Electronic device, operating method thereof, and recording medium

Abstract

This electronic device may comprise: a communication circuit; a speaker; a processor; and a memory for storing instructions. The instructions, when executed by the processor, may be configured to cause the electronic device to transmit input text, corresponding to a user input, to a server via the communication circuit. The instructions, when executed by the processor, may be configured to cause the electronic device to receive, from the server via the communication circuit, response text corresponding to the input text and generated by the server. The instructions, when executed by the processor, may be configured to cause the electronic device to identify a reception speed of the response text. The instructions, when executed by the processor, may be configured to cause the electronic device to determine the attribute of a response voice corresponding to the response text on the basis of the reception speed. The instructions, when executed by the processor, may be configured to cause the electronic device to output a voice signal corresponding to the response text via the speaker on the basis of the attribute of the response voice. Various other embodiments are also possible.

Description

Electronic devices, their operating methods and recording media

[0001] The present disclosure relates to an electronic device, an operating method thereof, and a recording medium according to one embodiment.

[0002] Text-to-speech (TTS) systems take text input, typically words or sentences, and generate speech output. The goal is to produce speech that accurately and naturally pronounces each word. Therefore, to achieve more natural speech output, existing technologies have evolved to accept sentence-level or even paragraph-level input, analyze the meaning, and impart natural intonation to the entire text. In other words, technological advancements have focused on producing high-quality speech under the assumption of regular input and output.

[0003] However, the limitation of these TTS systems lies in their assumption that the input data is prepared in advance. Text input must be above a certain speed to produce speech that is comfortable for the human ear. If text input is below this speed, the speech may be interrupted and provide no feedback to the user.

[0004] 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-described matters constitute prior art related to the present disclosure.

[0005] According to one embodiment, the electronic device may be operable to convert text provided from a generative model (e.g., a large language model (LLM)) that generates data into speech and output it.

[0006] According to one embodiment, an electronic device may include a communication circuit, a speaker, a processor, and a memory storing instructions. The instructions, when executed by the processor, may be configured to cause the electronic device to transmit input text corresponding to a user input to a server through the communication circuit. The instructions, when executed by the processor, may be configured to cause the electronic device to receive response text corresponding to the input text generated by the server from the server through the communication circuit. The instructions, when executed by the processor, may be configured to cause the electronic device to determine a reception speed of the response text. The instructions, when executed by the processor, may be configured to cause the electronic device to determine an attribute of a response voice corresponding to the response text based on the reception speed. The instructions, when executed by the processor, may be configured to cause the electronic device to output, through the speaker, a voice signal corresponding to the response text based on the property of the response voice.

[0007] According to one embodiment, a method of operating an electronic device may include transmitting an input text corresponding to a user input to a server. The method may include receiving a response text corresponding to the input text generated by the server from the server. The method may include checking a reception speed of the response text. The method may include determining an attribute of a response voice corresponding to the response text based on the reception speed. The method may include outputting a voice signal corresponding to the response text based on the attribute of the response voice.

[0008] According to one embodiment, a computer-readable recording medium storing instructions configured to cause a processor of an electronic device to perform at least one operation may include transmitting an input text corresponding to a user input to a server. The at least one operation may include receiving a response text corresponding to the input text generated by the server from the server. The at least one operation may include checking a reception speed of the response text. The at least one operation may include determining a property of a response voice corresponding to the response text based on the reception speed. The at least one operation may include outputting a voice signal corresponding to the response text based on the property of the response voice.

[0009] FIG. 1 is a block diagram of an electronic device within a network environment, according to one embodiment.

[0010] FIG. 2 is a block diagram of an electronic device according to one embodiment.

[0011] FIG. 3 is a block diagram of an electronic device and a server according to one embodiment.

[0012] FIG. 4 is a drawing illustrating the operation of an electronic device according to one embodiment.

[0013] FIG. 5 is a flowchart of a method of operating an electronic device according to one embodiment.

[0014] FIG. 6 is a drawing illustrating the operation of an electronic device according to one embodiment.

[0015] FIG. 7 is a flowchart of a method of operating an electronic device according to one embodiment.

[0016] FIG. 8 is a drawing illustrating the operation of an electronic device according to one embodiment.

[0017] FIG. 9 is a drawing illustrating the operation of an electronic device according to one embodiment.

[0018] FIG. 10 is a drawing illustrating the operation of an electronic device according to one embodiment.

[0019] FIG. 11 is a drawing illustrating the operation of an electronic device according to one embodiment.

[0020] FIG. 12 is a flowchart of a method of operating an electronic device according to one embodiment.

[0021] FIG. 13A is a diagram illustrating the operation of an electronic device according to one embodiment.

[0022] FIG. 13b is a diagram illustrating the operation of an electronic device according to one embodiment.

[0023] FIG. 14A is a diagram illustrating the operation of an electronic device according to one embodiment.

[0024] FIG. 14b is a diagram illustrating the operation of an electronic device according to one embodiment.

[0025] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings so that those skilled in the art can easily implement the present disclosure. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein. In connection with the description of the drawings, the same or similar reference numerals may be used for identical or similar components. Furthermore, in the drawings and related descriptions, descriptions of well-known functions and configurations may be omitted for clarity and conciseness.

[0026] FIG. 1 is a block diagram of an electronic device (101) within a network environment according to one embodiment.

[0027] 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). In 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)).

[0028] 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 operations. According to one embodiment, as at least a part of the data processing or operations, 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 an auxiliary 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 with the main processor (121). For example, when the electronic device (101) includes the main processor (121) and the auxiliary processor (123), the auxiliary processor (123) may be configured to use less power than the main processor (121) or to be specialized for a given function. The auxiliary processor (123) may be implemented separately from the main processor (121) or as a part thereof.

[0029] 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.

[0030] 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).

[0031] 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).

[0032] 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).

[0033] 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.

[0034] 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. According to 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.

[0035] 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).

[0036] 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.

[0037] 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.

[0038] 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).

[0039] The 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. According to one embodiment, the haptic module (179) can include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0040] 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.

[0041] 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 as, for example, at least a part of a power management integrated circuit (PMIC).

[0042] 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.

[0043] 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).

[0044] 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 realizing 1eMBB, a loss coverage (e.g., 164 dB or less) for realizing mMTC, 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 realizing URLLC.

[0045] 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, for example, by the communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device via the at least one selected 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).

[0046] According to various embodiments, the antenna module (197) may form a mmWave antenna module. In 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.

[0047] 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)).

[0048] 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 one 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.

[0049] FIG. 2 is a block diagram of an electronic device (101) according to one embodiment.

[0050] Referring to FIG. 2, according to one embodiment, an electronic device (101) may include a speaker (255) (e.g., the audio output module (155) of FIG. 1). The electronic device (101) may include a display (260) (e.g., the display module (160) of FIG. 1). The electronic device (101) may include a microphone (250) (e.g., the input module (250) of FIG. 1). The electronic device (101) may include a communication circuit (290) (e.g., the communication module (190) of FIG. 1). For example, the electronic device (101) may be configured to communicate with a server (108) via the communication circuit (290) (e.g., the communication module (190) of FIG. 1). The electronic device (101) may include a processor (120). The operation of the electronic device (101) may be controllable by the processor (120). Hereinafter, the operation of the electronic device (101) may be understood as the electronic device (101) (or a component included in the electronic device (101)) being operated by the processor (120). The electronic device (101) may include a memory (130). The memory (130) may include instructions. The instructions, when executed by the processor (120), may be configured to cause the electronic device (101) to perform a specific operation.

[0051] FIG. 3 is a block diagram of an electronic device (101) and a server (108) according to one embodiment.

[0052] At least some of the components of the server (108) described below may be included in the electronic device (101). For example, at least some of the operations of the server (108) may be performed by the electronic device (101). For example, the electronic device (101) may process data using the components included in the electronic device (101) without transmitting data to or receiving data from the server (108). For example, the electronic device (101) may include a generative model (e.g., a large language model (LLM)).

[0053] According to one embodiment, the electronic device (101) (e.g., the processor (120)) may include a voice recognition module (e.g., an automatic speech recognition (ASR) (311)). The electronic device (101) (e.g., the processor (120)) may be configured to perform voice recognition using the voice recognition module (e.g., the ASR (311)). There is no limitation on the implementation method of the voice recognition module (e.g., the ASR (311)). For example, the electronic device (101) may be configured to convert voice acquired through the microphone (250) into text using the voice recognition module (e.g., the ASR (311)). The electronic device (101) may be configured to transmit data corresponding to the converted text to the server (108) through the communication circuit (290). For example, the electronic device (101) may be configured to convert a voice (e.g., input voice) corresponding to a user input (e.g., voice input) into text (e.g., input text) and transmit the converted text to the server (108). According to one embodiment, the electronic device (101) may be configured to transmit a text (e.g., input text) corresponding to a user input (e.g., text input) to the server (108). The “input text” may be a text input to a generative model (e.g., LLM). The “response text” described below may be a text output (e.g., generated) from the generative model (e.g., LLM) based on the input text.

[0054] According to one embodiment, the server (108) may include a voice recognition module (e.g., ASR (321)). For example, the electronic device (101) may be configured to transmit data corresponding to a voice acquired through the microphone (250) to the server (108) through the communication circuit (290). The server (108) may be configured to convert data (e.g., voice) provided from the electronic device (101) into text (e.g., input text) using the voice recognition module (e.g., ASR (321)).

[0055] According to one embodiment, the server (108) may include a natural language processing (NLP) (322) module. For example, the NLP (322) may be processed using an artificial neural network-based large language model (LLM) (323). The LLM (323), which is one of the artificial neural network models, may be pre-trained on a large data set to provide a function of deriving responses to various questions based on the influence of the large data set. The server (108) may be configured to generate (e.g., output) a response text using an artificial neural network model (e.g., LLM (323)) based on an input text. When the NLP (322) based on the LLM (323) generates a response text, it may be sequentially generated in linguistic units (e.g., phoneme units, syllable units, word units, or sentence units) (as a characteristic of a generative model). The response text may be output at an irregular rate due to the state of the model, the resource allocation status of the system, or the characteristics of the input text. The server (108) may transmit the response text output (e.g., generated) based on the input text to the electronic device (101).

[0056] According to one embodiment, the electronic device (101) (e.g., the processor (120)) may include a text-to-speech conversion module (e.g., a text-to-speech (TTS) (312)). The electronic device (101) (e.g., the processor (120)) may be configured to convert text into speech using the TTS (312). For example, the electronic device (101) may be configured to convert a response text received from the server (108) into speech using the TTS (312). There is no limitation on the implementation method of the text-to-speech conversion module (e.g., the TTS (312)).

[0057] In one embodiment, the server (108) may include a text-to-speech module (e.g., TTS). The server (108) may be configured to convert text into speech using TTS. For example, the server (108) may convert response text generated using an artificial neural network model (e.g., LLM (323)) into speech using TTS. The server (108) may be configured to transmit the speech generated using TTS to the electronic device (101). The electronic device (101) may be configured to receive the speech generated using TTS from the server (108).

[0058] FIG. 4 is a drawing illustrating the operation of an electronic device (101) according to one embodiment.

[0059] With reference to FIG. 4, the TTS (312) of the electronic device (101) can be described.

[0060] According to one embodiment, the response text (410) may include a response text generated by an LLM-based system. The response text (410) may be input to the TTS (312). For example, the electronic device (101) may be configured to receive the response text from the server (108). The electronic device (101) may be configured to sequentially receive the response text from the server (108). For example, the electronic device (101) may receive a first section of the response text from the server (108) at a first point in time, and a second section of the response text at a second point in time. According to one embodiment, the electronic device (101) may also operate based on the response text provided by the LLM included in the electronic device (101).

[0061] In one embodiment, the encoder (411) may be configured to generate (or predict) linguistic features for generating speech from a string. The encoder (411) may be configured to generate (or predict) how phonemes and letter groups required for speech generation are pronounced from a string (e.g., a response text). For example, the encoder (411) may operate based on a language model (412). For example, the linguistic features (e.g., linguistic features) may include pronunciation, stress, spacing, and intonation of the text. For example, the linguistic features (e.g., linguistic features) may include pronunciation sequences (e.g., phoneme sequences, syllable sequences) of the response text. For example, the linguistic features (e.g., linguistic features) may be in the form of N-grams of pronunciation units (e.g., phonemes, syllables).

[0062] According to one embodiment, the text rate determination module (414) (e.g., token rate decision) may be configured to determine (or verify or calculate) a reception rate of a response text (e.g., text rate). The text rate determination module (414) may record a time interval of an incoming response text (410) and calculate an average time. The text rate determination module (414) may be configured to measure a time interval of an input value provided from the LLM (323) through the response text (410) and calculate an average of the input values ​​from the present to n previous input values. The text rate determination module (414) may be configured to calculate the number of words received per unit time of the response text (e.g., reception rate of the response text). Data obtained by the text rate determination module (414) may be provided to the speech rate determination module (415).

[0063] In one embodiment, the speech rate determination module (415) (e.g., output TTS rate decision) may be configured to determine (or verify or calculate) a playback speed (e.g., a speech rate) of a response speech to be generated based on data provided by the text rate determination module (414). The speech rate determination module (415) may be configured to probabilistically predict a time interval of a subsequent response text (or the number of words per unit time of a response text to be received) based on the data provided by the text rate determination module (414), and determine a playback speed of the response speech to be generated. For example, the speech rate determination module (415) may be configured to verify a reception speed of the response text based on the data provided by the text rate determination module (414). The speech rate determination module (415) may be configured to determine a normal speed (e.g., a basic playback speed) as the playback speed of the speech when the reception speed of the response text is maintained at a speed equal to or greater than a reference value. The voice speed determination module (415) may be configured to determine a playback speed slower than a normal speed (e.g., a basic playback speed) as the voice playback speed based on the fact that the voice to be generated can be generated at a speed or tone that is not uncomfortable to listen to, even though the reception speed of the response text is lower than a reference value. The voice speed determination module (415) may be configured to determine the voice playback speed using a moving average method. The voice speed determination module (415) may be configured to determine the voice playback speed corresponding to the next sentence based on the playback speed of the voice corresponding to the previous sentence. For example, referring to Equation 1, the voice speed determination module (415) may determine the playback speed of the response voice corresponding to the reception speed of the response text of the second time point after the first time point, when the playback speed of the response voice corresponding to the reception speed of the response text of the first time point is calculated as x times the speed (e.g., r in Equation 1) n-1), the playback speed of the response voice corresponding to the reception speed of the response text at the second point in time (e.g. r in Equation 1) n ) can be configured to determine (Mathematical Formula 1: ). For example, the voice rate determination module (415) may be configured to determine that the playback rate of the response voice corresponding to one sentence is maintained constant. The above mathematical expression 1 is merely an example to aid understanding, and the embodiments of the present disclosure may not be limited thereto. For example, the above mathematical expression 1 may be modified, applied, or expanded in various ways.

[0064] In one embodiment, the pitch / duration determination module (416) (e.g., pitch / duration predictor) may be configured to determine the most appropriate pitch and duration based on the response text received so far in a situation where the input of the entire sentence cannot be considered. The pitch / duration determination module (416) may be configured to determine the pitch (e.g., stress) and duration of the voice to be generated in response to the response text received so far based on the playback speed determined by the speech rate determination module (415).

[0065] In one embodiment, the speech pattern determination module (417) (e.g., a speech variator) may be configured to adjust the speed of the response speech based on the playback speed of the response speech. The speech pattern determination module (417) may be configured to change the speech pattern based on the playback speed of the response speech. The speech pattern determination module (417) may be configured to determine the speed and / or the speech pattern so that the user can hear the result of slowly adding emphasis to words or phrases of the language being generated. For example, determining the speech pattern may be pronouncing “girin” as “giirin” slowly and distinctly so that a young child learning to speak can easily understand. Based on the speed and speech pattern of the response speech being determined by the speech pattern determination module (417), the user may experience less discomfort in hearing than when only the speed of the response speech is determined.

[0066] According to one embodiment, the filler insertion module (413) (e.g., filler insertion decision) may be configured to determine that it is difficult to generate a normally audible voice when the time interval of the incoming response text exceeds a reference value or the number of words received per unit time of the response text is less than the reference value, and to decide to add a filler (e.g., an additional voice) to fill the empty time slot of the generated voice. The filler may be an additional voice to be inserted between response voices. The filler insertion module (413) may be configured to provide a signal to the encoder (411) or the vocoder (419) that causes the generation of a filler (e.g., an additional voice) to fill the empty space of the response voice corresponding to the response text, based on the reception speed of the response text being less than the reference value. The filler (e.g., an additional voice) may be generated as a voice with a tone that is not awkward to hear for a user by being in harmony with the content of the received response text or the content of the generated response voice, and may fill the empty space of the response voice. A filler (e.g., additional voice) may include speech sounds and / or non-speech sounds. For example, the filler (e.g., additional voice) may be stored in the form of a waveform corresponding to a plurality of sounds. For example, the filler (e.g., additional voice) may be synthesized by inputting additional text into the TTS (312). The filler (e.g., additional voice) may be selected from one of a plurality of types. The type of the filler (e.g., additional voice) may be selected based on the reception speed of the response text. The type of the filler (e.g., additional voice) may include silence, a designated speech sound, a nasal sound, a natural sound, a beep sound, white noise, or a designated sentence indicating an output delay. For example, based on the reception speed of the response text being within a first range (e.g., slightly slow), the type of the filler (e.g., additional voice) may be determined as a pause. The length of the pause may be determined based on the reception speed of the response text.For example, based on whether the reception speed of the response text falls within a second range (e.g., medium-slow), a designated speech sound (e.g., "Hmm...", "Let's just stay still") or a designated non-speech sound (e.g., natural sounds (e.g., wind, rain), beeping sounds (e.g., beep-beep-), white noise) may be determined as a filler (e.g., additional speech). For example, based on whether the reception speed of the response text falls within a third range (e.g., very slow), a designated sentence indicating an output delay (e.g., "The response is a bit delayed") may be determined as a filler (e.g., additional speech). For example, the filler (e.g., additional speech) may be a sound recorded in a different voice than the TTS (312). For example, a filler (e.g., an additional voice) may be synthesized by a second TTS (e.g., TTS (312)) corresponding to a second voice type that is different from a first TTS (e.g., TTS (312)) corresponding to a first voice type. The second TTS (e.g., TTS (312)) corresponding to the filler (e.g., the additional voice) may use a different language model (e.g., 412) or a different acoustic model (e.g., 418) than the first TTS (e.g., TTS (312)). The filler (e.g., the additional voice) may be selected by the user. The filler (e.g., the additional voice) may be played repeatedly. For example, the repetition playback time of the filler (e.g., the additional voice) may be specified by the user or may be determined by the electronic device (101) based on a reception speed of the response text. The size (e.g., volume) of the output of the filler (e.g., additional voice) may be determined based on the reception speed of the response text. For example, when the electronic device (101) receives a first section of the response text at a first time point and a second section of the response text at a second time point, the electronic device (101) may be configured to determine the size of the output of the filler based on the interval between the first time point and the second time point.For example, the electronic device (101) may be configured to determine the size of the output of the filler to naturally increase from a small volume to a certain level of volume in proportion to the time it takes to wait for the response text.

[0067] According to one embodiment, the vocoder (419) may be configured to generate a voice (e.g., a voice signal (420)) suitable for a user to hear. For example, the vocoder (419) may be configured to operate based on an acoustic model (418). The vocoder (419) may be configured to generate a voice signal (420) (e.g., a voice waveform) based on data (or signals) provided from each module of the TTS (312). For example, the vocoder (419) may be configured to generate a voice signal based on a reproduction speed of a response voice. The vocoder (419) may be configured to adjust the length of each phoneme section (or the number of unit phonemes) of a pronunciation sequence generated by the encoder (411) based on duration information determined by the pitch / duration determination module (416), determine an acoustic feature vector corresponding to the adjusted pronunciation sequence, and generate a voice signal using the determined acoustic feature vector.

[0068] Fig. 5 is a flowchart of an operating method of an electronic device (101) according to one embodiment. Fig. 5 can be explained with reference to the previously described embodiments and the embodiments described below.

[0069] At least some of the operations of FIG. 5 may be omitted. The order of the operations of FIG. 5 may be changed. At least two of the operations of FIG. 5 may be performed in parallel. Operations other than those of FIG. 5 may be performed before, during, or after the operations of FIG. 5.

[0070] Referring to FIG. 5, in operation 501, according to one embodiment, the electronic device (101) (e.g., the processor (120)) may be configured to verify an input text corresponding to a user input. In operation 503, according to one embodiment, the electronic device (101) (e.g., the processor (120)) may be configured to transmit the input text to the server (108). For example, the electronic device (101) may be configured to verify an input text corresponding to a user input (e.g., a mouse, a keyboard, a key (e.g., a button), a touch screen, or a digital pen (e.g., a stylus pen)). The electronic device (101) may be configured to transmit the verified input text to the server (108). For example, the electronic device (101) may verify the input text using the ASR (311) based on a user input (e.g., a voice verified through the microphone (250). The electronic device (101) may be configured to transmit the verified input text to the server (108). For example, the electronic device (101) may be configured to transmit data (e.g., voice) corresponding to a user input (e.g., voice verified through a microphone (250)) to the server (108). The server (108) may be configured to verify the input text using ASR (321) based on the data (e.g., voice) provided from the electronic device (101).

[0071] In operation 505, according to one embodiment, the server (108) may be configured to generate a response text corresponding to the input text based on the LLM (323). Each segment of the response text may be generated sequentially. The segments of the response text may include linguistic units (e.g., phoneme units, syllable units, word units, phrase units, or sentence units).

[0072] In operation 507, according to one embodiment, the server (108) may be configured to transmit the generated response text to the electronic device (101). The electronic device (101) may be configured to receive the response text from the server (108). The electronic device (101) may be configured to sequentially receive sections of the response text from the server (108).

[0073] In operation 509, according to one embodiment, the electronic device (101) (e.g., processor (120)) may be configured to check (or determine or calculate) a reception rate of a response text. For example, the reception rate of the response text may include a time interval of incoming response text and / or a number of words received per unit time of the response text.

[0074] In operation 511, according to one embodiment, the electronic device (101) (e.g., processor (120)) may be configured to determine properties of a response voice corresponding to the response text based on a reception speed of the response text. The properties of the response voice may include a playback speed of the response voice, a speech tone, and / or whether fillers are inserted.

[0075] In operation 513, according to one embodiment, the electronic device (101) (e.g., processor (120)) may be configured to output a voice signal corresponding to the response text based on properties of the response voice.

[0076] FIG. 6 is a drawing illustrating the operation of an electronic device (101) according to one embodiment.

[0077] FIG. 6 is a diagram illustrating an embodiment of outputting a voice signal at a basic playback speed without voice modulation (e.g., changing the playback speed and / or changing the speech tone) when the reception speed of the response text is sufficient. For example, referring to FIG. 6, an LLM (e.g., an LLM (323) included in a server (108) or an LLM included in an electronic device (101)) may be configured to generate a response text. The generated response text (601, 605, 609) may be provided to a TTS (312) (e.g., an electronic device (101)). Although FIG. 6 illustrates that the response text is directly transmitted from the LLM (e.g., 323) to the TTS (e.g., 312), this is for convenience of explanation. FIG. 6 is a diagram showing that the response text is generated in the LLM (e.g., 323) and the generated response text (e.g., 601, 605, 609) is ultimately transmitted to the TTS (e.g., 312). The transmission (or transmission) of the response text can be understood with reference to the description of the embodiment of FIG. 5. For example, the server (108) may be configured to transmit the response text generated by the LLM (323) to the electronic device (101). The electronic device (101) may be configured to convert the response text received from the server (108) into a voice signal using the TTS (312). As described above, according to one embodiment, at least a part of the configuration of the server (108) may be included in the electronic device (101). At least some of the operations of the server (108) may be performed by the electronic device (101). For example, the electronic device (101) may include an LLM. For example, a response text generated by the LLM of the electronic device (101) may ultimately be input to the TTS (e.g., 312) of the electronic device (101).Hereinafter, at least some of the configurations of the server (108) may be included in the electronic device (101), and for example, at least some of the operations of the server (108) may be performed by the electronic device (101). For convenience of explanation, a description of an embodiment in which the electronic device (101) performs operations without the server (108) will be omitted.

[0078] In FIG. 6, at a first time point, a first section (601) of the response text (e.g., "today") may be transmitted, and a first voice signal (603) corresponding to the first section (601) of the response text (e.g., "today") may be output. At a second time point, a second section (605) of the response text (e.g., "the weather is") may be transmitted, and a second voice signal (607) corresponding to the second section (605) of the response text (e.g., "the weather is") may be output. At a third time point, a third section (609) of the response text (e.g., "it is sunny") may be transmitted, and a third voice signal (611) corresponding to the third section (609) of the response text (e.g., "it is sunny") may be output. In Fig. 6, depending on the reception speed of the response text and the generation and reproduction speed of the response voice, the next section of the response text (e.g., 609) may be received before the output of the previous voice signal (e.g., 607) is completed (e.g., before the output starts, or before the output starts and the output ends).

[0079] Fig. 7 is a flowchart of an operating method of an electronic device (101) according to one embodiment. Fig. 7 can be explained with reference to the previously described embodiments and the embodiments described below.

[0080] At least some of the operations of FIG. 7 may be omitted. The order of the operations of FIG. 7 may be changed. At least two of the operations of FIG. 7 may be performed in parallel. Operations other than those of FIG. 7 may be performed before, during, or after the operations of FIG. 7.

[0081] With reference to Fig. 7, the operations of Fig. 5 can be described in detail.

[0082] Referring to FIG. 7, in operation 701, according to one embodiment, the electronic device (101) (e.g., processor (120)) may be configured to receive a response text from the server (108). Operation 701 may be the same as or similar to operation 507 of FIG. 5.

[0083] In operation 703, according to one embodiment, the electronic device (101) (e.g., processor (120)) may be configured to calculate (or determine or verify) a text rate (e.g., a reception rate of a response text). Operation 703 may be the same as or similar to operation 509 of FIG. 5.

[0084] In operation 705, according to one embodiment, the electronic device (101) (e.g., processor (120)) may be configured to compare the text speed with a reference value (e.g., a first reference value).

[0085] In operation 707, according to one embodiment, the electronic device (101) (e.g., the processor (120)) may be configured to determine the basic playback speed as the playback speed of the response voice based on whether the text speed is greater than or equal to a reference value (e.g., a first reference value). The electronic device (101) may be configured to determine the basic playback speed as the playback speed of the response voice based on whether the response text is received at a sufficient speed.

[0086] In operation 709, according to one embodiment, the electronic device (101) (e.g., the processor (120)) may be configured to calculate (or confirm or determine) a playback speed of the response voice based on whether the text speed is less than a reference value (e.g., a first reference value). The electronic device (101) may be configured to calculate (or confirm or determine) a playback speed of the response voice that is lower than a base playback speed based on whether the response text is received at an insufficient speed.

[0087] In operation 711, according to one embodiment, the electronic device (101) (e.g., the processor (120)) may be configured to change (or determine) the speech tone of the response voice. Changing the speech tone may mean determining the speech tone of the response voice to be different from a default speech tone. The default speech tone may be selected by the user or the electronic device (101). The speech tone different from the default speech tone may be selected by the user or the electronic device (101). For example, the electronic device (101) may change the speech tone of the response voice based on whether the text speed is less than a reference value (e.g., a first reference value). Operation 711 may be omitted. For example, in operations 709 and 711, the electronic device (101) may determine the playback speed of the response voice to be slower than the default playback speed and change the speech tone of the response voice based on whether the text speed is less than the reference value (e.g., the first reference value). For example, by omitting operation 711 and performing only operation 709, the electronic device (101) can determine the playback speed of the response voice to be slower than the default playback speed, and determine the speech tone of the response voice to be the default speech tone, based on the text speed being less than a reference value (e.g., a first reference value).

[0088] In operation 713, according to one embodiment, the electronic device (101) (e.g., the processor (120)) may be configured to compare the playback speed of the response voice with a reference value (e.g., a second reference value). The electronic device (101) may be configured to replace the operation (e.g., the first operation) of comparing the playback speed of the response voice with the reference value (e.g., the second reference value) with an operation (e.g., the second operation) of comparing the text speed (e.g., the reception speed of the response text) with a reference value (e.g., a third reference value that is less than the first reference value of operation 705), or may be configured to perform both the first and second operations. For example, the electronic device (101) may be configured to perform operation 715 based on the playback speed of the response voice being less than the reference value (e.g., the second reference value). For example, the electronic device (101) may be configured to perform operation 715 based on the text speed being less than a reference value (e.g., a third reference value less than the first reference value of operation 705).

[0089] In operation 715, according to one embodiment, the electronic device (101) (e.g., processor (120)) may be configured to determine the addition of a filler (e.g., additional voice). The filler (e.g., additional voice) is described in FIG. 4.

[0090] In operation 717, according to one embodiment, the electronic device (101) (e.g., processor (120)) may be configured to output a voice signal. The electronic device (101) may generate a voice signal and output the voice signal using a speaker (255). The voice signal may include a signal corresponding to a response text and / or a signal corresponding to filler (e.g., additional voice).

[0091] For example, after operation 707 is performed, the electronic device (101) may be configured to output a voice signal corresponding to the response text based on the basic playback speed of the response voice.

[0092] For example, after operation 709 is performed, the electronic device (101) may be configured to output a voice signal corresponding to the response text based on a playback speed of the response voice that is slower than the default playback speed and the default speech tone.

[0093] For example, after operations 709 and 711 are performed, the electronic device (101) may be configured to output a voice signal corresponding to the response text based on a playback speed of the response voice that is slower than the basic playback speed and the changed speech tone.

[0094] For example, after operations 709 and 715 are performed, the electronic device (101) may be configured to output a first voice signal corresponding to a first section of the response text, an additional voice signal corresponding to a filler (e.g., additional voice), and a second voice signal corresponding to a second section of the response text, based on a playback speed of the response voice that is slower than the basic playback speed.

[0095] For example, after operations 709, 711, and 715 are performed, the electronic device (101) may be configured to output a first voice signal corresponding to a first section of the response text, an additional voice signal corresponding to a filler (e.g., additional voice), and a second voice signal corresponding to a second section of the response text, based on a playback speed of the response voice that is slower than the basic playback speed and the changed speech tone.

[0096] For example, by omitting operations 709 and 711 and performing operations 713 and 715, the electronic device (101) may be configured to output a first voice signal corresponding to a first section of the response text, an additional voice signal corresponding to a filler (e.g., additional voice), and a second voice signal corresponding to a second section of the response text.

[0097] FIG. 8 is a drawing illustrating the operation of an electronic device according to one embodiment. FIG. 9 is a drawing illustrating the operation of an electronic device according to one embodiment.

[0098] With reference to FIGS. 8 and 9, the basic playback speed, the playback speed slower than the basic playback speed, the basic speech tone, and the changed speech tone can be described.

[0099] FIGS. 8 and 9 are diagrams illustrating an embodiment of outputting a voice signal based on voice modulation (e.g., changing the playback speed and / or changing the speech tone) when a response text is received at an insufficient speed. For example, FIGS. 8 and 9 may be diagrams illustrating an embodiment in which operation 717 is performed after operation 709 and / or operation 711. For example, referring to FIG. 8, an LLM (323) (e.g., a server (108)) may operate to generate a response text and provide the generated response text (801, 807, 813) to a TTS (312) (e.g., an electronic device (101)). In FIG. 8, a first section (801) of the response text (e.g., "Today") may be transmitted at a first time point. A second section (807) of the response text (e.g., "The weather is") may be transmitted at a second time point. At a third point in time, a third segment (813) of the response text (e.g., "It is clear") may be transmitted. The electronic device (101) may be configured to determine a voice modulation (e.g., a change in playback speed and / or a change in speech) if the response text is received at an insufficient speed. The electronic device (101) may be configured to determine a voice modulation (e.g., a change in playback speed and / or a change in speech) based on the text speed. The electronic device (101) may be configured to determine a voice modulation (e.g., a change in playback speed and / or a change in speech) based on a period (e.g., 805 or 811) between the time of output (or the time of completion of output) of a previous voice signal (e.g., 803 or 809) and the time of reception of the next segment (e.g., 807 or 813) of the response text. In FIG. 8, depending on the reception speed of the response text and the generation and reproduction speed of the response voice, a first voice signal (803) corresponding to a first section (801) of the response text (e.g., “today”) can be output at a default reproduction speed and default speech tone.In Fig. 8, depending on the reception speed of the response text and the generation and reproduction speed of the response voice, a second voice signal (809) corresponding to a second section (807) of the response text (e.g., “the weather is”) may be output at a playback speed slower than the default playback speed and with a changed speech tone. In Fig. 8, depending on the reception speed of the response text and the generation and reproduction speed of the response voice, a third voice signal (815) corresponding to a third section (813) of the response text (e.g., “it is sunny”) may be output at a playback speed slower than the default playback speed and with a changed speech tone. For example, Fig. 9 may illustrate an embodiment of a default playback speed and a default speech tone (910), an embodiment of a playback speed slower than the default playback speed and a default speech tone (920), and an embodiment of a playback speed slower than the default playback speed and a changed speech tone (930). Figure 9 is a schematic diagram showing the speech sound by time interval for understanding the change in speech rate, and does not indicate the exact time length.

[0100] FIG. 10 is a drawing illustrating the operation of an electronic device according to one embodiment. FIG. 11 is a drawing illustrating the operation of an electronic device according to one embodiment.

[0101] Referring to FIGS. 10 and 11, fillers (e.g., additional voices) can be described.

[0102] FIGS. 10 and 11 are diagrams illustrating an embodiment of outputting a voice signal based on voice modulation (e.g., changing the playback speed and / or changing the speech tone) and adding fillers when the response text is received at an insufficient speed. For example, FIGS. 10 and 11 may be diagrams illustrating an embodiment in which operation 717 is performed after operation 715. For example, referring to FIG. 10 , an LLM (323) (e.g., a server (108)) may be configured to generate a response text and provide the generated response text (1001, 1009, 1017) to a TTS (312) (e.g., an electronic device (101)). In FIG. 10 , a first section (1001) of the response text (e.g., "Today") may be transmitted at a first time point. A second section (1009) of the response text (e.g., "The weather is") may be transmitted at a second time point. At a third point in time, a third segment (1017) of the response text (e.g., "It is clear") may be transmitted. The electronic device (101) may be configured to determine whether to add voice modulation (e.g., change the playback speed and / or change the speech tone) and filler (e.g., add additional voice) when the response text is received at an insufficient speed. The electronic device (101) may be configured to determine the voice modulation (e.g., change the playback speed and / or change the speech tone) based on the text speed. The electronic device (101) may be configured to determine the addition of filler (e.g., add additional voice) based on the text speed and / or the playback speed of the response voice. The electronic device (101) may be configured to determine whether to add voice modulation (e.g., change playback speed and / or change speech) and filler (e.g., 1007 or 1015) based on a period (e.g., 1005 or 1013) between the time of output (or completion of output) of a previous voice signal (e.g., 1003 or 1011) and the time of reception of the next segment of response text (e.g., 1009 or 1017).In FIG. 10, depending on the reception speed of the response text and the generation and reproduction speed of the response voice, a first voice signal (1003) corresponding to a first section (1001) of the response text (e.g., “today”) may be output with a default reproduction speed and a default speech tone. Thereafter, as the reception of a second section (1009) of the response text (e.g., “the weather is”) is delayed, a first filler (1007) (e.g., a beep sound (e.g., “tut-tut-”)) may be output. In FIG. 10, depending on the reception speed of the response text and the generation and reproduction speed of the response voice, a second voice signal (1011) corresponding to a second section (1009) of the response text (e.g., “the weather is”) may be output with a reproduction speed slower than the default reproduction speed and with a changed speech tone. Thereafter, as the reception of the third section (1017) of the response text (e.g., "It is clear") is delayed, a second filler (1015) (e.g., a beep sound (e.g., "tut-tut-")) may be output. In FIG. 10, depending on the reception speed of the response text and the generation and reproduction speed of the response voice, a third voice signal (1019) corresponding to the third section (1017) of the response text (e.g., "It is clear") may be output with a playback speed slower than the default playback speed and with a changed speech tone. For example, FIG. 11 may illustrate an embodiment (1110) of the default playback speed and the default speech tone, and an embodiment (1120) in which a filler is added in addition to the playback speed slower than the default playback speed and the changed speech tone. 1110 of FIG. 11 can explain that after the first voice signal corresponding to the first section of the response text (e.g., “today”) and the second voice signal corresponding to the second section of the response text (e.g., “the weather”) are output, no signal is output as the reception of the next section of the response text is delayed.1120 of FIG. 11 can explain that after a first voice signal corresponding to a first section of a response text (e.g., "Today") and a second voice signal corresponding to a second section of the response text (e.g., "The weather is") are output at a playback speed slower than the default playback speed and with a changed speech tone, a filler (e.g., a beep sound (e.g., "tuttu")) is output as reception of the next section of the response text is delayed. FIG. 11 is a diagram schematically showing the speech voice by time section for understanding the change in speech speed and does not represent the exact time length. In the case of 1120 of FIG. 11, the user can recognize that reception of the next section of the response text is delayed as a filler (e.g., a beep sound (e.g., "tuttu")) is output. In one embodiment, the voice signal may not be output at a playback speed slower than the default playback speed and / or with a changed speech tone, and only a filler (e.g., an additional voice) may be added between voice signals. In one embodiment, fillers (e.g., additional speech) may be added between sentences. In one embodiment, fillers (e.g., additional speech) may be added between words.

[0103] Fig. 12 is a flowchart of an operating method of an electronic device (101) according to one embodiment. Fig. 12 can be explained with reference to the previously described embodiments and the embodiments described below.

[0104] At least some of the operations of FIG. 12 may be omitted. The order of the operations of FIG. 12 may be changed. At least two of the operations of FIG. 12 may be performed in parallel. Operations other than those of FIG. 12 may be performed before, during, or after the operations of FIG. 12.

[0105] Referring to FIG. 12, in operation 1201, according to one embodiment, the electronic device (101) (e.g., processor (120)) may be configured to receive a first section of response text from the server (108) at a first point in time.

[0106] In operation 1203, according to one embodiment, the electronic device (101) (e.g., processor (120)) may be configured to receive a second section of response text from the server (108) at a second point in time.

[0107] In operation 1205, according to one embodiment, the electronic device (101) (e.g., processor (120)) may be configured to determine the type of filler (e.g., additional speech) to be added based on the interval (or text speed) between the first time point and the second time point. The type of filler (e.g., additional speech) may include silence, a designated speech sound, a nasal sound, a natural sound, a beep sound, white noise, or a designated sentence indicating an output delay. For example, the type of filler (e.g., additional speech) may be determined to be a pause based on the interval (or text speed) between the first time point and the second time point being within a first range (e.g., slightly slower). The length of the pause may be determined based on the reception speed of the response text. For example, based on whether the interval (or text speed) between the first and second time points falls within a second range (e.g., medium slow), a designated speech sound (e.g., habitual phrases such as “um…”, “let’s just wait and see”, “well…”, “you know…”, “well…”, “so…”) or a designated non-speech sound (e.g., natural sounds (e.g., wind, rain), beeping sounds (e.g., beep-beep-), white noise) may be determined as a filler (e.g., additional speech). For example, based on whether the interval (or text speed) between the first and second time points falls within a third range (e.g., very slow), a designated sentence indicating an output delay (e.g., “the response is a little late”) may be determined as a filler (e.g., additional speech). For example, the filler (e.g., additional speech) may be a sound recorded in a different voice than the TTS (312). For example, a filler (e.g., an additional voice) may be synthesized by a first TTS (e.g., TTS (312)) corresponding to a first voice type and a second TTS (e.g., TTS (312)) corresponding to a second voice type. The filler (e.g., an additional voice) may also be selected by the user. The filler (e.g., an additional voice) may be played repeatedly.For example, the repetition playback time of a filler (e.g., additional voice) may be specified by the user or may be determined by the electronic device (101) based on the reception speed of the response text. The size (e.g., volume) of the output of the filler (e.g., additional voice) may be determined based on the interval between the first time point and the second time point (or the text speed). For example, the electronic device (101) may be configured to determine the size of the output of the filler based on the interval between the first time point and the second time point. For example, the electronic device (101) may be configured to determine the size of the output of the filler to naturally increase from a small volume to a certain level of volume in proportion to the time for waiting for the response text.

[0108] In operation 1207, according to one embodiment, the electronic device (101) (e.g., the processor (120)) may be configured to identify a first section of the response text and select a filler based on the first section. The electronic device (101) may be configured to select one filler based on the first section of the response text from among a plurality of fillers included in the determined filler type. For example, the electronic device (101) may be configured to analyze the context of the first section of the response text and, based on the analysis result, select a filler that matches the content included in the first section (e.g., a filler specified according to the content included in the first section). Accordingly, different fillers may be selected as the content included in the first section of the response text changes.

[0109] FIG. 13A is a diagram illustrating the operation of an electronic device according to one embodiment. FIG. 13B is a diagram illustrating the operation of an electronic device according to one embodiment.

[0110] Referring to FIGS. 13A and 13B , the display of response text can be described. For example, the electronic device (101) can be configured to display a screen including the response text on the display (260) while outputting a voice signal corresponding to the response text. In FIGS. 13A and 13B , the electronic device (101) can be configured to display response text generated based on the user input (e.g., “Tell me the weather today”) on the screens (e.g., 1310, 1320, 1330, 1340, 1350, and 1360).

[0111] The screens (1310, 1320, 1330, 1340, 1350, and 1360) of FIGS. 13a and 13b will be sequentially described as follows. Hereinafter, the first section of the response text will be expressed as the first response text. In the screens (1310, 1320, 1330, 1340, 1350, and 1360) of FIGS. 13a and 13b, 1311 may be an input text corresponding to a user input displayed in a text input window. In the screens (1310, 1320, 1330, 1340, 1350, and 1360) of FIGS. 13a and 13b, 1312 may be a button for receiving a user's voice input. In the screens (1310, 1320, 1330, 1340, 1350, and 1360) of FIGS. 13a and 13b, 1313 may be a screen where input text corresponding to user input is displayed in a conversational form.

[0112] The first screen (1310) may be a screen on which a first response text ("Today") and a second response text ("The weather is") are displayed (1314) while a first voice signal corresponding to the first response text ("Today") is output. At this time, the first response text ("Today") and the second response text ("The weather is") may have different properties. For example, if a voice signal corresponding to the response text (e.g., the first response text) is being output or has already been output, the response text may be displayed in a dark color, and if the response text (e.g., the second response text) has been received but the voice signal corresponding to the response text has not yet been output, the response text may be displayed in a light color. The display properties (e.g., color) of the response text are merely examples, and various properties may be applied.

[0113] The second screen (1320) is a screen that shows that the properties (e.g., color) of the second response text ("the weather") are changed (1324) as the second voice signal corresponding to the second response text ("the weather") is output after the first voice signal corresponding to the first response text ("today") is output.

[0114] The third screen (1330) may be a screen in which text or an image (e.g., "(.)") corresponding to a filler is displayed (1334) while outputting a filler (e.g., additional voice) based on the fact that the next section of the response text is not received after the second voice signal corresponding to the second response text ("the weather is") is output. The fourth screen (1340) and the fifth screen (1350) may be screens in which text or an image (e.g., "(..)", "(...)") corresponding to a filler are continuously displayed (1344, 1354) while the filler continues to be output. In the third screen (1330), the fourth screen (1340), and the fifth screen (1350), the number of periods (.) in the text or image corresponding to the filler (e.g., "(.)", "(..)", "(...)") may increase based on the fact that the next section of the response text is not continuously received. The text or image corresponding to the filler may be a text or image indicating the insertion of a filler. The text or image corresponding to the filler is not limited to "(.)", "(..)", "(...)" of FIG. 13. The text or image corresponding to the filler may be displayed within a text box as in FIG. 13, or may be displayed in an area other than a text box on the screen.

[0115] The sixth screen (1360) is a drawing that displays (1364) the third response text ("It is clear") while outputting a third voice signal corresponding to the third response text ("It is clear") based on the third response text ("It is clear") being received while the filler is being output.

[0116] FIG. 14A is a diagram illustrating the operation of an electronic device according to one embodiment. FIG. 14B is a diagram illustrating the operation of an electronic device according to one embodiment.

[0117] FIG. 14A is a diagram showing an embodiment in which a sixth screen (1360) (e.g., 1410 including 1414) of FIG. 13B is displayed after the fifth screen (1350) of FIG. 13B is displayed. FIG. 14A can be understood to be identical to or similar to the display of the screen of FIG. 13B.

[0118] FIG. 14B is a diagram illustrating an embodiment in which the display of text or an image corresponding to a filler is stopped after the fifth screen (1350) of FIG. 13B is displayed. For example, the electronic device (101) may display text or an image (e.g., "(...)") corresponding to the filler while outputting the filler due to a delay in receiving the next response text after displaying the previous response text (e.g., "Today", "The weather is"). Thereafter, the electronic device (101) may stop displaying the text or image (e.g., "(...)") corresponding to the filler while outputting a voice signal corresponding to the received response text based on the reception of the next response text (e.g., "It is sunny"), and display the received response text on the screen (e.g., 1420 including 1424). As described above, the text or image corresponding to the filler may indicate the insertion of the filler, and other text or images other than "(...)" may be used.

[0119] Those skilled in the art will appreciate that the embodiments described herein may be applied interchangeably, within the scope of their applicability. For example, those skilled in the art will appreciate that at least some operations of one embodiment described herein may be omitted and applied, and at least some operations of one embodiment may be applied interchangeably.

[0120] The technical tasks to be achieved in this document are not limited to the technical tasks mentioned above, and other technical tasks not mentioned will be clearly understood by those with ordinary skill in the technical field to which this document pertains from the description below.

[0121] The effects that can be obtained from the present disclosure are not limited to the effects mentioned above, and other effects that are not mentioned can be clearly understood by a person having ordinary skill in the art to which the present disclosure belongs from the description below.

[0122] According to one embodiment, an electronic device (101) may include a communication circuit (190; 290), a speaker (155: 255), a processor (120), and a memory (130) storing instructions. The instructions, when executed by the processor (120), may be configured to cause the electronic device (101) to transmit an input text corresponding to a user input to a server (108) via the communication circuit (190; 290). The instructions, when executed by the processor (120), may be configured to cause the electronic device (101) to receive a response text corresponding to the input text generated by the server (108) from the server (108) via the communication circuit (190; 290). The instructions, when executed by the processor (120), may be configured to cause the electronic device (101) to determine a reception speed of the response text. The instructions, when executed by the processor (120), may be configured to cause the electronic device (101) to determine, based on the reception speed, a property of a response voice corresponding to the response text. The instructions, when executed by the processor (120), may be configured to cause the electronic device (101) to output, through the speaker (155: 255), a voice signal corresponding to the response text based on the property of the response voice.

[0123] In one embodiment, the instructions, when executed by the processor (120), may be configured to cause the electronic device (101) to receive, at a first point in time, a first section of the response text from the server (108) via the communication circuit (190; 290). The instructions, when executed by the processor (120), may be configured to cause the electronic device (101) to receive, at a second point in time after the first point in time, a second section of the response text from the server (108) via the communication circuit (190; 290). The above instructions, when executed by the processor (120), may be configured to cause the electronic device (101) to output a first voice signal corresponding to the first section of the response text and to output a second voice signal corresponding to the second section, based on the property of the response voice.

[0124] In one embodiment, the property of the response voice may include a playback speed of the response voice.

[0125] In one embodiment, the instructions may be configured to cause the electronic device (101) to determine a basic playback speed as the playback speed of the response voice based on the reception speed corresponding to the response text being greater than or equal to a first reference value when executed by the processor (120). The instructions may be configured to cause the electronic device (101) to determine a playback speed of the response voice as a playback speed slower than the basic playback speed when executed by the processor (120).

[0126] According to one embodiment, the instructions, when executed by the processor (120), may be configured to cause the electronic device (101) to output a filler after outputting the first voice signal and before outputting the second voice signal based on the reception speed being less than the second reference value.

[0127] According to one embodiment, the instructions, when executed by the processor (120), may be configured to cause the electronic device (101) to determine a size of the output of the filler based on an interval between the first point in time and the second point in time.

[0128] According to one embodiment, the instructions, when executed by the processor (120), may be configured to cause the electronic device (101) to generate the first voice signal and the second voice signal using a first Text to Speech (TTS) corresponding to a first voice type. The instructions, when executed by the processor (120), may be configured to cause the electronic device (101) to generate the filler using a second TTS corresponding to a second voice type.

[0129] According to one embodiment, the instructions, when executed by the processor (120), may be configured to cause the electronic device (101) to determine the type of filler based on an interval between the first point in time and the second point in time.

[0130] In one embodiment, the type of filler may include a designated sentence representing silence, a designated voice sound, a nasal sound, a natural sound, a beep sound, white noise, or an output delay.

[0131] According to one embodiment, the instructions, when executed by the processor (120), may be configured to cause the electronic device (101) to select, as the filler, one of the fillers included in the determined type of filler based on the first section of the response text.

[0132] In one embodiment, the instructions, when executed by the processor (120), may be configured to cause the electronic device (101) to determine the reception speed corresponding to the response text based on intervals between sections of the response text and the number of words received per unit time of the response text. The instructions, when executed by the processor (120), may be configured to cause the electronic device (101) to predict a reception speed of the response text to be received later based on the determined reception speed. The instructions, when executed by the processor (120), may be configured to cause the electronic device (101) to determine the property of the response voice based on the determined reception speed and the predicted reception speed.

[0133] According to one embodiment, the electronic device (101) may include a display (160; 260). The instructions, when executed by the processor (120), may be configured to cause the electronic device (101) to display, through the display (160; 260), a first text corresponding to the first speech signal, a text corresponding to the filler, and a second text corresponding to the second speech signal.

[0134] According to one embodiment, the instructions, when executed by the processor (120), may be configured to cause the electronic device (101) to stop displaying the text corresponding to the filler and to display the second text corresponding to the second speech signal, after displaying the text corresponding to the filler.

[0135] According to one embodiment, a method of operating an electronic device (101) may include transmitting an input text corresponding to a user input to a server (108). The method may include receiving a response text corresponding to the input text generated by the server (108) from the server (108). The method may include checking a reception speed of the response text. The method may include determining a property of a response voice corresponding to the response text based on the reception speed. The method may include outputting a voice signal corresponding to the response text based on the property of the response voice.

[0136] In one embodiment, the operation of receiving the response text from the server (108) may include an operation of receiving a first section of the response text from the server (108) at a first time point. The operation of receiving the response text from the server (108) may include an operation of receiving a second section of the response text from the server (108) at a second time point after the first time point. The operation of outputting the voice signal may include an operation of outputting a first voice signal corresponding to the first section of the response text and outputting a second voice signal corresponding to the second section, based on the property of the response voice.

[0137] In one embodiment, the property of the response voice may include a playback speed of the response voice.

[0138] In one embodiment, the operation of determining the properties of the response voice may include an operation of determining a basic playback speed as the playback speed of the response voice based on whether the reception speed corresponding to the response text is greater than or equal to a first reference value. The operation of determining the properties of the response voice may include an operation of determining the playback speed of the response voice as a playback speed slower than the basic playback speed based on whether the reception speed corresponding to the response text is less than the first reference value.

[0139] In one embodiment, the method may include outputting a filler after outputting the first voice signal and before outputting the second voice signal, based on the reception speed being less than a second reference value.

[0140] In one embodiment, the method may include determining a size of the output of the filler based on a gap between the first point in time and the second point in time.

[0141] In one embodiment, the operation of outputting the voice signal may include an operation of generating the first voice signal and the second voice signal using a first Text to Speech (TTS) corresponding to a first voice type. The operation of outputting the voice signal may include an operation of generating the filler using a second TTS corresponding to a second voice type.

[0142] In one embodiment, the method may include determining a type of filler based on an interval between the first time point and the second time point.

[0143] In one embodiment, the type of filler may include a designated sentence representing silence, a designated voice sound, a nasal sound, a natural sound, a beep sound, white noise, or an output delay.

[0144] In one embodiment, the method may include selecting, as the filler, one of the fillers included in the determined type of the filler based on the first section of the response text.

[0145] According to one embodiment, the operation of checking the reception speed may include an operation of checking the reception speed corresponding to the response text based on intervals between sections of the response text and the number of words received per unit time of the response text. The operation of checking the reception speed may include an operation of predicting a reception speed of the response text to be received later based on the confirmed reception speed. The operation of determining the property of the response voice may include an operation of determining the property of the response voice based on the confirmed reception speed and the predicted reception speed.

[0146] According to one embodiment, the method may include an operation of displaying, through a display (160; 260) of the electronic device (101), a first text corresponding to the first voice signal, a text corresponding to the filler, and a second text corresponding to the second voice signal.

[0147] In one embodiment, the act of displaying the second text may include an act of stopping display of the text corresponding to the filler and displaying the second text corresponding to the second speech signal to display the second text after displaying the text corresponding to the filler.

[0148] According to one embodiment, a computer-readable recording medium storing instructions configured to cause a processor (120) of an electronic device (101) to perform at least one operation may include an operation of transmitting an input text corresponding to a user input to a server (108). The at least one operation may include an operation of receiving a response text corresponding to the input text generated by the server (108) from the server (108). The at least one operation may include an operation of checking a reception speed of the response text. The at least one operation may include an operation of determining a property of a response voice corresponding to the response text based on the reception speed. The at least one operation may include an operation of outputting a voice signal corresponding to the response text based on the property of the response voice.

[0149] In one embodiment, the operation of receiving the response text from the server (108) may include an operation of receiving a first section of the response text from the server (108) at a first time point. The operation of receiving the response text from the server (108) may include an operation of receiving a second section of the response text from the server (108) at a second time point after the first time point. The operation of outputting the voice signal may include an operation of outputting a first voice signal corresponding to the first section of the response text and outputting a second voice signal corresponding to the second section, based on the property of the response voice.

[0150] In one embodiment, the property of the response voice may include a playback speed of the response voice.

[0151] In one embodiment, the operation of determining the properties of the response voice may include an operation of determining a basic playback speed as the playback speed of the response voice based on whether the reception speed corresponding to the response text is greater than or equal to a first reference value. The operation of determining the properties of the response voice may include an operation of determining the playback speed of the response voice as a playback speed slower than the basic playback speed based on whether the reception speed corresponding to the response text is less than the first reference value.

[0152] In one embodiment, the at least one operation may include outputting a filler after outputting the first voice signal and before outputting the second voice signal, based on the reception speed being less than the second reference value.

[0153] In one embodiment, the at least one operation may include determining a magnitude of the output of the filler based on a gap between the first point in time and the second point in time.

[0154] In one embodiment, the operation of outputting the voice signal may include an operation of generating the first voice signal and the second voice signal using a first Text to Speech (TTS) corresponding to a first voice type. The operation of outputting the voice signal may include an operation of generating the filler using a second TTS corresponding to a second voice type.

[0155] In one embodiment, the at least one operation may include determining a type of filler based on an interval between the first time point and the second time point.

[0156] In one embodiment, the type of filler may include a designated sentence representing silence, a designated voice sound, a nasal sound, a natural sound, a beep sound, white noise, or an output delay.

[0157] In one embodiment, the at least one action may include selecting, as the filler, one of the fillers included in the determined type of filler based on the first section of the response text.

[0158] According to one embodiment, the operation of checking the reception speed may include an operation of checking the reception speed corresponding to the response text based on intervals between sections of the response text and the number of words received per unit time of the response text. The operation of checking the reception speed may include an operation of predicting a reception speed of the response text to be received later based on the confirmed reception speed. The operation of determining the property of the response voice may include an operation of determining the property of the response voice based on the confirmed reception speed and the predicted reception speed.

[0159] According to one embodiment, the at least one operation may include displaying, through the display (160; 260) of the electronic device (101), a first text corresponding to the first voice signal, a text corresponding to the filler, and a second text corresponding to the second voice signal.

[0160] In one embodiment, the act of displaying the second text may include an act of stopping display of the text corresponding to the filler and displaying the second text corresponding to the second speech signal to display the second text after displaying the text corresponding to the filler.

[0161] 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.

[0162] 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 (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.

[0163] 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).

[0164] Various embodiments of the present document may be implemented as software (e.g., a program) including one or more instructions stored on a storage medium that can be read by a machine (e.g., an electronic device). For example, a processor (e.g., a controller) of the machine 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 instruction called. The one or more instructions may include code generated by a compiler or code that can be executed by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' only means that the storage medium is a tangible device and does not contain a signal (e.g., electromagnetic waves), and this term does not distinguish between cases where data is stored semi-permanently and cases where it is stored temporarily in the storage medium.

[0165] According to one embodiment, the method according to various embodiments disclosed in this 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) through 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.

[0166] 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), Communication circuit (190; 290); Speaker(155: 255); Processor (120); and Includes a memory (130) for storing instructions, The above instructions, when executed by the processor (120), cause the electronic device (101) to: Transmitting input text corresponding to user input to the server (108) through the communication circuit (190; 290), Receive a response text corresponding to the input text generated by the server (108) from the server (108) through the communication circuit (190; 290), Check the reception speed of the above response text, Based on the above reception speed, determine the properties of the response voice corresponding to the response text, Based on the above properties of the above response voice, configured to cause the speaker (155: 255) to output a voice signal corresponding to the response text. Electronic devices (101).

2. In paragraph 1, The above instructions, when executed by the processor (120), cause the electronic device (101) to: At the first point in time, the first section of the response text is received from the server (108) through the communication circuit (190; 290), At a second point in time after the first point in time, a second section of the response text is received from the server (108) through the communication circuit (190; 290), Based on the above properties of the above response voice, configured to cause a first voice signal corresponding to the first section of the above response text to be output, and a second voice signal corresponding to the second section to be output. Electronic devices (101).

3. In paragraph 1 or 2, The above properties of the above response voice include the playback speed of the above response voice, Electronic devices (101).

4. In any one of paragraphs 1 to 3, The above instructions, when executed by the processor (120), cause the electronic device (101) to: Based on the reception speed corresponding to the response text being greater than or equal to the first reference value, the basic playback speed is determined as the playback speed of the response voice, configured to cause the playback speed of the response voice to be determined as a playback speed slower than the basic playback speed, based on the reception speed corresponding to the response text being less than the first reference value; Electronic devices (101).

5. In any one of paragraphs 1 to 4, The above instructions, when executed by the processor (120), cause the electronic device (101) to: Based on the fact that the reception speed is less than the second reference value, the method is configured to cause a filler to be output before outputting the second voice signal after outputting the first voice signal. Electronic devices (101).

6. In any one of paragraphs 1 to 5, The above instructions, when executed by the processor (120), cause the electronic device (101) to: configured to cause the size of the output of the filler to be determined based on the interval between the first point in time and the second point in time; Electronic devices (101).

7. In any one of paragraphs 1 to 6, The above instructions, when executed by the processor (120), cause the electronic device (101) to: Generating the first voice signal and the second voice signal using the first TTS (Text to Speech) corresponding to the first voice type, configured to cause the filler to be generated using a second TTS corresponding to the second voice type, Electronic devices (101).

8. In any one of paragraphs 1 to 7, The above instructions, when executed by the processor (120), cause the electronic device (101) to: configured to cause the type of filler to be determined based on the interval between the first time point and the second time point; Electronic devices (101).

9. In any one of paragraphs 1 to 8, The above type of filler includes a silence, a designated voice sound, a nasal sound, a natural sound, a beep sound, a white noise, or a designated sentence indicating an output delay. Electronic devices (101).

10. In any one of paragraphs 1 to 9, The above instructions, when executed by the processor (120), cause the electronic device (101) to: configured to cause selection of one of the fillers included in the determined type of the filler as the filler based on the first section of the response text. Electronic devices (101).

11. In any one of paragraphs 1 to 10, The above instructions, when executed by the processor (120), cause the electronic device (101) to: Based on the intervals between the sections of the response text and the number of words received per unit time of the response text, the reception speed corresponding to the response text is determined, Based on the above confirmed reception speed, predict the reception speed of the response text to be received later, configured to cause the property of the response voice to be determined based on the above-determined reception speed and the above-determined predicted reception speed; Electronic devices (101).

12. In any one of paragraphs 1 to 11, Including additional displays (160; 260), The above instructions, when executed by the processor (120), cause the electronic device (101) to: configured to cause the display (160; 260) to display a first text corresponding to the first voice signal, a text corresponding to the filler, and a second text corresponding to the second voice signal. Electronic devices (101).

13. In any one of paragraphs 1 to 12, The above instructions, when executed by the processor (120), cause the electronic device (101) to: After displaying the text corresponding to the filler, to display the second text, the display of the text corresponding to the filler is stopped, and the second text corresponding to the second speech signal is displayed, configured to cause the display of the second text. Electronic devices (101).

14. In the operating method of an electronic device (101), An operation of transmitting input text corresponding to user input to the server (108), An operation of receiving a response text corresponding to the input text generated by the server (108) from the server (108); An action to check the reception speed of the above response text, and An operation for determining the properties of a response voice corresponding to the response text based on the above reception speed, An operation for outputting a voice signal corresponding to the response text, based on the property of the response voice, method.

15. In a computer readable recording medium storing instructions set to perform at least one operation by a processor (120) of an electronic device (101), the at least one operation is: An operation of transmitting input text corresponding to user input to the server (108), An operation of receiving a response text corresponding to the input text generated by the server (108) from the server (108); An action to check the reception speed of the above response text, and An operation for determining the properties of a response voice corresponding to the response text based on the above reception speed, An operation for outputting a voice signal corresponding to the response text, based on the property of the response voice, Recording medium.

Images