Method, device, and recording medium for controlling proximity voice input device
The proximity voice input device addresses the inconvenience and inefficiency of conventional voice recognition by dynamically switching modes based on distance and voice analysis, ensuring quick and accurate voice input while optimizing resource usage.
Patent Information
- Application Number
- PCT/KR2025/006289
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-05-09
- Publication Date
- 2026-11-12
AI Technical Summary
Conventional voice recognition technologies require manual initiation of voice input, which is inconvenient when hands are unavailable, and misrecognition occurs due to noise and inefficient resource consumption.
A proximity voice input device that switches between idle, active, and sleep modes based on distance and voice analysis to prevent misrecognition and optimize resource usage.
Enables quick and accurate voice input by eliminating unnecessary steps, preventing misrecognition, and reducing power consumption.
Smart Images

Figure KR2025006289_12112026_PF_FP_ABST
Abstract
Description
Control method, device, and recording medium of a proximity voice input device
[0001] The present disclosure relates to a control method, device, and recording medium for a proximity voice input device.
[0002] Recently, as interest in user interfaces has grown and voice processing technology has advanced, IT devices with built-in voice recognition capabilities are becoming more common. For example, smartphones, smartwatches, smart TVs, and smart refrigerators that can recognize a user's voice and perform actions requested by the user are becoming widely available.
[0003] However, according to conventional voice recognition technology, the point at which the user begins voice input had to be specified by pressing a button or entering a predetermined trigger word before voice input could begin. The former method, involving pressing a button, inevitably caused inconvenience because voice input could not be performed when the user's hands were unavailable. Furthermore, the latter method, where the user speaks a predetermined trigger word, had limitations: it was difficult to pinpoint the input point due to various noises, such as the voices of others in the same space, even if the user was only slightly separated from the input device; additionally, even if the user spoke the trigger word, feedback via sound or light had to be provided to confirm that voice input had started before the user could begin input, resulting in a significant amount of time required from the very beginning of the voice input process.
[0004] To address this, a technology is known that recognizes voice by determining only voice input provided by the user in close proximity (i.e., proximity voice) as valid voice intended for voice input. However, according to this conventional technology, even if the input voice is not proximity voice, it may be misrecognized as proximity voice depending on the usage environment of the voice input device. Furthermore, since the voice input device must detect all input voices and determine whether they are proximity voices, the efficiency of the voice input device may be reduced due to the consumption of power for operating the voice input device and resources for determining proximity voices.
[0005] Accordingly, the inventors propose a technology that can prevent misrecognition and improve the efficiency of a device for recognizing proximity voice.
[0006] The present disclosure aims to solve the problems of the aforementioned prior art and supports users in quickly inputting voice by omitting unnecessary steps to initiate voice input.
[0007] In addition, the present disclosure aims to prevent misrecognition caused by noise input and to improve the accuracy of speech recognition.
[0008] In addition, the present disclosure also aims to improve the efficiency of the device by preventing unnecessary resource consumption during the operation of the voice input device.
[0009] A method for controlling a proximity voice input device according to one embodiment of the present disclosure comprises the steps of: acquiring an input signal including at least one of a voice signal and a sensing signal; analyzing the input signal; determining an operating mode of the proximity voice input device according to the analysis of the input signal; and generating a control signal of the proximity voice input device according to the operating mode. Herein, the operating mode of the proximity voice input device includes a first mode, a second mode, and a third mode, wherein in the first mode, the microphone of the proximity voice input device waits for the initiation of voice recognition while in a deactivated state, in the second mode, the microphone of the proximity voice input device is activated to perform voice recognition, and in the third mode, the microphone of the proximity voice input device remains in a deactivated state.
[0010] According to one embodiment of the present disclosure, when the operating mode of a proximity voice input device is a first mode, a signal regarding the distance between the proximity voice input device and an object is acquired in the step of acquiring an input signal, and the distance between the proximity voice input device and the object is compared with a preset first reference value in the step of analyzing the input signal, and in the step of determining the operating mode of the proximity voice input device, if the distance between the proximity voice input device and the object is less than or equal to the preset first reference value as a result of the input signal analysis, the operating mode may be configured to be switched to a second mode.
[0011] According to one embodiment of the present disclosure, when the proximity voice input device is in a third mode, distance information between the proximity voice input device and an object is acquired in the step of acquiring an input signal, the distance between the proximity voice input device and the object is compared with a preset second reference value in the step of analyzing the input signal, and in the step of determining the operating mode of the proximity voice input device, if the distance between the proximity voice input device and the object is greater than or equal to the preset second reference value as a result of the input signal analysis, the operating mode may be configured to be switched to a first mode.
[0012] According to one embodiment of the present disclosure, the second reference value may be set to be greater than the first reference value.
[0013] According to one embodiment of the present disclosure, when the proximity voice input device is in a second mode, a voice signal is acquired through a microphone of the proximity voice input device in the step of acquiring an input signal, and in the step of analyzing the input signal, it is determined whether the voice input to the proximity voice input device from the voice signal is proximity voice. In the step of determining the operating mode of the proximity voice input device, if the input voice is proximity voice, the operating mode is maintained in the second mode, and if it is not proximity voice, the operating mode is switched to the third mode.
[0014] In a method according to one embodiment of the present disclosure, when determining whether a voice is a proximity voice, at least one feature information associated with a proximity effect is detected from a voice signal, and depending on whether at least one feature information associated with a proximity effect is detected, a voice input to a proximity voice input device can be determined whether the voice is a proximity voice.
[0015] In a method according to one embodiment of the present disclosure, when determining whether a voice is a proximity voice, the attributes of the voice input to the proximity voice input device are classified from the voice signal, and the voice input to the proximity voice input device is determined whether the voice is a proximity voice based on the attributes of the voice and the amplitude of the voice.
[0016] In a method according to one embodiment of the present disclosure, when determining whether it is a proximity voice, it is determined whether the voice input to the proximity voice input device is noise, and if it is determined to be noise, it can be determined that the voice input to the proximity voice input device is not a proximity voice.
[0017] An apparatus for controlling a proximity voice input device according to one embodiment of the present disclosure comprises: an input signal acquisition unit for acquiring an input signal including at least one of a voice signal and a sensing signal; an input signal analysis unit for analyzing the input signal; a mode determination unit for determining an operating mode of the proximity voice input device according to the analysis of the input signal; and a control signal generation unit for generating a control signal of the proximity voice input device according to the operating mode determined by the mode determination unit. Herein, the operating mode of the proximity voice input device includes a first mode, a second mode, and a third mode, wherein in the first mode, the microphone of the proximity voice input device is deactivated and waiting for voice input, in the second mode, the microphone of the proximity voice input device is activated and voice recognition is performed, and in the third mode, the microphone of the proximity voice input device is maintained in a deactivated state.
[0018] In addition to the above, other methods for implementing the present disclosure, other devices, and a recording medium for recording a computer program for executing the method are further provided.
[0019] According to one embodiment of the present disclosure, unnecessary steps for initiating voice input are omitted, allowing the user to quickly input voice.
[0020] In addition, according to one embodiment of the present disclosure, the microphone can be disabled when the voice input to the proximity voice input device is not proximity voice, thereby preventing misrecognition due to noise input and improving the accuracy of voice recognition.
[0021] In addition, according to one embodiment of the present disclosure, by selectively deactivating the microphone of the proximity voice input device, unnecessary resource consumption during the operation of the voice input device can be prevented and the efficiency of the device can be improved.
[0022] FIG. 1 is a diagram schematically illustrating an overall system environment for proximity voice input according to one embodiment of the present disclosure.
[0023] FIG. 2 is a diagram showing the configuration of a proximity voice input device according to one embodiment of the present disclosure.
[0024] FIG. 3 is a functional block diagram schematically illustrating the functional configuration of a device for controlling a proximity voice input device according to one embodiment of the present disclosure.
[0025] FIG. 4 is a diagram exemplarily showing the input of proximity voice to a proximity voice input device according to one embodiment of the present disclosure.
[0026] FIG. 5 is a drawing showing a proximity voice input device according to another embodiment of the present disclosure.
[0027] FIG. 6 is an operation flowchart illustrating an exemplary method of controlling a proximity voice input device according to one embodiment of the present disclosure.
[0028] [Explanation of the symbol]
[0029] 110: Proximity voice input device
[0030] 120: Communication network
[0031] 130: User terminal
[0032] 140: Server
[0033] 150: External device
[0034] 201: Mike
[0035] 203: Sensor section
[0036] 205: Communications Department
[0037] 207: Processor
[0038] 300: Control device for proximity voice input device
[0039] 301: Input signal acquisition unit
[0040] 303: Input signal analysis unit
[0041] 305: Mode Determination Unit
[0042] 307: Control signal generation unit
[0043] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In the following, specific descriptions of already known functions and configurations are omitted where it is deemed that doing so would unnecessarily obscure the essence of the present disclosure. Furthermore, it should be understood that the content described below relates only to one embodiment of the present disclosure and that the present disclosure is not limited thereto.
[0044] The terms used in this disclosure are used merely to describe specific embodiments and are not intended to limit this disclosure. For example, a component expressed in the singular should be understood as a concept including a plural component unless the context clearly implies only the singular. It should be understood that the term "and / or" used in this disclosure encompasses any possible combination of one or more of the items listed. Terms such as "comprising" or "having" used in this disclosure are intended only to specify the existence of the features, numbers, steps, motions, components, parts, or combinations thereof described in this disclosure, and the use of such terms is not intended to exclude the existence or addition of one or more other features, numbers, steps, motions, components, parts, or combinations thereof.
[0045] In embodiments of the present disclosure, a 'module' or 'part' refers to a functional part that performs at least one function or motion, and may be implemented in hardware or software, or a combination of hardware and software. Additionally, a plurality of 'modules' or 'parts' may be integrated into at least one software module and implemented by at least one processor, except for 'modules' or 'parts' that need to be implemented in specific hardware.
[0046] Additionally, unless otherwise defined, all terms used in this disclosure, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which this disclosure pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology and should not be interpreted as being overly limited or expanded unless explicitly defined otherwise in this disclosure.
[0047] FIG. 1 is a diagram schematically illustrating an overall system environment for proximity voice input according to one embodiment of the present disclosure.
[0048] Referring to FIG. 1, the entire system environment (100) for proximity voice input may include a proximity voice input device (110), a communication network (120), a user terminal (130), and a server (140).
[0049] A proximity voice input device (110) according to one embodiment of the present disclosure may be an electronic device having voice input and communication functions. The proximity voice input device (110) may be a portable device that a user can carry or a wearable device that a user can wear. In one embodiment, the proximity voice input device (110) may be a smart ring in the form of a ring.
[0050] According to one embodiment of the present disclosure, a proximity voice input device (110) can communicate with a user terminal (130) through a communication network (120). In one embodiment, the proximity voice input device (110) can receive user input such as a button press or voice, and a signal regarding the user input received by the proximity voice input device (110) can be transmitted to the user terminal (130) through the communication network (120).
[0051] A communication network (120) according to one embodiment of the present disclosure may include any wired or wireless communication network, such as a TCP / IP communication network. According to one embodiment of the present disclosure, the communication network (120) may be composed of a Local Area Network (LAN), a Metropolitan Area Network (MAN), a Wide Area Network (WAN), an Internet network, etc., but the present disclosure is not limited thereto. For example, the communication network (120) may be a wireless data communication network that implements conventional communication methods such as WiFi communication, WiFi-Direct communication, Long Term Evolution (LTE) communication, 5G communication, Bluetooth communication (including Bluetooth Low Energy (BLE) communication), infrared communication, ultrasonic communication, etc., in at least a part thereof, and as another example, the communication network (120) may be an optical communication network that implements conventional communication methods such as Light Fidelity (LiFi), etc., in at least a part thereof.
[0052] A user terminal (130) according to one embodiment of the present disclosure is a device capable of communicating with a proximity voice input device (110) through a communication network (120). The user terminal (130) is a digital device equipped with memory means and equipped with a microprocessor to have computational capabilities, and may be, for example, a smartphone. The user terminal (130) of the present disclosure is not limited to what is illustrated, and the user terminal (130) may be a smart pad, a notebook computer, a PDA, a desktop, and any other device capable of achieving the purpose of the present disclosure may be used as the user terminal (130) of the present disclosure.
[0053] According to one embodiment of the present disclosure, a user terminal (130) can receive a signal regarding user input from a proximity voice input device (110) through a communication network (120) and can perform a function according to the user input. For example, when voice is detected by the proximity voice input device (110), the corresponding voice signal is transmitted to the user terminal (130) through the communication network (120), and the user terminal (130) can generate a response signal or a control signal according to the voice recognized from the voice signal and the user's intention.
[0054] A server (140) according to one embodiment of the present disclosure is a server system capable of communicating with a user terminal (130) through a communication network (120). The server (140) may be an independent physical server or a virtual server such as a cloud server.
[0055] According to one embodiment of the present disclosure, a server (140) is an artificial intelligence server that receives a voice signal from a user terminal (130), performs voice recognition thereon, and then generates feedback. In one embodiment, the server (140) provides the generated feedback to the user terminal (130), and the user terminal (130) may generate a response signal and / or a control signal by referring to the feedback.
[0056] According to one embodiment of the present disclosure, a user terminal (130) may generate a response signal based on a recognized voice and transmit it to an external device (150). In one embodiment, the external device (150) to which the response signal is transmitted may be an earpiece, a headset, or a speaker. For example, the user terminal (130) may transmit the response signal to an earpiece worn by the user and may respond to the voice input by the user through the earpiece.
[0057] According to one embodiment of the present disclosure, a user terminal (130) may generate a control signal based on a recognized voice and transmit it to an external device (150). In one embodiment, the external device (150) to which the control signal is transmitted may be a smart TV, an air conditioner, a refrigerator, a home appliance, a smart car, etc. For example, the user terminal (130) may generate a control signal based on the user's intention or request identified from the voice signal and transmit it to a smart TV, and the smart TV may be controlled (power on / off, channel or volume change, etc.) according to the control signal.
[0058] Meanwhile, the external device (150) to which the response signal and / or control signal is transmitted is not limited to those exemplified above, and it should be understood that any electronic device capable of providing an auditory or visual response to a user, or any electronic device equipped with wireless communication capabilities that can be controlled according to the user's intention, is included.
[0059] In the illustrated embodiment, it is described that the proximity voice input device (110) communicates with the user terminal (130) and the user terminal (130) communicates with the server (140); however, the system for proximity voice recognition may be implemented differently. For example, the proximity voice input device (110) may communicate directly with the server (140). In this case, the proximity voice input device (110) transmits a voice signal detected via the communication network (120) to the server (140), and the server (140) may recognize the voice from the voice signal and then generate and transmit a response signal and / or a control signal. As another example, the user terminal (130) may function as an on-device AI to directly recognize the voice from the voice signal and generate a response signal and / or a control signal without communicating with the server (140). As another example, the proximity voice input device (110) can communicate directly with an IoT device other than the user terminal (130) or server (140), such as an AI speaker.
[0060] In addition, the proximity voice input device (110) is configured to perform operations such as voice recognition, the generation of response signals and / or control signals, and the operations may be processed at the proximity voice input device (110) instead of being performed at an external device such as a user terminal (130) or a server (140).
[0061] FIG. 2 is a diagram showing the configuration of a proximity voice input device according to one embodiment of the present disclosure.
[0062] Referring to FIG. 2, a proximity voice input device (110) according to one embodiment of the present disclosure may include a microphone (201), a sensor unit (203), a communication unit (205), and a processor (207).
[0063] A microphone (201) of a proximity voice input device (110) according to one embodiment of the present disclosure is for voice input and can perform the function of detecting a user's voice and generating a voice signal. The microphone (201) may be installed on one side of the proximity voice input device (110) and configured to detect external voice. In one embodiment, the microphone (201) can perform the function of detecting the sound pressure of the input voice.
[0064] A sensor unit (203) of a proximity voice input device (110) according to one embodiment of the present disclosure is for detecting proximity and / or movement of the proximity voice input device (110) and can perform the function of generating a sensing signal regarding proximity information and / or movement information.
[0065] According to one embodiment of the present disclosure, the sensor unit (203) may include a proximity sensor. The proximity sensor may detect the distance between the proximity voice input device (110) and an object, and the sensor unit (203) may generate a sensing signal based on the proximity information of the proximity voice input device (110) detected by the proximity sensor. The proximity sensor may be at least one of an optical sensor, a photoelectric sensor, an ultrasonic sensor, an inductive sensor, a capacitive sensor, a resistive sensor, an eddy current sensor, an infrared sensor, and a magnetic sensor.
[0066] According to one embodiment of the present disclosure, the sensor unit (203) may include an IMU sensor. The IMU sensor may detect movement (e.g., a change in height) of the proximity voice input device (110), and the sensor unit (203) may generate a sensing signal regarding movement information of the proximity voice input device (110) detected by the IMU sensor.
[0067] According to one embodiment of the present disclosure, the sound pressure of voice input from the microphone (201) can be detected, but alternatively, the sensor unit (203) may include a sound pressure sensor. For example, the sensor unit (203) may include at least one of a pressure sensor, a wind pressure sensor, and a noise sensor as a sound pressure sensor for detecting sound pressure.
[0068] A communication unit (205) of a proximity voice input device (110) according to one embodiment of the present disclosure may function to enable the proximity voice input device (110) to communicate with an external communication network. A communication unit (205) of a voice input device (110) according to one embodiment of the present disclosure may function to enable the voice input device (110) to communicate with an external communication network. For example, the communication unit (205) may perform the function of transmitting a voice signal to a user terminal (130) or a server (140).
[0069] A processor (207) of a proximity voice input device (110) according to one embodiment of the present disclosure can perform the function of receiving and processing at least one of a voice signal regarding voice input from a microphone (201) and a sensing signal generated from a sensor unit (203). In one embodiment, the voice signal from the microphone (201) and the sensing signal from the sensor unit (203) can be transmitted to the processor (207) for processing and can be transmitted to a user terminal (130) or a server (140) through a communication unit (205).
[0070] A proximity voice input device (110) according to one embodiment of the present disclosure may further include a storage unit (not shown). According to one embodiment of the present disclosure, the storage unit may store device information, user information, etc. of the proximity voice input device (110), and may also store voice input to the proximity voice input device (110).
[0071] A proximity voice input device (110) according to one embodiment of the present disclosure is configured such that the operating mode of the device is controlled depending on whether there is proximity voice, in order to prevent misrecognition of the input voice and improve the efficiency of the device. Hereinafter, a control device for a voice input device (hereinafter referred to as the 'control device') for controlling the operating mode of the proximity voice input device (110) and a method for controlling the proximity voice input device through the same will be described.
[0072] FIG. 3 is a functional block diagram schematically illustrating the functional configuration of a device for controlling a proximity voice input device according to one embodiment of the present disclosure.
[0073] Referring to FIG. 3, the control device (300) may include an input signal acquisition unit (301), an input signal analysis unit (303), a mode determination unit (305), and a control signal generation unit (307). The components illustrated in FIG. 3 do not reflect all functions of the control device (300) and are not essential, so the control device (300) may include more components than those illustrated or fewer components.
[0074] According to one embodiment of the present disclosure, an input signal acquisition unit (301), an input signal analysis unit (303), a mode determination unit (305), and a control signal generation unit (307) may be program modules in which at least a portion thereof communicates with an external system (not shown). Such program modules may be included in the control device (300) in the form of an operating system, an application program module, or other program modules, and may be physically stored in various known storage devices. Additionally, such program modules may be stored in a remote storage device capable of communicating with the control device (300). Meanwhile, such program modules include, but are not limited to, routines, subroutines, programs, objects, components, data structures, etc., which perform specific tasks or execute specific abstract data types as described below according to the present disclosure.
[0075] An input signal acquisition unit (301) according to one embodiment of the present disclosure may perform the function of acquiring an input signal including at least one of a voice signal and a sensing signal. In one embodiment, the input signal acquisition unit (301) may acquire a signal regarding voice input through a microphone (201) of a proximity voice input device (110), and a signal regarding proximity information and / or movement information input through a sensor unit (203) of a proximity voice input device (110). For example, the signal regarding voice acquired by the input signal acquisition unit (301) may include information regarding the attributes of the voice, the loudness or sound pressure of the voice, and the signal regarding proximity information may include information regarding the distance between the proximity voice input device (110) and an object.
[0076] An input signal analysis unit (303) according to one embodiment of the present disclosure can perform the function of analyzing an input signal acquired from an input signal acquisition unit (301). The analysis of the input signal in the input signal analysis unit (303) is for determining the operating mode of the proximity voice input device (110), and according to one embodiment of the present disclosure, the operating mode of the proximity voice input device (110) may include a first mode, a second mode, and a third mode.
[0077] The first mode is a so-called idle mode, which is an operating mode that waits for the start of voice recognition while the microphone (201) of the proximity voice input device (110) is deactivated. In the first mode, the microphone (201) of the proximity voice input device (110) is deactivated, but if certain conditions are satisfied, the microphone (201) can be activated and switched to the second mode.
[0078] The second mode is a so-called activated mode, which is an operating mode in which the microphone (201) of the proximity voice input device (110) is activated to perform voice recognition. In the second mode, voice is input through the microphone (201) of the proximity voice input device (110), and voice recognition can be performed depending on whether the input voice is proximity voice.
[0079] The third mode is a so-called sleep mode, which is an operating mode in which the microphone (201) of the proximity voice input device (110) remains in a deactivated state. In the third mode, even when voice is input in close proximity to the proximity voice input device (110), the microphone (201) remains in a deactivated state if certain conditions are satisfied.
[0080] According to one embodiment of the present disclosure, the input signal analysis unit (303) can compare the distance between the proximity voice input device (110) and an object with a preset reference value. Here, the reference value is a value that serves as a reference for determining the operating mode of the proximity voice input device (110).
[0081] In one embodiment, the input signal analysis unit (303) can compare the distance between the proximity voice input device (110) and an object with a preset first reference value. The first reference value is a value that serves as a reference for switching the operating mode of the proximity voice input device (110) from a first mode to a second mode, and for example, the first reference value may be 5 cm.
[0082] In one embodiment, the input signal analysis unit (303) can compare the distance between the proximity voice input device (110) and an object with a preset second reference value. The second reference value is a value that serves as a reference for switching the operating mode of the proximity voice input device (110) from a third mode to a first mode, and for example, the second reference value may be 10 cm.
[0083] According to one embodiment of the present disclosure, the input signal analysis unit (303) can analyze the input signal to determine whether the voice input to the proximity voice input device (110) is proximity voice. As described above, proximity voice is voice input by a user with the intention of voice recognition, and the proximity voice can be determined by referring to the voice input to the proximity voice input device (110), the distance between the proximity voice input device (110) and an object (e.g., the user's mouth, etc.).
[0084] In one embodiment, the input signal analysis unit (303) detects at least one feature information associated with a proximity effect from the voice signal acquired by the input signal acquisition unit (301), and can determine whether it is a proximity voice based on whether at least one feature information associated with a proximity effect is detected.
[0085] FIG. 4 is a diagram illustrating an exemplary manner of inputting voice to a proximity voice input device according to one embodiment of the present disclosure. As shown in FIG. 4, in order to input voice to a proximity voice input device (110) (e.g., a smart ring), the proximity voice input device (110) (or the microphone (201) of the proximity voice input device (110)) is first moved close to the mouth (or lips).
[0086] As such, when speaking with the mouth close to the proximity voice input device (110), characteristic phenomena associated with close-range speech may occur. For example, a proximity effect may occur in which sensitivity to low frequencies increases as the distance between the sound source and the microphone (201) becomes closer. Another example is that breathing sounds, such as nasal air or breath, may be mixed in with the voice, or sounds caused by contact between body parts (e.g., the sound of a hand or finger touching the face) may be mixed in during the process of positioning the proximity voice input device (110) near the lips. Yet another example is that as the proximity voice input device (110) gets closer to the skin of the face, the sound may be absorbed by the skin, causing background noise to be reduced.
[0087] The input signal analysis unit (303) detects characteristic information based on characteristic phenomena of the above-mentioned near-field speech in the acquired voice signal and, based on this, can determine whether the acquired voice is a near-field speech.
[0088] For example, the input signal analysis unit (303) can detect feature information associated with the proximity effect by calculating the relative magnitude of the low-frequency range. The input signal analysis unit (303) can extract waveform features through analysis of the voice signal in the time domain or extract frequency features through analysis of the voice signal in the frequency domain. For example, the input signal analysis unit (303) can divide the voice signal into multiple frames of a fixed time unit, convert each frame from the time domain to the frequency domain to obtain a spectrum, and arrange each spectrum on the time axis to obtain a spectrogram. Furthermore, the input signal analysis unit (303) can extract frequency features through analysis of the spectrum or spectrogram, and can detect feature information associated with the proximity effect by calculating the ratio of the low-frequency range to the mid-frequency range in the spectrum or spectrogram of the voice signal to calculate the relative magnitude of the low-frequency range.
[0089] As another example, the input signal analysis unit (303) can detect feature information associated with breathing sounds. For example, the input signal analysis unit (303) can detect feature information associated with breathing sounds by comparing the waveform features or frequency features of the voice signal with the waveform features or frequency features of a preset reference breathing sound.
[0090] As another example, the input signal analysis unit (303) can detect feature information associated with sound absorption by the skin of a user in close proximity to the proximity voice input device (110). For example, the input signal analysis unit (303) can detect feature information associated with sound absorption by the skin of a user in close proximity to the proximity voice input device (110) by analyzing the degree of reduction of the background noise level.
[0091] As another example, the input signal analysis unit (303) can detect feature information associated with sound caused by contact between the user's body parts associated with the proximity voice input device (110). For example, the input signal analysis unit (303) can detect feature information associated with sound caused by contact between body parts by comparing the waveform features or frequency features of the voice signal with the waveform features or frequency features of the sound caused by contact between body parts that are pre-set.
[0092] The detection of the above feature information can be achieved through an artificial intelligence-based classification model. The artificial intelligence-based classification model may be trained based on feature information associated with proximity effects.
[0093] In one embodiment, the input signal analysis unit (303) can determine whether the voice signal is a close voice by referring to whether the detected feature information is detected. For example, if at least one feature information associated with a close voice is detected in the voice signal, the input signal analysis unit (303) can determine that the input voice is a close voice.
[0094] According to one embodiment of the present disclosure, the input signal analysis unit (303) may classify the attributes of the voice and determine whether the input voice is a close voice based on the attributes of the voice and the amplitude of the voice.
[0095] Speech consists of combinations of vowels and consonants, and the resulting sounds encompass a wide frequency spectrum. These properties of speech can vary depending on the method of voice generation.
[0096] For example, a human whisper differs from normal speech in terms of frequency and timbre because it is produced without the vibration of the vocal cords. Specifically, in whispering, vowel production is primarily driven by airflow, while consonant pronunciation occurs without vocal cord vibration. Consequently, the voice spectrum of a whisper emphasizes the high-frequency range relatively less than that of normal speech, which contributes to the lower and softer timbre of a whisper. On the other hand, normal speech is produced using the vocal cords. Since normal speech involves the vibration of the vocal cords to produce sound, attempting to speak too softly prevents the cords from vibrating properly, making it difficult to produce a clear sound; therefore, normal speech cannot be lowered below a certain volume. Furthermore, shouting is a sound generated by applying significant pressure to the vocal cords, utilizing much stronger vocal cord vibration and airflow than normal speech. The voice spectrum of shouting is more broadly distributed than that of normal speech, and is characterized by increased energy, particularly in the low-frequency and high-frequency ranges. As a result, shouting possesses a powerful and penetrating timbre.
[0097] In summary, whispering is characterized by low volume, low pitch, a spectral shape with decreasing energy in the low-frequency band, and periodicity. Additionally, because whispering requires little vocal effort, the spectral slope is steep and the attenuation rate is high. On the other hand, shouting is characterized by high volume, high pitch, a spectral shape with increasing energy in the high-frequency band, and non-periodic features. Furthermore, because shouting requires a large vocal effort, the spectral slope is gentle (i.e., high high-frequency energy) and the attenuation rate is low. Normal speech exhibits intermediate levels in terms of volume, pitch, vocal effort, spectral slope, and attenuation rate, and is characterized by clear periodicity.
[0098] An input signal analysis unit (303) according to one embodiment of the present disclosure can classify the attributes of the voice based on these differences between whispers and normal voice.
[0099] For example, the volume of a voice can be determined by measuring the average amplitude or RMS (root mean square) value of the voice signal, and the pitch can be calculated by measuring the fundamental frequency of the voice signal. In addition, periodicity can be detected using the autocorrelation of the voice signal, and vocal effort can be determined by analyzing the attenuation characteristics and spectral slope of the voice signal.
[0100] In one embodiment, the input signal analysis unit (303) can classify the voice as a whisper if the ratio of the volume of the high-frequency band (e.g., a frequency band of 1 kHz or more) to the volume of the low-frequency band (e.g., a frequency band of 500 Hz or less) in the acquired voice signal is less than or equal to a predetermined value. Conversely, if the ratio of the volume of the high-frequency band to the volume of the low-frequency band exceeds a predetermined value, the voice can be classified as normal voice. Meanwhile, in shouting, the volume in the high-frequency band is emphasized compared to normal voice, and at the same time, the volume in the low-frequency band also increases compared to normal voice. That is, since shouting shows an increase in volume across the overall frequency band, it is possible to determine whether the voice corresponds to shouting by comparing the spectrum shape with the characteristics of the voice signal of shouting, along with the ratio of the volume of the high-frequency band to the volume of the low-frequency band.
[0101] The input signal analysis unit (303) may classify the attributes of the voice using an artificial intelligence-based classification model. For example, the input signal analysis unit (303) may classify the attributes of the voice using a voice attribute classification model learned based on the spectrum of multiple voice signals accumulated in the input.
[0102] In one embodiment, the input signal analysis unit (303) can calculate the speech distance of a voice signal based on the attributes of the classified voice and the amplitude of the voice. For example, the input signal analysis unit (303) can calculate the speech distance of a voice by referring to the correlation between the speech distance and the sound pressure according to the attributes of the voice.
[0103] In one embodiment, the input signal analysis unit (303) can determine whether it is a proximity voice by referring to the speech distance calculated based on the attributes and amplitude of the voice and the distance between the proximity voice input device (110) and the object measured through the sensor unit (203). For example, the distance obtained from the proximity sensor of the sensor unit (203) can be compared with the distance calculated based on the attributes and sound pressure of the voice, and if the two distances are similar, it can be determined that the input voice is the user's proximity voice.
[0104] According to one embodiment of the present disclosure, the input signal analysis unit (303) determines whether the voice input to the proximity voice input device (110) is noise, and if it is determined to be noise, it can determine that the voice input to the proximity voice input device (110) is not proximity voice.
[0105] In one embodiment, the input signal analysis unit (303) may determine that the input sound is noise if it is determined that the sound is not uttered from a human body. That is, even if it is determined to be a sound input from a short distance based on sensing information (e.g., distance information measured through a proximity sensor), if it is not a voice uttered from a human body, it may be classified as noise and determined not to be a sound from a short distance.
[0106] A mode determining unit (305) according to one embodiment of the present disclosure can determine the operating mode of a proximity voice input device based on the analysis of an input signal. In one embodiment, the mode determining unit (305) can determine the operating mode of the proximity voice input device (110) to be one of the first to third modes described above.
[0107] When the operating mode of the proximity voice input device (110) is in the first mode (idle mode), if the input signal analysis unit (303) determines that the distance between the proximity voice input device (110) and an object is less than or equal to a preset first reference value, the mode determination unit (305) can switch the operating mode of the proximity voice input device (110) to the second mode (active mode). For example, when a user brings the proximity voice input device (110) to the area around their mouth to input proximity voice, and the distance between the user's mouth and the proximity voice input device (110) becomes less than or equal to the first reference value (e.g., 5 cm), the mode determination unit (305) can switch the operating mode of the proximity voice input device (110) to the second mode, which can perform voice recognition by activating the microphone (201).
[0108] When the operating mode of the proximity voice input device (110) is in the second mode (active mode), if the input signal analysis unit (303) determines from the voice signal obtained through the microphone of the proximity voice input device (110) that the voice input to the proximity voice input device (110) is not proximity voice, the mode determination unit (305) can switch the operating mode of the proximity voice input device (110) to the third mode (sleep mode). Specifically, if the input signal analysis unit (303) determines that the voice input to the proximity voice input device (110) is not proximity voice based on at least one feature information associated with the proximity effect detected from the voice signal, the attributes of the voice, the loudness of the voice, the presence of noise, etc., the mode determination unit (305) can switch the operating mode of the proximity voice input device (110) to the third mode in which the microphone (201) remains in a deactivated state.
[0109] This is intended to prevent unintended voice recognition, i.e., misrecognition, from occurring by disabling the microphone (201) and blocking voice input when voice or noise is input while the proximity voice input device (110) is in close proximity to an object, but the input voice is not the voice that the user intended to input for voice recognition. Additionally, by disabling the microphone when the voice input in close proximity to the proximity voice input device (110) is not a proximity voice, power consumption of the proximity voice input device (110) due to voice signal generation can be prevented, and resource consumption due to voice signal processing can also be prevented.
[0110] When the operating mode of the proximity voice input device (110) is in the third mode (sleep mode), if the input signal analysis unit (303) determines that the distance between the proximity voice input device (110) and an object is greater than or equal to a preset second reference value, the mode determination unit (305) can switch the operating mode of the proximity voice input device (110) to the first mode (idle mode). For example, if the distance between the proximity voice input device (110) and an object increases to greater than the second reference value (e.g., 10 cm), the mode determination unit (305) may switch the operating mode of the proximity voice input device (110) to the first mode, which is a state of waiting for voice input to begin, by considering that the state of inputting noise has ended.
[0111] A control signal generating unit (307) according to one embodiment of the present disclosure can generate a control signal for a proximity voice input device according to an operating mode. Specifically, the control signal generating unit (307) can generate a control signal regarding whether a microphone is activated, whether voice recognition is initiated, etc., according to the operating mode of the proximity voice input device (110).
[0112] According to one embodiment of the present disclosure, a control device (300) may be provided in a user terminal (130) or a server (140) that communicates with a proximity voice input device (110). For example, the control device (300) may be a user terminal (130) or a server (140). In one embodiment, a voice signal from the proximity voice input device (110) is transmitted to the control device (300) via a communication network (120), for example, low-power Bluetooth, Wi-Fi, etc., and the control device (300) may determine the operating mode of the proximity voice input device (110) and generate a control signal, etc.
[0113] However, the present disclosure is not limited thereto, and at least some of the components or functions of the control device (300) may be realized within the proximity voice input device (110) or included within the proximity voice input device (110) as needed. Additionally, in some cases, all functions and all components of the control device (300) may be entirely executed within the proximity voice input device (110) or entirely included within the proximity voice input device (110).
[0114] Meanwhile, in one embodiment of the present disclosure, the proximity voice input device (110) is described as being a ring-shaped smart ring, but the proximity voice input device may be implemented in other forms.
[0115] FIG. 5 is a drawing showing a proximity voice input device according to another embodiment of the present disclosure. Referring to FIG. 5, the proximity voice input device may have a form other than a ring shape, such as a remote control (500a) equipped with a microphone, a stylus pen (500b), a smart watch (500c), or a smartphone (500d). As illustrated, the proximity voice input device (500a, 500b, 500c, 500d) is configured to enable voice input (proximity voice input) by providing a microphone (501a, 501b, 501c, 501d). In addition, the proximity voice input device according to the present disclosure may be implemented in various forms other than those exemplified, provided that it is equipped with a microphone capable of voice input.
[0116] FIG. 6 is an operation flowchart illustrating an exemplary method of controlling a proximity voice input device according to one embodiment of the present disclosure. Each step of the method of controlling the proximity voice input device (110) in the present embodiment must not necessarily be performed in the order illustrated, nor does it mean that each step is necessarily essential. That is, it should be understood that each step of the method of controlling the proximity voice input device (110) according to the present embodiment may be performed in a different order than illustrated, and that some steps may be omitted or other steps may be added.
[0117] In step (S601), the control device (300) of the proximity voice input device acquires an input signal comprising at least one of a voice signal or a sensing signal.
[0118] In step (S603), the control device (300) analyzes the acquired input signal.
[0119] In one embodiment, in step (S603), the distance between the proximity voice input device (110) and the object can be compared with a preset reference value. For example, the control device (300) can compare the distance between the proximity voice input device (110) and the object with a preset first reference value (e.g., 5 cm). As another example, the control device (300) can compare the distance between the proximity voice input device (110) and the object with a preset second reference value (e.g., 10 cm).
[0120] In one embodiment, in step (S603), it can be determined whether the voice input to the proximity voice input device (110) is proximity voice. For example, the control device (300) can determine whether the voice input to the proximity voice input device (110) is proximity voice based on at least one feature information associated with a proximity effect detected from a voice signal, the attributes of the voice, the loudness of the voice, the presence of noise, etc.
[0121] In step (S605), the control device (300) determines the operating mode of the proximity voice input device (110) based on the analysis of the input signal.
[0122] In one embodiment, the control device (300) may determine the operating mode of the proximity voice input device (110) as one of a first mode in which the microphone (201) is deactivated and waiting for voice recognition to begin, a second mode in which the microphone (201) is activated and voice recognition is performed, and a third mode in which the microphone (201) remains in a deactivated state.
[0123] For example, when the operating mode of the proximity voice input device (110) is in the first mode (idle mode), if it is determined that the distance between the proximity voice input device (110) and an object is less than or equal to a preset first reference value (e.g., 5 cm), the control device (300) can switch the operating mode of the proximity voice input device (110) to the second mode (active mode). Additionally, when the operating mode of the proximity voice input device (110) is in the second mode (active mode), if it is determined that the voice input to the proximity voice input device (110) is not proximity voice based on the voice signal obtained through the microphone of the proximity voice input device (110), the control device (300) can switch the operating mode of the proximity voice input device (110) to the third mode (sleep mode). Additionally, when the operating mode of the proximity voice input device (110) is in the third mode (sleep mode), if it is determined that the distance between the proximity voice input device (110) and an object is greater than or equal to a preset second reference value (e.g., 10 cm), the control device (300) and the mode determination unit (305) can switch the operating mode of the proximity voice input device (110) to the first mode (idle mode).
[0124] In step (S607), the control device (300) generates a control signal for the proximity voice input device according to the operating mode. Specifically, the control device (300) may generate a control signal regarding whether the microphone is activated, whether voice recognition is initiated, etc., according to the operating mode of the proximity voice input device (110).
[0125] In this way, by dynamically controlling the activation and deactivation of the proximity voice input device (110), particularly the microphone (201) of the proximity voice input device (110), through the control device (300) of the proximity voice input device, misrecognition due to the input of noise can be prevented, and the resource usage of the proximity voice input device (110) and the control device (300) can be reduced, thereby improving the efficiency of the proximity voice input.
[0126] Although the present disclosure has been described above with specific details such as specific components and limited embodiments, the embodiments are provided merely to aid in a more comprehensive understanding of the present disclosure and are not limited thereto. A person skilled in the art to which the present disclosure pertains may make various modifications and variations from this description. For example, appropriate results may be achieved even if the described techniques are performed in a different order than described, or if the described components are combined in a different form than described, or if they are replaced or substituted by other components or equivalents.
[0127] Meanwhile, the embodiments according to the present disclosure described above may be implemented in the form of program instructions that can be executed through various computer components and recorded on a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc., either alone or in combination. The program instructions recorded on the computer-readable recording medium may be those specifically designed and configured for the present disclosure or those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. Hardware devices may be modified into one or more software modules to perform processing according to the present disclosure, and vice versa.
[0128] As such, the concept of the present disclosure is not limited to the embodiments described above, and all things equivalent to or modified to the claims set forth below, as well as the claims set forth below, shall be considered to fall within the scope of the concept of the present disclosure.
Claims
1. A method for controlling a proximity voice input device, A step of acquiring an input signal including at least one of a voice signal and a sensing signal, Step of analyzing the above input signal, A step of determining the operating mode of the proximity voice input device according to the analysis of the above input signal and A step of generating a control signal for the proximity voice input device according to the above operating mode Includes, The operating modes of the above proximity voice input device include a first mode, a second mode, and a third mode, and A method of waiting for the initiation of voice recognition with the microphone of the proximity voice input device deactivated in the first mode, performing voice recognition with the microphone of the proximity voice input device activated in the second mode, and maintaining the microphone of the proximity voice input device in a deactivated state in the third mode.
2. In Paragraph 1, When the operating mode of the above proximity voice input device is the first mode, In the step of acquiring the above input signal, a signal regarding the distance between the proximity voice input device and the object is acquired, and In the step of analyzing the input signal, the distance between the proximity voice input device and the object is compared with a preset first reference value, and A method for determining the operating mode of the proximity voice input device, wherein if the distance between the proximity voice input device and an object is less than or equal to a preset first reference value as a result of analyzing the input signal, the operating mode is switched to a second mode.
3. In Paragraph 2, When the above proximity voice input device is in third mode, In the step of acquiring the above input signal, distance information between the proximity voice input device and the object is acquired, and In the step of analyzing the input signal, the distance between the proximity voice input device and the object is compared with a preset second reference value, A method for determining the operating mode of the proximity voice input device, wherein if the distance between the proximity voice input device and an object is greater than or equal to a preset second reference value as a result of analyzing the input signal, the operating mode is switched to a first mode.
4. In Paragraph 3, A method in which the second reference value is set to be greater than the first reference value.
5. In Paragraph 1, When the above proximity voice input device is in the second mode, In the step of acquiring the above input signal, a voice signal is acquired through the microphone of the proximity voice input device, and In the step of analyzing the input signal, it is determined whether the voice input from the voice signal to the proximity voice input device is proximity voice, and A method for determining the operating mode of the above-mentioned proximity voice input device, wherein if the input voice is proximity voice, the operating mode is maintained in a second mode, and if it is not proximity voice, the operating mode is switched to a third mode.
6. In Paragraph 5, A method for determining whether the voice input to the proximity voice input device is a proximity voice, wherein, when determining whether the voice is a proximity voice, at least one feature information associated with a proximity effect is detected from the voice signal, and depending on whether the at least one feature information associated with the proximity effect is detected, the voice input to the proximity voice input device is a proximity voice.
7. In Paragraph 5, A method for determining whether the voice input to the proximity voice input device is a proximity voice, wherein the attributes of the voice input to the proximity voice input device are classified from the voice signal, and the voice input to the proximity voice input device is determined based on the attributes of the voice and the amplitude of the voice.
8. In Paragraph 5, A method for determining whether the voice input to the proximity voice input device is noise when determining whether the voice input to the proximity voice input device is noise, and if it is determined to be noise, determining that the voice input to the proximity voice input device is not proximity voice.
9. A recording medium for recording a computer program for executing the method according to paragraph 1.
10. As a device for controlling a proximity voice input device, An input signal acquisition unit that acquires an input signal including at least one of a voice signal and a sensing signal, Input signal analysis unit that analyzes the above input signal, A mode determining unit that determines the operating mode of the proximity voice input device according to the analysis of the above input signal, and A control signal generating unit that generates a control signal for the proximity voice input device according to the operating mode determined by the mode determining unit above. Includes, The operating modes of the above proximity voice input device include a first mode, a second mode, and a third mode, and In the first mode, the microphone of the proximity voice input device is deactivated to wait for voice input, in the second mode, the microphone of the proximity voice input device is activated to perform voice recognition, and in the third mode, the microphone of the proximity voice input device is maintained in a deactivated state. device.
