit) the recognition result to the server connected to the electronic device (101). In addition, the electronic device (101) may obtain (or receive) information about the recognition results of the one or more devices from the server. The recognition results of the one or more devices may include a first recognition result for a call word and / or a second recognition result for a speaker. For example, the second recognition result may indicate a recognition result for a speaker who uttered the voice signal. Alternatively, the electronic device (101) may provide (or transmit) the recognition result to the one or more identified devices. In addition, the electronic device (101) may obtain (or receive) the recognition results of the one or more devices from the one or more devices.

[0145] In operation (620), the electronic device (101) can identify whether the call word is the target of the instruction. For example, the electronic device (101) can identify whether the call word is the target of the instruction. In other words, the electronic device (101) can identify whether the device that will respond to the call word (or execute a function) is the electronic device (101).

[0146] According to one embodiment, the electronic device (101) can identify whether the target of the call word is the electronic device (101) based on the recognition result generated by the electronic device (101) and the recognition result of the one or more devices shared through the operation (615). For example, the electronic device (101) can identify the target of the call based on the sound level. For example, the electronic device (101) can identify the device that has the maximum sound level among the sound levels included in the recognition result generated by the electronic device (101) and the recognition result of the one or more devices shared through the operation (615) as the target of the call.

[0147] In operation (620), the electronic device (101) may perform operation (625) based on identifying that the instruction target is the electronic device (101). Alternatively, the electronic device (101) may perform operation (600) based on identifying that the instruction target is not the electronic device (101).

[0148] In operation (625), the electronic device (101) can identify whether the recognition result for the speaker has been received. For example, the electronic device (101) can identify whether the recognition result of the one or more devices received during the sharing includes the second recognition result for the speaker. For example, if the second recognition result is included, the electronic device (101) can identify that the recognition result for the speaker has been received. Conversely, if the second recognition result is not included, the electronic device (101) can identify that the recognition result for the speaker has not been received.

[0149] In operation (625), the electronic device (101) may perform operation (630) if the recognition results of the one or more devices include the second recognition result. Alternatively, in operation (625), the electronic device (101) may perform operation (635) if the recognition results of the one or more devices do not include the second recognition result.

[0150] In operation (630), the electronic device (101) may execute a designated function. For example, if the electronic device (101) includes the second recognition result, the electronic device (101) may identify the speaker who uttered the voice signal based on the second recognition result. For example, the electronic device (101) may execute the designated function within the electronic device (101) for the speaker who uttered the voice signal. For example, the designated function may be included in a speaker recognition service. For example, the electronic device (101) may include, as the designated function, displaying a designated user interface (UI) (e.g., UI (330) of FIG. 3) or executing an application allowed for a specific speaker (e.g., when the voice signal includes the wake word and a command for executing the application). For example, the application allowed for the specific speaker may include a software application that requires authentication of the speaker. However, the embodiments of the present disclosure are not limited thereto.

[0151] In operation (635), the electronic device (101) may execute a mode for receiving a voice signal. For example, the electronic device (101) may execute the mode for waiting for reception of the voice signal. For example, the mode may include a state in which the microphone (e.g., the microphone (411) of FIG. 4) included in the electronic device (101) is activated. The voice signal received in the state in which the mode is executed may include a command word. For example, the electronic device (101) may expect that the voice signal including the command word will be received based on processing the voice signal including the wake word identified in operation (605).

[0152] In operation (640), the electronic device (101) may execute a function according to a command. For example, the electronic device (101) may receive the voice signal while the mode is running. The electronic device (101) may recognize the command included in the voice signal. The electronic device (101) may recognize the function according to the command. For example, recognizing the function may be performed based on at least a part of the natural language processing (e.g., the natural language recognition module (921), the natural language understanding module (923), the planner module (925), the natural language generation module (927), and the text-to-speech conversion module (929)) of the natural language platform (920) of FIG. 9 described below. For example, the function according to the command may be linked to the speaker recognition service. For example, when the voice signal is "Tell me my schedule for today," the function may include recognizing and displaying the user's schedule. Accordingly, the electronic device (101) can display the user's schedule through the display.

[0153] According to one embodiment, when executing the function according to the command, the electronic device (101) may receive personal information about the user (or speaker) from an external electronic device based on recognition information about the user (e.g., the second recognition result). For example, the personal information may include the user's schedule information, phone number, and multimedia content. For example, the external electronic device may be a device not included in the MDW environment (400).

[0154] Figure 7 illustrates an example of an operational flow for how an electronic device generates a speaker recognition model.

[0155] At least some of the methods of FIG. 7 may be performed by the external electronic device (105) of FIG. 4. For example, at least some of the methods may be controlled by at least one processor of the external electronic device (105). However, the embodiments of the present disclosure are not limited thereto. For example, at least some of the methods may be controlled by at least one processor of the external electronic device (105). In the following embodiments, the operations may be performed sequentially, but are not necessarily performed sequentially. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0156] In operation (700), an external electronic device (105) may acquire a voice signal. For example, the external electronic device (105) of FIG. 7 may include a speaker recognition model for recognizing a speaker who has uttered the voice signal, as described in FIG. 4, but may represent an electronic device in which the speaker who has uttered the voice signal is not registered. For example, the external electronic device (105) may acquire the voice signal through a microphone (451).

[0157] Although not illustrated in FIG. 7, according to one embodiment, the external electronic device (105) may identify whether the voice signal acquired in operation (700) as described in FIG. 6 includes a wake word, identify whether it is an MDW environment, and share the recognition result. Furthermore, according to one embodiment, the external electronic device (105) may identify whether the recognition result received from one or more devices within the MDW environment includes a recognition result (e.g., a second recognition result) for the speaker who uttered the voice signal. For specific details related thereto, the operations of FIG. 6 may be substantially identically referenced.

[0158] In operation (705), the external electronic device (105) can identify whether a speaker recognition model has been generated. For example, the external electronic device (105) can identify whether a speaker recognition model has been generated for the speaker who uttered the speech signal.

[0159] In operation (705), if the speaker recognition model is generated, the external electronic device (105) can perform operation (710). Conversely, in operation (705), if the speaker recognition model is not generated, the external electronic device (105) can perform operation (715).

[0160] In operation (710), the external electronic device (105) may perform speaker recognition and execute a designated function. For example, if the speaker recognition model is generated, the external electronic device (105) may identify whether the speaker who uttered the voice signal is a registered speaker for the external electronic device (105). For specific details related thereto, operation (510) of FIG. 5 may be substantially identically referenced. The external electronic device (105) may execute the designated function based on recognizing that the speaker who uttered the voice signal is the registered speaker. For example, the designated function may be included in a speaker recognition service. For example, the external electronic device (105) may include, as the designated function, displaying a designated UI (user interface) (e.g., UI (330) of FIG. 3) or executing an application allowed for a specific speaker (e.g., when the voice signal includes the wake word and a command for executing the application). For example, the applications allowed for the specific speaker may include a software application that requires authentication of the speaker. However, embodiments of the present disclosure are not limited thereto.

[0161] In operation (715), the external electronic device (105) may perform training of the speaker recognition model. For example, if the speaker recognition model has not been generated, the external electronic device (105) may perform the training to generate the speaker recognition model. For example, the external electronic device (105) may identify the speaker who uttered the voice signal based on the recognition results received from the one or more devices. For example, the external electronic device (105) may perform the training for the identified speaker based on the voice signal acquired by the external electronic device (105).

[0162] In one embodiment, the speaker recognition model may be trained based on a speaker recognition algorithm. For example, the speaker recognition algorithm may include a Gaussian mixture model (GMM) / hidden Markov model (HMM)-based algorithm, a deep neural network (DNN)-based algorithm, or an identity vector (i-vector)-based algorithm.

[0163] According to one embodiment, the external electronic device (105) may display a UI inquiring whether to perform the training for generating the speaker recognition model when the speaker recognition model has not been generated. The external electronic device (105) may perform the training based on an input to the UI. According to one embodiment, the external electronic device (105) may store voice signals uttered by the speaker identified based on the recognition results received from the one or more devices. The voice signals may include voice signals directly acquired by the external electronic device (105). For example, the external electronic device (105) may perform the training when the voice signals uttered by the speaker are greater than or equal to a specified number or a specified time period. When the training is completed based on the voice signals greater than or equal to the specified number or a specified time period, the external electronic device (105) may display a UI notifying that the training is completed.

[0164] According to one embodiment, the speech signals used for the training may be signals that satisfy a specified criterion. For example, the speech signals may include signals having a signal-to-noise ratio (SNR) greater than or equal to a threshold SNR. However, the embodiments of the present disclosure are not limited thereto. The SNR may represent an example of signal quality of the speech signal. Alternatively, for example, the speech signals may include signals whose signal distance from a speech signal stored at a previous timing is within a reference distance or signals whose signal features are less than or equal to a reference value. For example, the signal distance may include a spectral distance and a feature domain distance. The signal features may include similarity and coherence.

[0165] According to one embodiment, the external electronic device (105) may define operations such as processing (e.g., acoustic echo cancellation), noise suppression, or beam forming that amplifies signals in a specific direction based on a signal generated by the external electronic device (105) itself and playing the sound played by the external electronic device (105) into a microphone (e.g., microphone 451) of the external electronic device (105), taking into account distortion that may be caused by a preprocessing process. The voice signals may include voice signals identified by each of the operations or a combination of the operations. According to one embodiment, each of the voice signals may include a wake word, the wake word and a command, or the command.

[0166] According to one embodiment, the external electronic device (105) may perform the training based on a speaker recognition engine (e.g., the speaker recognition engine (457) of FIG. 4) and a speaker registration module (e.g., the speaker registration module (459) of FIG. 4). In addition, the external electronic device (105) may include a call word recognition engine (e.g., the call word recognition engine (455) of FIG. 4) that is different from the speaker recognition engine. According to one embodiment, the speaker recognition engine and the call word recognition engine may be implemented as a single recognition engine. For example, the single recognition engine may be referred to as a speaker dependent speech recognition engine. In this case, the voice signals used for the training may be voice signals including a call word. According to one embodiment, the external electronic device (105) may use the speaker dependent speech recognition engine to use a trained speaker recognition model as an acoustic model for recognizing the call word. In this case, the acoustic model for recognizing the call word may be an external It can be used based on the user's input to a designated UI displayed through the electronic device (105).

[0167] In one embodiment, the training may be imperceptible to the user of the external electronic device (105). For example, the training may be performed automatically in the background and may be repeated for a specified number of times or for a specified length of time.

[0168] Figure 8 illustrates an example of an operational flow for a method in which an electronic device recognizes a speaker using an external electronic device.

[0169] At least some of the methods of FIG. 8 may be performed by the electronic device (101) of FIG. 4. For example, at least some of the methods may be controlled by at least one processor of the electronic device (101). However, the embodiments of the present disclosure are not limited thereto. At least some of the methods may be performed by the external electronic device (105) of FIG. 4. For example, at least some of the methods may be controlled by at least one processor of the external electronic device (105). In the following embodiments, the operations may be performed sequentially, but are not necessarily performed sequentially. For example, the order of the operations may be changed, and at least two operations may be performed in parallel. The following describes the method performed by the electronic device (101), but it may be substantially equally applied to the external electronic device (105).

[0170] In operation (800), the electronic device (101) may obtain a voice signal. For example, the electronic device (101) of FIG. 8 may represent an electronic device that does not include a speaker recognition model for recognizing a speaker who has uttered the voice signal, as described in FIG. 4. Alternatively, for example, the external electronic device (105) of FIG. 8 may represent an electronic device that includes a speaker recognition model for recognizing a speaker who has uttered the voice signal, as described in FIG. 4, but in which the speaker who has uttered the voice signal is not registered. For example, the electronic device (101) may obtain the voice signal through a microphone (411).

[0171] In operation (810), the electronic device (101) may generate a first recognition result for the wake word. According to one embodiment, the electronic device (101) may identify whether the voice signal includes the wake word. For example, the electronic device (101) may extract feature values ​​of the voice signal and identify whether the voice signal includes the wake word based on the extracted feature values. For example, the wake word may represent a wake word commonly set for the electronic device (101) and devices within the MDW environment. For example, the MDW environment may include the electronic device (101) and one or more external electronic devices (e.g., the external electronic device (103) of FIG. 4 or the external electronic device (105) of FIG. 4). However, the embodiments of the present disclosure are not limited thereto.

[0172] According to one embodiment, the electronic device (101) may generate the first recognition result for the wake word included in the voice signal. For example, the first recognition result may include a recognition score, speech power, signal-to-noise ratio (SNR), and time. However, the embodiments of the present disclosure are not limited thereto. For example, the first recognition result may include only the speech power. Alternatively, for example, the first recognition result may include information regarding priorities between electronic devices in addition to the information exemplified in the table. For example, the priorities may indicate priorities for responding to the wake word. For example, the priorities may be set by a user of the electronic device.

[0173] For example, the recognition score may represent recognition information for the call word. For example, the electronic device (101) may obtain the recognition score, which represents the degree of recognition of the voice signal for the call word as a probability value. For example, the electronic device (101) may obtain the recognition score. The recognition score may be referred to as the reliability (or recognition reliability) of the call word.

[0174] For example, the volume may represent the sound power level of the speech signal. For example, the electronic device (101) may identify the level of the speech signal. The volume or sound power level may be used to identify (or recognize) the electronic device that is located closest to the user who uttered the speech signal. For example, the volume may be referred to as speech power, sound power, or sound power level.

[0175] For example, the SNR may represent the ratio between the signal (e.g., the voice) within the voice signal and the noise. For example, the electronic device (101) may identify the noise level of the environment (or space) in which the voice signal was spoken based on the SNR. For example, the time may represent the time at which the voice signal was acquired.

[0176] For example, the electronic device (101) may generate device information associated with the first recognition result. The device information may include information about the electronic device (101) that acquired the first recognition result. For example, the device information may include a device name, a device type, a device identity (device ID), a wake-up word, and an IP (internet protocol address) of the device. For example, the device name may include a model name of the electronic device (101). For example, the device type may include a type of the electronic device (101) (e.g., TV). For example, the device identifier may include a unique identification number of the electronic device (101). For example, the wake-up word may include a name of a wake-up word set for the electronic device (101). The contents of the above-described table are merely examples for the convenience of explanation, and embodiments of the present disclosure are not limited thereto. For example, the device information may be transmitted or received (i.e., shared) together with the first recognition result.

[0177] In operation (820), the electronic device (101) can transmit the first recognition result to a server connected to one or more external electronic devices to which the call word is set.

[0178] For example, the electronic device (101) can identify whether it is an MDW environment. For example, the electronic device (101) can identify one or more connectable external electronic devices based on at least one communication circuit of the electronic device (101). For example, the electronic device (101) can identify whether it is an MDW environment based on identifying the one or more connectable external electronic devices. For example, the one or more connectable external electronic devices may indicate a device to which the wake word is set. Alternatively, for example, the electronic device (101) can identify whether it is an MDW environment based on information obtained from a server for the MDW environment (e.g., server (107) of FIG. 4). For example, the information may include information about the one or more external electronic devices managed by the server. According to one embodiment, the electronic device (101) can provide (or transmit) the first recognition result to the server connected to the electronic device (101).

[0179] For example, the non-MDW environment may indicate a case where the only device capable of acquiring the voice signal is the electronic device (101), or where the only device for which the call word is set is the electronic device (101). In the case where the device capable of acquiring the voice signal is the electronic device (101), this may include a state where there are no other devices in the vicinity, or a state where the signal cannot be acquired (e.g., a power-off state).

[0180] In operation (830), the electronic device (101) may receive, from the server, a second recognition result for the user who uttered the call word. The user may be referred to as the speaker who uttered the call word. For example, the electronic device (101) may obtain (or receive) information about the second recognition results of one or more external electronic devices from the server. However, the embodiments of the present disclosure are not limited thereto. For example, the electronic device (101) may include, from the server, a first recognition result for the call word and / or a second recognition result for the speaker.

[0181] In operation (840), the electronic device (101) may execute a function designated within the electronic device (101) for the user (with respect to) based on the second recognition result. For example, the electronic device (101) may identify the user based on the second recognition result. For example, the electronic device (101) may execute the designated function for the user. For example, the designated function may be included in a speaker recognition service. For example, the external electronic device (105) may include, as the designated function, display of a designated user interface (UI) (e.g., UI (330) of FIG. 3) or execution of an application permitted for a specific speaker (e.g., when the voice signal includes the wake word and a command for executing the application). For example, the application permitted for the specific speaker may include a software application requiring authentication of the speaker. However, the embodiments of the present disclosure are not limited thereto.

[0182] Although not illustrated in FIG. 8, according to one embodiment, the electronic device (101) can identify whether the target of the call word is the electronic device (101). For example, the electronic device (101) can identify whether the target of the call word is the electronic device (101). In other words, the electronic device (101) can identify whether the device that responds to the call word (or executes a function) is the electronic device (101). For example, the electronic device (101) can identify whether the target of the call word is the electronic device (101) based on the recognition result generated by the electronic device (101) and the first recognition result received from the one or more external electronic devices. For example, the electronic device (101) can identify the target of the call word based on the sound level.

[0183] According to one embodiment, the electronic device (101) may execute a mode for receiving a voice signal. For example, after executing the specified function, the electronic device (101) may execute the mode for waiting for reception of the voice signal. For example, the mode may include a state in which the microphone (e.g., the microphone (411) of FIG. 4) included in the electronic device (101) is activated. The voice signal received in the state in which the mode is executed may include a command word.

[0184] FIG. 9 is a block diagram illustrating an integrated intelligence system according to various embodiments.

[0185] Referring to FIG. 9, an integrated intelligent system of one embodiment may include an electronic device (101), an intelligent server (900) (e.g., server (108) of FIG. 1), and a service server (990) (e.g., server (108) of FIG. 1).

[0186] The electronic device (101) of one embodiment may be a terminal device (or electronic device) that can connect to the Internet, and may be, for example, a mobile phone, a smart phone, a personal digital assistant (PDA), a laptop computer, a TV, white goods, a wearable device, an HMD, or a smart speaker.

[0187] According to the illustrated embodiment, the electronic device (101) may include an interface (177), an input module (150), an audio output module (155), a display module (160), a memory (130), or a processor (120). The above-listed components may be operatively or electrically connected to each other.

[0188] An interface (177) of one embodiment may be configured to connect to an external device and transmit and receive data. An input module (150) of one embodiment may receive sound (e.g., user speech) and convert it into an electrical signal. An audio output module (155) of one embodiment may output the electrical signal as sound (e.g., voice).

[0189] The display module (160) of one embodiment may be configured to display an image or video. The display module (160) of one embodiment may also display a graphical user interface (GUI) of a running app (or application program). The display module (160) of one embodiment may receive touch input via a touch sensor. For example, the display module (160) may receive text input via a touch sensor in an on-screen keyboard area displayed within the display module (160).

[0190] In one embodiment, the memory (130) may store a client module (151), a software development kit (SDK) (153), and a plurality of apps (146). The client module (151) and the SDK (153) may constitute a framework (or solution program) for performing general functions. In addition, the client module (151) or the SDK (153) may constitute a framework for processing user input (e.g., voice input, text input, touch input).

[0191] The plurality of apps (146) stored in the memory (130) of one embodiment may be programs for performing a specified function. According to one embodiment, the plurality of apps (146) may include a first app (146-1) and a second app (146-2). According to one embodiment, each of the plurality of apps (146) may include a plurality of operations for performing a specified function. For example, the apps may include an alarm app, a message app, and / or a schedule app. According to one embodiment, the plurality of apps (146) may be executed by the processor (120) to sequentially execute at least some of the plurality of operations.

[0192] The processor (120) of one embodiment can control the overall operation of the electronic device (101). For example, the processor (120) can be electrically connected to an interface (177), an input module (150), an audio output module (155), and a display module (160) to perform a specified operation.

[0193] The processor (120) of one embodiment may also execute a program stored in the memory (130) to perform a designated function. For example, the processor (120) may execute at least one of the client module (151) or the SDK (153) to perform the following operations for processing user input. The processor (120) may control the operations of multiple apps (146), for example, through the SDK (153). The following operations described as operations of the client module (151) or the SDK (153) may be operations executed by the processor (120).

[0194] The client module (151) of one embodiment can receive user input. For example, the client module (151) can receive a voice signal corresponding to a user utterance detected through the input module (150). Alternatively, the client module (151) can receive a touch input detected through the display module (160). Alternatively, the client module (151) can receive a text input detected through a keyboard or a visual keyboard. In addition, the client module (151) can receive various forms of user input detected through an input module included in the electronic device (101) or an input module connected to the electronic device (101). The client module (151) can transmit the received user input to the intelligent server (900). The client module (151) can transmit status information of the electronic device (101) to the intelligent server (900) together with the received user input. The status information can be, for example, execution status information of an app.

[0195] The client module (151) of one embodiment can receive a result corresponding to the received user input. For example, the client module (151) can receive a result corresponding to the received voice input when the intelligent server (900) can produce a result corresponding to the received user input. The client module (151) can display the received result on the display module (160). In addition, the client module (151) can output the received result as audio through the audio output module (155).

[0196] In one embodiment, the client module (151) can receive a plan corresponding to the received user input. The client module (151) can display the results of executing multiple operations of the app according to the plan on the display module (160). For example, the client module (151) can sequentially display the results of executing multiple operations on the display and output audio through the audio output module (155). The electronic device (101) can, for example, display only some results of executing multiple operations (e.g., the result of the last operation) on the display module (160) and output audio through the audio output module (155).

[0197] According to one embodiment, the client module (151) may receive a request from the intelligent server (900) to obtain information necessary to produce a result corresponding to a user input. According to one embodiment, the client module (151) may transmit the necessary information to the intelligent server (900) in response to the request.

[0198] The client module (151) of one embodiment can transmit result information of executing multiple operations according to a plan to the intelligent server (900). The intelligent server (900) can use the result information to confirm that the received user input has been processed correctly.

[0199] The client module (151) of one embodiment may include a voice recognition module. According to one embodiment, the client module (151) may recognize voice inputs that perform limited functions through the voice recognition module. For example, the client module (151) may execute an intelligent app to process voice inputs to perform organic actions through designated inputs (e.g., "Wake up!").

[0200] An intelligent server (900) of one embodiment can receive information related to a user voice input from an electronic device (101) via a communication network. According to one embodiment, the intelligent server (900) can convert data related to the received voice input into text data. According to one embodiment, the intelligent server (900) can generate a plan for performing a task corresponding to the user voice input based on the text data.

[0201] In one embodiment, the plan may be generated by an artificial intelligence (AI) system. The AI ​​system may be a rule-based system, a neural network-based system (e.g., a feedforward neural network (FNN) or a recurrent neural network (RNN)), or a combination of the above or another AI system. In one embodiment, the plan may be selected from a set of predefined plans or may be generated in real time in response to a user request. For example, the AI ​​system may select at least one plan from a plurality of predefined plans.

[0202] An intelligent server (900) of one embodiment may transmit a result according to a generated plan to an electronic device (101), or transmit the generated plan to the electronic device (101). According to one embodiment, the electronic device (101) may display a result according to the plan on a display module (160). According to one embodiment, the electronic device (101) may display a result of executing an operation according to the plan on a display module (160).

[0203] An intelligent server (900) of one embodiment may include a front end (910), a natural language platform (920), a capsule DB (930), an execution engine (940), an end user interface (950), a management platform (960), a big data platform (970), or an analytic platform (980).

[0204] A front end (910) of one embodiment can receive user input from an electronic device (101). The front end (910) can transmit a response corresponding to the user input.

[0205] According to one embodiment, the natural language platform (920) may include an automatic speech recognition module (ASR module) (921), a natural language understanding module (NLU module) (923), a planner module (925), a natural language generator module (NLG module) (927), or a text to speech module (TTS module) (929).

[0206] The automatic speech recognition module (921) of one embodiment can convert voice input received from the electronic device (101) into text data. The natural language understanding module (923) of one embodiment can use the text data of the voice input to determine the user's intention. For example, the natural language understanding module (923) can perform syntactic analysis or semantic analysis on user input in the form of text data to determine the user's intention. The natural language understanding module (923) of one embodiment can use linguistic features (e.g., grammatical elements) of morphemes or phrases to determine the meaning of words extracted from the user input, and can match the meaning of the determined words to the intent to determine the user's intent. The natural language understanding module (923) can obtain intent information corresponding to the user's utterance. The intent information may be information indicating the user's intent determined by interpreting text data. The intent information may include information indicating an action or function that the user intends to execute using the device.

[0207] The planner module (925) of one embodiment can generate a plan using the intent and parameters determined by the natural language understanding module (923). According to one embodiment, the planner module (925) can determine a plurality of domains necessary to perform a task based on the determined intent. The planner module (925) can determine a plurality of operations included in each of the plurality of domains determined based on the intent. According to one embodiment, the planner module (925) can determine parameters necessary to execute the determined plurality of operations or result values ​​output by the execution of the plurality of operations. The parameters and the result values ​​can be defined as concepts of a specified format (or class). Accordingly, the plan can include a plurality of operations and a plurality of concepts determined by the user's intent. The planner module (925) can determine the relationship between the plurality of operations and the plurality of concepts in a stepwise (or hierarchical) manner. For example, the planner module (925) can determine the execution order of a plurality of actions based on the user's intention based on a plurality of concepts. In other words, the planner module (925) can determine the execution order of a plurality of actions based on parameters required for the execution of the plurality of actions and results output by the execution of the plurality of actions. Accordingly, the planner module (925) can generate a plan including association information (e.g., ontology) between the plurality of actions and the plurality of concepts. The planner module (925) can generate the plan using information stored in a capsule database (930) in which a set of relationships between concepts and actions is stored.

[0208] The natural language generation module (927) of one embodiment can convert specified information into text format. The information converted into text format may be in the form of natural language speech. The text-to-speech conversion module (929) of one embodiment can convert information in text format into information in speech format.

[0209] According to one embodiment, some or all of the functions of the natural language platform (920) may also be implemented in the electronic device (101).

[0210] The capsule database (930) may store information on the relationships between a plurality of concepts and actions corresponding to a plurality of domains. According to one embodiment, a capsule may include a plurality of action objects (or action information) and concept objects (or concept information) included in a plan. According to one embodiment, the capsule database (930) may store a plurality of capsules in the form of a concept action network (CAN). According to one embodiment, the plurality of capsules may be stored in a function registry included in the capsule database (930).

[0211] The capsule database (930) may include a strategy registry that stores strategy information required when determining a plan corresponding to a voice input. The strategy information may include reference information for determining a single plan when there are multiple plans corresponding to a user input. According to one embodiment, the capsule database (930) may include a follow-up registry that stores information on follow-up actions for suggesting follow-up actions to a user in a given situation. The follow-up actions may include, for example, follow-up utterances. According to one embodiment, the capsule database (930) may include a layout registry that stores layout information of information output through the electronic device (101). According to one embodiment, the capsule database (930) may include a vocabulary registry that stores vocabulary information included in capsule information. According to one embodiment, the capsule database (930) may include a dialog registry that stores information on dialogue (or interaction) with a user. The capsule database (930) may update stored objects through a developer tool. The developer tool may include, for example, a function editor for updating action objects or concept objects. The developer tool may include a vocabulary editor for updating vocabulary. The developer tool may include a strategy editor for creating and registering strategies that determine plans. The developer tool may include a dialog editor for creating dialogues with the user.The developer tool may include a follow-up editor that activates follow-up goals and allows editing of follow-up utterances that provide hints. The follow-up goals may be determined based on currently set goals, user preferences, or environmental conditions. In one embodiment, the capsule database (930) may also be implemented within the electronic device (101).

[0212] The execution engine (940) of one embodiment can produce a result using the generated plan. The end user interface (950) can transmit the produced result to the electronic device (101). Accordingly, the electronic device (101) can receive the result and provide the received result to the user. The management platform (960) of one embodiment can manage information used in the intelligent server (900). The big data platform (970) of one embodiment can collect user data. The analysis platform (980) of one embodiment can manage the quality of service (QoS) of the intelligent server (900). For example, the analysis platform (980) can manage the components and processing speed (or efficiency) of the intelligent server (900).

[0213] A service server (990) of one embodiment may include CP service A (991), CP service B (992), and CP service C (993). The service server (990) of one embodiment may provide a service (e.g., food ordering or hotel reservation) specified for the electronic device (101). According to one embodiment, the service server (990) may be a server operated by a third party. The service server (990) of one embodiment may provide information for generating a plan corresponding to the received user input to the intelligent server (200). The provided information may be stored in the capsule database (230). In addition, the service server (990) may provide result information according to the plan to the intelligent server (900).

[0214] In the integrated intelligence system of FIG. 9, the electronic device (101) can provide various intelligent services to the user in response to user input. The user input may include, for example, input via a physical button, touch input, or voice input.

[0215] In one embodiment, the electronic device (101) may provide a voice recognition service through an intelligent app (or voice recognition app) stored internally. In this case, for example, the electronic device (101) may recognize a user utterance or voice input received through the microphone and provide the user with a service corresponding to the recognized voice input.

[0216] In one embodiment, the electronic device (101) may perform a designated operation, either alone or in conjunction with the intelligent server and / or service server, based on the received voice input. For example, the electronic device (101) may execute an app corresponding to the received voice input and perform a designated operation through the executed app.

[0217] In one embodiment, when an electronic device (101) provides a service together with an intelligent server (900) and / or a service server (990), the electronic device (101) can detect a user's speech using the input module (150) and generate a signal (or voice data) corresponding to the detected user's speech. The electronic device (101) can transmit the voice data to the intelligent server (900) using the interface (177).

[0218] According to one embodiment, an intelligent server (900) may generate a plan for performing a task corresponding to a voice input received from an electronic device (101), or a result of performing an operation according to the plan, in response to a voice input. The plan may include, for example, a plurality of operations for performing a task corresponding to a user's voice input, and a plurality of concepts related to the plurality of operations. The concept may define parameters input to the execution of the plurality of operations, or result values ​​output by the execution of the plurality of operations. The plan may include association information between the plurality of operations and the plurality of concepts.

[0219] An electronic device (101) of one embodiment can receive the response using an interface (177). The electronic device (101) can output a voice signal generated within the electronic device (101) to the outside using the audio output module (155), or can output an image generated within the electronic device (101) to the outside using the display module (160).

[0220] FIG. 10 is a diagram showing the form in which relationship information between concepts and operations according to various embodiments is stored in a database.

[0221] The capsule database (e.g., the capsule database (930) of FIG. 9) of the intelligent server (e.g., the intelligent server (900) of FIG. 9) may store capsules in the form of a CAN (concept action network). The capsule database may store operations for processing tasks corresponding to a user's voice input and parameters necessary for the operations in the form of a CAN (concept action network).

[0222] The capsule database may store a plurality of capsules (capsule (A) (1001), capsule (B) (1004)) corresponding to each of a plurality of domains (e.g., applications). According to one embodiment, one capsule (e.g., capsule (A) (1001)) may correspond to one domain (e.g., location (geo), application). In addition, one capsule may correspond to at least one service provider (e.g., CP 1 (1002), CP 2 (1003), CP 3 (1006), or CP 4 (1005)) for performing a function for a domain related to the capsule. According to one embodiment, one capsule may include at least one operation (1010) and at least one concept (1020) for performing a specified function.

[0223] The natural language platform (e.g., the natural language platform (920) of FIG. 9) can generate a plan for performing a task corresponding to a received voice input using capsules stored in a capsule database. For example, the planner module of the natural language platform (e.g., the planner module (925) of FIG. 9) can generate a plan using capsules stored in a capsule database. For example, a plan (1007) can be generated using actions (1001-1, 1001-3) and concepts (1001-2, 1001-4) of capsule A (1001) and actions (1004-1) and concepts (1004-2) of capsule B (1004).

[0224] FIG. 11 is a diagram illustrating a screen for processing voice input received through an intelligent app by an electronic device according to various embodiments.

[0225] The electronic device (101) can execute an intelligent app to process user input through an intelligent server (e.g., the intelligent server (200) of FIG. 2A).

[0226] According to one embodiment, on the screen (1110), when the electronic device (101) recognizes a designated voice input (e.g., wake up!) or receives an input via a hardware key (e.g., a dedicated hardware key), the electronic device (101) may execute an intelligent app for processing the voice input. For example, the electronic device (101) may execute an intelligent app while the schedule app is running. According to one embodiment, the electronic device (101) may display an object (e.g., an icon) (1111) corresponding to the intelligent app on a display module (e.g., the display module (160) of FIG. 1). According to one embodiment, the electronic device (101) may receive a voice input by a user's speech. For example, the electronic device (101) may receive a voice input such as "Tell me my schedule for this week!" According to one embodiment, the electronic device (101) can display a user interface (UI) (1113) (e.g., an input window) of an intelligent app displaying text data of received voice input on a display module (e.g., the display module (160) of FIG. 1).

[0227] According to one embodiment, on the screen (1120), the electronic device (101) may display a result corresponding to the received voice input on a display module (e.g., the display module (160) of FIG. 1). For example, the electronic device (101) may receive a plan corresponding to the received user input and display 'this week's schedule' on the display module (160) according to the plan.

[0228] As described above, the electronic device (101, 105) may include a communication circuit. The electronic device (101, 105) may include a memory that stores instructions and includes one or more storage media. The electronic device (101, 105) may include a microphone (411, 451). The electronic device (101, 105) may include at least one processor that includes a processing circuit. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device (101, 105) to acquire a voice signal through the microphone (411, 451). The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device (101, 105) to generate a first recognition result for a wake-up word from the voice signal including the wake-up word. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device (101, 105) to transmit the first recognition result to a server (107) connected to one or more external electronic devices capable of recognizing the wake-up word. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device (101, 105) to receive, from the server (107), a second recognition result for a user who uttered the wake-up word.The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device (101, 105) to execute a designated function within the electronic device (101, 105) with respect to the user based on the second recognition result. The second recognition result may include identification information indicating the user obtained from an external electronic device (103) in which the user is registered among the one or more external electronic devices.

[0229] According to one embodiment, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device (101, 105) to extract a plurality of feature values ​​from the voice signal. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device (101, 105) to identify the wake word based on the plurality of feature values. The wake word may be used to execute a voice recognition function of each of the electronic device (101, 105) and the one or more external electronic devices.

[0230] According to one embodiment, the first recognition result may include at least one of a recognition accuracy value of the call word in the voice signal identified by the electronic device (101, 105), a sound power level of the voice signal including the call word, a signal to noise ratio (SNR) of the voice signal, or a timing of acquiring the voice signal.

[0231] According to one embodiment, the second recognition result may include a third recognition result for the call word transmitted from each of the one or more external electronic devices and a fourth recognition result including the identification information. The third recognition result may be generated based on another voice signal including the call word acquired by each of the one or more external electronic devices. The fourth recognition result may be generated based on the other voice signal acquired by the external electronic device with which the user is registered.

[0232] According to one embodiment, the fourth recognition result may include at least one of the identification information of the user who uttered the call word, group information including the user, or the recognition accuracy value of the user.

[0233] According to one embodiment, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device (101, 105) to identify whether an indication target of the call word is the electronic device based on the first recognition result and the second recognition result. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device (101, 105) to execute a mode for receiving a voice signal including a command word based on identifying that the indication target is the electronic device (101, 105).

[0234] According to one embodiment, the specified function may include at least one of displaying a user interface to guide the electronic device (101, 105) to recognize the user or executing a software application requiring authentication of the user.

[0235] According to one embodiment, the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device (101, 105) to identify whether a speaker recognition model for recognizing the user identified based on the second recognition result has been generated. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device (101, 105) to train the speaker recognition model for the user using the first recognition result based on identifying that the speaker recognition model has not been generated.

[0236] In one embodiment, the training of the speaker recognition model may be performed based on a specified number of speech signals for the user. The specified number may be identified based on the signal quality of the speech signals.

[0237] As described above, a method performed by an electronic device (101, 105) may include an operation of acquiring a voice signal. The method may include an operation of generating a first recognition result for a wake-up word from the voice signal including the wake-up word. The method may include an operation of transmitting the first recognition result to a server (107) connected to one or more external electronic devices capable of recognizing the wake-up word. The method may include an operation of receiving, from the server (107), a second recognition result for a user who uttered the wake-up word. The method may include an operation of executing a designated function within the electronic device (101, 105) with respect to the user based on the second recognition result. The second recognition result may include identification information indicating the user, which is acquired from an external electronic device (103) in which the user is registered among the one or more external electronic devices.

[0238] The non-transitory computer-readable storage medium as described above may store one or more programs comprising instructions that, when individually or collectively executed by at least one processor of an electronic device (101, 105) including a communication circuit and a microphone (411, 451), cause the electronic device (101, 105) to acquire a voice signal via the microphone (411, 451). The non-transitory computer-readable storage medium may store one or more programs comprising instructions that, when individually or collectively executed by the at least one processor, cause the electronic device (101, 105) to generate a first recognition result for a wake-up word from the voice signal including the wake-up word. The non-transitory computer-readable storage medium may store one or more programs including instructions that, when individually or collectively executed by the at least one processor, cause the electronic device (101, 105) to transmit the first recognition result to a server (107) connected to one or more external electronic devices capable of recognizing the call word. The non-transitory computer-readable storage medium may store one or more programs including instructions that, when individually or collectively executed by the at least one processor, cause the electronic device (101, 105) to receive, from the server (107), a second recognition result for a user who uttered the call word.The non-transitory computer-readable storage medium may store one or more programs including instructions that, when individually or collectively executed by the at least one processor, cause the electronic device (101, 105) to execute a designated function within the electronic device (101, 105) with respect to the user based on the second recognition result. The second recognition result may include identification information indicating the user obtained from an external electronic device (103) in which the user is registered among the one or more external electronic devices.

[0239] As described above, an electronic device (101, 105) may include a communication circuit. The electronic device (101, 105) may include a microphone (411, 451). The electronic device (101, 105) may include at least one processor. The at least one processor may be configured to acquire a voice signal through the microphone (411, 451). The at least one processor may be configured to generate a first recognition result for a wake-up word from the voice signal including the wake-up word. The at least one processor may be configured to broadcast the first recognition result to one or more external electronic devices capable of recognizing the wake-up word. The at least one processor may be configured to receive a second recognition result for the wake-up word broadcast from an external electronic device (103) in which the user is registered among the one or more external electronic devices, and a third recognition result for a user who uttered the wake-up word. The at least one processor may be configured to execute a designated function within the electronic device (101, 105) with respect to the user based on the third recognition result. The third recognition result may include identification information indicating the user.

[0240] According to one embodiment, the at least one processor may be configured to extract a plurality of feature values ​​from the voice signal. The at least one processor may be configured to identify the wake word based on the plurality of feature values. The wake word may be used to execute a voice recognition function of each of the electronic device (101, 105) and the one or more external electronic devices.

[0241] According to one embodiment, the first recognition result may include at least one of a recognition accuracy value of the call word in the voice signal identified by the electronic device (101, 105), a sound power level of the voice signal including the call word, a signal to noise ratio (SNR) of the voice signal, or a timing of acquiring the voice signal.

[0242] According to one embodiment, each of the second recognition result and the third recognition result may be generated based on another voice signal including the call word obtained by the external electronic device.

[0243] According to one embodiment, the third recognition result may include at least one of the identification information of the user who uttered the call word, group information including the user, or a recognition accuracy value of the user.

[0244] According to one embodiment, the at least one processor may be configured to identify whether the indication target of the call word is the electronic device based on the first recognition result, the second recognition result, and the third recognition result. The at least one processor may be configured to execute a mode for receiving a voice signal including a command word based on identifying that the indication target is the electronic device (101, 105).

[0245] According to one embodiment, the specified function may include at least one of displaying a user interface to guide the electronic device (101, 105) to recognize the user or executing a software application requiring authentication of the user.

[0246] In one embodiment, the at least one processor may be configured to identify whether a speaker recognition model for recognizing the user identified based on the third recognition result has been generated. The at least one processor may be configured to train the speaker recognition model for the user using the first recognition result, based on the identification that the speaker recognition model has not been generated.

[0247] In one embodiment, the training of the speaker recognition model may be performed based on a specified number of speech signals for the user. The specified number may be identified based on the signal quality of the speech signal.

[0248] As described above, a method performed by an electronic device (101, 105) may include an operation of acquiring a voice signal. The method may include an operation of generating a first recognition result for a wake-up word from the voice signal including the wake-up word. The method may include an operation of broadcasting the first recognition result to one or more external electronic devices capable of recognizing the wake-up word. The method may include an operation of receiving a second recognition result for the wake-up word broadcast from an external electronic device (103) in which the user is registered among the one or more external electronic devices and a third recognition result for the user who uttered the wake-up word. The method may include an operation of executing a designated function within the electronic device (101, 105) with respect to the user based on the third recognition result. The third recognition result may include identification information indicating the user.

[0249] The non-transitory computer-readable storage medium as described above may store one or more programs including instructions that, when executed by at least one processor of an electronic device (101, 105) including a communication circuit and a microphone (411, 451), cause the device to acquire a voice signal through the microphone (411, 451). The non-transitory computer-readable storage medium may store one or more programs including instructions that, when executed by the at least one processor, cause the device to generate a first recognition result for a wake-up word from the voice signal including the wake-up word. The non-transitory computer-readable storage medium may store one or more programs including instructions that, when executed by the at least one processor, cause the device to broadcast the first recognition result to one or more external electronic devices capable of recognizing the wake-up word. The non-transitory computer-readable storage medium may store one or more programs including instructions that, when executed by the at least one processor, cause the electronic device (103) among the one or more external electronic devices to receive a second recognition result for the call word broadcasted from the user registered therein and a third recognition result for the user who uttered the call word. The non-transitory computer-readable storage medium may store one or more programs including instructions that, when executed by the at least one processor, cause the electronic device (101, 105) to execute a designated function with respect to the user based on the third recognition result. The third recognition result may include identification information indicating the user.

[0250] As described above, an electronic device (103) may include a communication circuit. The electronic device (103) may include a microphone (431). The electronic device (103) may include at least one processor. The at least one processor may be configured to acquire a voice signal through the microphone (431). The at least one processor may be configured to identify a user who utters the voice signal, from the voice signal including a wake-up word. The at least one processor may be configured to transmit a signal including a first recognition result for the wake-up word and a second recognition result for the user to a server (107) connected to one or more external electronic devices (101, 105) capable of recognizing the wake-up word, based on identification of the user as a user registered with the electronic device (103). The first recognition result may include at least one of a recognition accuracy value of the call word in the voice signal identified by the electronic device (103), a sound power level of the voice signal including the call word, a signal to noise ratio (SNR) of the voice signal, or a timing at which the voice signal was acquired. The second recognition result may include at least one of the identification information of the user who uttered the call word, group information including the user, or a recognition accuracy value of the user.

[0251] According to one embodiment, the at least one processor may be configured to identify whether the indication target of the call word is the electronic device (103) based on the first recognition result and the second recognition result. The at least one processor may be configured to execute a mode for receiving a voice signal including a command word based on identifying that the indication target is the electronic device (103).

[0252] As described above, a method performed by an electronic device (103) may include an operation of acquiring a voice signal. The method may include an operation of identifying a user who utters the voice signal from the voice signal including a wake-up word. The method may include an operation of transmitting a signal including a first recognition result for the wake-up word and a second recognition result for the user to a server (107) connected to one or more external electronic devices (101, 105) capable of recognizing the wake-up word, based on identification of the user as a user registered with the electronic device (103). The first recognition result may include at least one of a recognition accuracy value of the wake-up word in the voice signal identified by the electronic device (103), a sound power level of the voice signal including the wake-up word, a signal to noise ratio (SNR) of the voice signal, or a timing of acquiring the wake-up word. The second recognition result may include at least one of the identification information of the user who uttered the call word, group information including the user, or the recognition accuracy value of the user.

[0253] The non-transitory computer-readable storage medium as described above may store one or more programs including instructions that, when executed by at least one processor of an electronic device (103) including a communication circuit and a microphone (431), cause the electronic device (103) to acquire a voice signal through the microphone (431). The non-transitory computer-readable storage medium may store one or more programs including instructions that, when executed by the at least one processor, cause the electronic device (103) to identify a user who uttered the voice signal from the voice signal including a wake-up word. The non-transitory computer-readable storage medium may store one or more programs including instructions that, when executed by the at least one processor, cause the processor to transmit a signal including a first recognition result for the call word and a second recognition result for the user to a server (107) connected to one or more external electronic devices (101, 105) capable of recognizing the call word based on identifying the user as a user registered with the electronic device (103). The first recognition result may include at least one of a recognition accuracy value of the call word in the voice signal identified by the electronic device (103), a sound power level of the voice signal including the call word, a signal to noise ratio (SNR) of the voice signal, or a timing at which the voice signal was acquired. The second recognition result may include at least one of identification information of the user who uttered the call word, group information including the user, or a recognition accuracy value of the user.

[0254] Electronic devices according to the various embodiments disclosed in this document may take various forms. Electronic devices may include, for example, portable communication devices (e.g., smartphones), computer devices, portable multimedia devices, portable medical devices, cameras, wearable devices, or home appliances. Electronic devices according to the embodiments of this document are not limited to the aforementioned devices.

[0255] The various embodiments of this document and the terminology used therein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the items, unless the context clearly indicates otherwise. In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase among those phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish one component from another, and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as "coupled" or "connected" to another component (e.g., a second component), with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0256] The term "module" used in various embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integral component, or a minimum unit or part of such a component that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0257] Various embodiments of the present document may be implemented as software (e.g., a program (140)) including one or more instructions stored in a storage medium (e.g., an internal memory (136) or an external memory (138)) readable by a machine (e.g., an electronic device (101)). For example, a processor (e.g., a processor (120)) of the machine (e.g., an electronic device (101)) may call at least one instruction among the one or more instructions stored from the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' simply means that the storage medium is a tangible device and does not contain signals (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently or temporarily on the storage medium.

[0258] According to one embodiment, the method according to various embodiments disclosed in the present document may be provided as included in a computer program product. The computer program product may be traded as a product between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or may be distributed online (e.g., downloaded or uploaded) via an application store (e.g., Play Store™) or directly between two user devices (e.g., smart phones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily generated in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0259] According to various embodiments, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and arranged in other components. According to various embodiments, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

Claims

1. In an electronic device (101, 105), A memory that stores instructions and includes one or more storage media; communication circuit; Mike (411, 451); and comprising at least one processor including a processing circuit; The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device (101, 105) to: Acquire a voice signal through the above microphone (411, 451); From the speech signal including the wake-up word, generating a first recognition result for the wake-up word; Transmitting the first recognition result to a server (107) connected to one or more external electronic devices capable of recognizing the call word; Receive a second recognition result for the user who uttered the call word from the server (107); and Based on the second recognition result, causing the electronic device (101, 105) to execute a designated function for the user (with respect to). The second recognition result includes identification information indicating the user obtained from an external electronic device (103) in which the user is registered among the one or more external electronic devices. Electronic devices (101, 105).

2. In claim 1, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device (101, 105) to: From the above speech signal, a plurality of feature values ​​are extracted; and Based on the above multiple feature values, cause the call word to be identified, The above call word is used to execute the voice recognition function of each of the electronic device (101, 105) and the one or more external electronic devices. Electronic devices (101, 105).

3. In claim 1, The first recognition result includes at least one of a recognition accuracy value of the call word in the voice signal identified by the electronic device (101, 105), a sound power level of the voice signal including the call word, a signal to noise ratio (SNR) of the voice signal, or a timing of acquiring the voice signal. Electronic devices (101, 105).

4. In claim 1, The second recognition result includes a third recognition result for the call word transmitted from each of the one or more external electronic devices and a fourth recognition result including the identification information, The third recognition result is generated based on another voice signal including the call word acquired by each of the one or more external electronic devices, and The fourth recognition result is generated based on the other voice signal acquired by the external electronic device registered by the user. Electronic devices (101, 105).

5. In claim 4, The fourth recognition result includes at least one of the identification information of the user who uttered the call word, group information including the user, or the recognition accuracy value of the user. Electronic devices (101, 105).

6. In claim 1, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device (101, 105) to: Based on the first recognition result and the second recognition result, identifying whether the indication target of the call word is the electronic device; and Based on identifying that the above instruction target is the electronic device (101, 105), causing a mode for receiving a voice signal including a command word to be executed. Electronic devices (101, 105).

7. In claim 1, The above-mentioned specified function includes at least one of displaying a user interface for guiding the electronic device (101, 105) to recognize the user or executing a software application requiring authentication of the user. Electronic devices (101, 105).

8. In claim 1, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device (101, 105) to: Identify whether a speaker recognition model for recognizing the user identified based on the second recognition result has been created; Based on identifying that the speaker recognition model is not generated, training of the speaker recognition model for the user is performed using the first recognition result. Electronic devices (101, 105).

9. In claim 8, The training of the speaker recognition model is performed based on a specified number of speech signals for the user, The above specified number is identified based on the signal quality of the voice signal. Electronic devices (101, 105).

10. In a method performed by an electronic device (101, 105), An operation of acquiring a voice signal through a microphone (411, 451) of the above electronic device (101, 105); An operation of generating a first recognition result for a wake-up word from the speech signal including the wake-up word; An action of transmitting the first recognition result to a server (107) connected to one or more external electronic devices capable of recognizing the call word; An operation of receiving a second recognition result for a user who uttered the call word from the server (107); and Based on the second recognition result, an action is included to execute a designated function within the electronic device (101, 105) with respect to the user, The second recognition result includes identification information indicating the user obtained from an external electronic device (103) in which the user is registered among the one or more external electronic devices. method.

11. In claim 10, The above method: An operation of extracting a plurality of feature values ​​from the above voice signal; and An operation for identifying the calling word based on the above plurality of feature values ​​is included, The above call word is used to execute the voice recognition function of each of the electronic device (101, 105) and the one or more external electronic devices. method.

12. In claim 10, The first recognition result includes at least one of a recognition accuracy value of the call word in the voice signal identified by the electronic device (101, 105), a sound power level of the voice signal including the call word, a signal to noise ratio (SNR) of the voice signal, or a timing of acquiring the voice signal. method.

13. In claim 10, The second recognition result includes a third recognition result for the call word transmitted from each of the one or more external electronic devices and a fourth recognition result including the identification information, The third recognition result is generated based on another voice signal including the call word acquired by each of the one or more external electronic devices, and The fourth recognition result is generated based on the other voice signal acquired by the external electronic device registered by the user. method.

14. In claim 13, The fourth recognition result includes at least one of the identification information of the user who uttered the call word, group information including the user, or the recognition accuracy value of the user. method.

15. A non-transitory computer-readable storage medium, when executed individually or collectively by at least one processor of an electronic device (101, 105) including a communication circuit and a microphone (411, 451), causes the electronic device (101, 105) to: Acquire a voice signal through the above microphone (411, 451); From the speech signal including the wake-up word, generating a first recognition result for the wake-up word; Transmitting the first recognition result to a server (107) connected to one or more external electronic devices capable of recognizing the call word; Receive a second recognition result for the user who uttered the call word from the server (107); and Based on the second recognition result, one or more programs including instructions causing the electronic device (101, 105) to execute a designated function with respect to the user are stored, The second recognition result includes identification information indicating the user obtained from an external electronic device (103) in which the user is registered among the one or more external electronic devices. A non-transitory computer-readable storage medium.

Images