WO2022151657A1

WO2022151657A1 - Noise cancellation method and apparatus, and audio device and computer-readable storage medium

Info

Publication number: WO2022151657A1
Application number: PCT/CN2021/101463
Authority: WO
Inventors: 吴泽先; 李彬; 毛盼盼
Original assignee: 闻泰科技(深圳)有限公司
Priority date: 2021-01-18
Filing date: 2021-06-22
Publication date: 2022-07-21
Also published as: CN112911441A

Abstract

The present disclosure relates to the field of audio processing. Provided are a noise cancellation method and apparatus, and an audio device and a computer-readable storage medium. The noise cancellation method comprises: when an earphone is in an active noise cancellation mode, if it is detected that a user is on a call, controlling the earphone to exit the active noise cancellation mode; acquiring sound energy of the user and ambient noise energy during a call process; and if it is determined, according to the sound energy and the ambient noise energy, that an ambient noise cancellation starting condition is met, controlling the earphone to start an ambient noise cancellation mode. By using the method, an active noise cancellation function can be automatically turned off during a call, and ambient noise cancellation is performed in an adaptive manner, such that the call quality is improved.

Description

Noise reduction method, apparatus, audio device, and computer-readable storage medium

This disclosure claims the priority of the Chinese patent application with the application number 202110065090.2 and the invention titled "Noise Reduction Method, Apparatus, Audio Equipment, and Computer-readable Storage Medium" filed with the China Patent Office on January 18, 2021, the entire contents of which are Incorporated in this disclosure by reference.

technical field

The present disclosure relates to the technical field of audio processing, and in particular, to a noise reduction method, an apparatus, an audio device, and a computer-readable storage medium.

Background technique

Many current audio devices, such as headphones, add noise reduction functions, such as Active Noise Cancellation (ANC), in order to satisfy users' immersive experience, so that users can reduce the interference of external noise during use.

However, while pursuing an immersive experience, if the user uses the headset to talk, and the headset does not automatically remove the active noise reduction function, the user will not have background noise as a reference during the call, and the volume of the sound cannot be well controlled. It will affect the surrounding people due to the loud sound, and it will also make the other party feel awkward and cause discomfort to the other party. In addition, due to the existence of environmental noise, it may interfere with the voice of the call, so that the other party of the call cannot receive high-quality voice signals, thereby reducing the quality of the call.

SUMMARY OF THE INVENTION

(1) Technical problems to be solved

In the prior art, when a user uses a headset with an active noise reduction function to make a call, the existence of environmental noise may interfere with the call sound, so that the other party of the call cannot receive high-quality voice signals, which reduces the call quality.

(2) Technical solutions

Based on this, it is necessary to provide a noise reduction method, device, audio device and computer-readable storage that can automatically turn off the active noise reduction function during a call and adaptively perform environmental noise reduction, thereby improving the quality of the call. medium.

An embodiment of the present disclosure provides a noise reduction method, which is applied to an earphone, and the method includes:

When the headset is in the active noise reduction mode, if it is detected that the user is talking, controlling the headset to exit the active noise reduction mode;

Obtain the voice energy and ambient noise energy of the user during the call;

If it is determined according to the sound energy and the ambient noise energy that the conditions for enabling ambient noise reduction are met, the earphone is controlled to enable the ambient noise reduction mode.

In one embodiment, the process of detecting that the user is talking includes:

determining that the user is a target user;

If the volume of the target user during the call is higher than a preset volume threshold, it is determined that the user is on a call.

In one embodiment, the process of determining that the user is a target user includes:

Identify the voiceprint feature of the user during the call;

matching the voiceprint feature with a preset reference voiceprint corresponding to the target user;

If the matching degree is higher than a preset matching degree threshold, it is determined that the user is the target user.

In one embodiment, the process of determining, according to the sound energy and ambient noise energy, that the conditions for enabling ambient noise reduction are met includes:

If the ratio of the user's sound energy to the environmental noise energy is greater than a preset signal-to-noise ratio threshold, it is determined that the activation environment noise reduction condition is satisfied.

An embodiment of the present disclosure provides a noise reduction device, which is applied to an earphone, and the device includes:

a first control module, configured to control the headset to exit the active noise reduction mode when it is detected that the user is talking when the headset is in the active noise reduction mode;

an acquisition module for acquiring the user's voice energy and ambient noise energy during the call;

The second control module is configured to control the earphone to activate the ambient noise reduction mode when it is determined according to the sound energy and the ambient noise energy that the conditions for enabling ambient noise reduction are satisfied.

An embodiment of the present disclosure provides an audio device, including a memory and a processor, where the memory stores a computer program, and the processor implements the steps of the noise reduction method provided by any embodiment of the present disclosure when the processor executes the computer program.

An embodiment of the present disclosure provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, implements the steps of the noise reduction method provided by any embodiment of the present disclosure.

(3) Beneficial effects

Compared with the prior art, the technical solutions provided by the embodiments of the present disclosure have the following advantages:

The noise reduction method, device, audio device, and computer-readable storage medium provided by the embodiments of the present disclosure control the headset to exit the active noise reduction mode when it is detected that the user is using the headset to talk, that is, the active noise reduction function is automatically turned off during the call, Therefore, the background noise is provided for the user as a reference, which is beneficial for the user to better control the volume, and avoid discomfort caused by the surrounding people or the other party of the call due to the loud sound. In addition, according to the acquired sound energy and ambient noise energy of the user during the call, when it is determined that the conditions for enabling ambient noise reduction are met, the headset is controlled to enable the ambient noise reduction function, that is, adaptive ambient noise reduction is realized, thereby avoiding the impact of ambient noise on the call sound. Interference, which is beneficial to improve the high-quality voice signal to the other party of the call, thereby improving the quality of the call.

Description of drawings

1 is a schematic flowchart of a noise reduction method in one embodiment;

2 is a schematic flowchart of a process of detecting that a user is talking in an embodiment;

3 is a schematic flowchart of a process of determining a user as a target user in one embodiment;

4 is a structural block diagram of a noise reduction device in one embodiment;

FIG. 5 is an internal structure diagram of an audio device in one embodiment.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present disclosure more clear, the present disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present disclosure, but not to limit the present disclosure.

In one embodiment, as shown in FIG. 1, a noise reduction method is provided. In this embodiment, the noise reduction method is mainly applied to an audio device, such as an earphone, for illustration. It can be understood that the earphone can be a wired earphone or a wireless communication earphone, such as a bluetooth earphone.

As shown in Figure 1, the noise reduction method includes the following steps:

Step S1: When the headset is in the active noise reduction mode, if it is detected that the user is talking, the headset is controlled to exit the active noise reduction mode.

Specifically, the earphone is in the active noise reduction mode, that is, the active noise reduction function of the earphone is turned on. At this time, the earphone will simulate a sound wave of the same frequency as the noise, and the anti-phase sound wave can partially or completely cancel the noise, so that the noise can be partially or completely canceled. Effectively reduce the interference of external noise and provide users with an immersive experience. For example, when a user is listening to music or watching a video, the headset is in active noise cancellation mode, thereby providing the user with a good sound experience.

It is understandable that when people speak, based on the background noise, they can clearly perceive the volume they emit, so that they can effectively control the volume of speech and emit a relatively balanced voice. When using the headset to talk, if you continue to turn on the active noise reduction function, the active noise reduction function greatly reduces the background noise, so that the user cannot clearly perceive the volume emitted by himself, and thus cannot effectively control the speaking volume. If the sound is too loud and affects the people around you, it will also bring discomfort to the caller, or the caller may not be able to hear clearly due to the low volume of the call, thereby affecting the call process and call experience. Therefore, in the embodiment of the present disclosure, it is detected whether the user is talking, and if the user is talking, the headset is controlled to exit the active noise reduction mode, that is, the active noise reduction function is turned off, the background noise is no longer reduced, and a natural noise state is presented. It enables users to clearly perceive the volume of their own voice, provides a reference for the comparison of the user's speaking volume, and then effectively controls the speaking volume, avoiding the discomfort caused to the surrounding people and the other party due to the excessively loud voice of the call, or because the voice of the call is too low As a result, the other party of the call cannot hear clearly, which in turn affects the call process and the call experience, thereby ensuring the balance of the user's call sound. If it is detected that the user is not talking, the corresponding action is not performed, that is, the headset does not exit the active noise reduction mode, and the active noise reduction function continues to be turned on.

Step S2: Acquire the sound energy of the user and the ambient noise energy of the environment where the user is located during the call.

Specifically, the user's voice during the call and the environmental noise of the environment where the user is located can be collected through an audio collection and processing device such as a microphone, and the corresponding volume levels can be obtained through analysis. Specifically, the sound wave energy corresponding to the user's voice, that is, the user's sound energy, and the sound wave energy corresponding to the ambient noise in the environment where the user is located, that is, the ambient noise energy, can be obtained through analysis.

Step S3: If it is determined according to the sound energy and the environmental noise energy that the conditions for enabling environmental noise reduction are met, control the earphone to start the environmental noise reduction mode.

Specifically, the headset activates the Environmental Noise Cancellation (ENC) mode, that is, the headset can accurately calculate the direction of the user's speech through the dual-microphone array, and remove various interfering noises in the environment while protecting the target voice in the main direction.

It is understandable that when the user is talking through the headset, there are various noises in the environment, which may interfere with the voice of the call, so that the other party of the call cannot receive high-quality voice signals, thereby reducing the quality of the call. Therefore, in the embodiment of the present disclosure, when the user talks through the headset, it is judged whether the conditions for enabling environmental noise reduction are satisfied according to the sound energy and ambient noise energy obtained in the above step S2, and if the conditions for enabling environmental noise reduction are satisfied, the headset is controlled Activate the environmental noise reduction mode to suppress or eliminate various noises in the environment, realize adaptive environmental noise reduction, improve the anti-interference of environmental noise during the call, and ensure that high-quality voice signals are provided for the caller, thereby improving call quality. . If the conditions for enabling ambient noise reduction are not met, the corresponding action is not performed, that is, the ambient noise reduction mode is not activated.

In the above noise reduction method, when it is detected that the user is using the headset to talk, the headset is controlled to exit the active noise reduction mode, that is, the active noise reduction function is automatically turned off during the call, so as to provide the user with background noise as a reference, which is conducive to better control by the user. The volume is too loud to avoid discomfort to the people around you or the other party in the call. In addition, according to the acquired sound energy and ambient noise energy of the user during the call, when it is determined that the conditions for enabling ambient noise reduction are met, the headset is controlled to enable the ambient noise reduction function, that is, adaptive ambient noise reduction is realized, thereby avoiding the impact of ambient noise on the call sound. Interference, which is beneficial to improve the high-quality voice signal to the other party of the call, thereby improving the quality of the call.

In an embodiment of the present disclosure, as shown in FIG. 2 , in step S1, the process of detecting that the user is on a call includes the following steps:

Step S11: Determine the user as the target user.

Specifically, the target user is, for example, the user to which the headset belongs, that is, it is determined that the user currently talking is the user to which the headset belongs, so as to avoid misoperation caused by false detection and improve reliability. For example, when it detects other people who are talking, control the headset to exit the active noise reduction mode, resulting in misoperation.

It is understandable that in some places with relatively small space or areas with relatively dense crowds, such as shopping malls, there are many people, and the crowd density is large, and the distance between them is relatively small. At this time, if the user is not talking, but listening to music, the headset is in active noise reduction mode. If someone is talking around the user, the headset may recognize the voice of the call and mistakenly think it is due to the small distance between them. When the user is on a call, he may exit the active noise reduction mode, causing misoperation. In fact, the user is listening to music, and exiting the active noise reduction mode at this time will greatly affect the user's experience and reduce the user's experience. Therefore, in the embodiment of the present disclosure, it is preferred to determine the user who is talking as the target user, that is, the user to which the headset belongs, so as to prevent misidentification and misoperation from affecting the user experience and experience, and improve reliability.

In other words, in step S11, it is determined that the person who is talking is the user himself, not other people.

Step S12: If the volume of the target user during the call is higher than the preset volume threshold, it is determined that the user is on a call.

Specifically, after it is determined that the user who is on the call is the target user, it is also necessary to determine whether the volume of the target user's voice during the call satisfies a certain condition, that is, to determine whether the volume of the target user during the call is higher than the preset volume threshold. If so, it is determined that the target user is talking, thereby further avoiding misidentification and misoperation, and improving reliability. If not, that is, when the target user's volume during the call is less than or equal to the preset volume threshold, it is determined that the target user is not talking, no operation is performed, and the headset continues to maintain the active noise reduction mode.

It is understandable that during a normal call, the user's speaking voice will reach a certain level, such as reaching a preset volume threshold, which is beneficial for the other party to receive the sound signal clearly. However, if the user's voice is low, the user is probably not talking. For example, the user is talking with the surrounding people in a low voice, or the user is currently listening to music through headphones and sings along with the music softly. If it is mistakenly recognized as a call sound, it will cause a misoperation, that is, the headset will exit the active noise reduction mode, which will affect the user's experience and experience. Therefore, in the embodiment of the present disclosure, after determining the target user, it is necessary to further determine whether the user's volume is higher than the preset volume threshold, and after determining that the user's volume is higher than the preset volume threshold, determine that the user is talking , at this time, the headset exits the active noise reduction mode, thereby further avoiding misidentification and misoperation, avoiding affecting the user's experience and experience, and improving reliability.

In a specific example, the preset volume threshold is, for example, a preset volume threshold, which is based on, for example, determining as accurately as possible whether the target user is on a call. In a specific embodiment, the preset volume threshold is, for example, 40 decibels, that is, when it is recognized that the volume of the target user during the call is greater than 40 decibels, it is determined that the user is talking. Otherwise, it is considered that the user is not talking, and the headset continues to maintain the active noise reduction mode.

In an embodiment of the present disclosure, as shown in FIG. 3 , in step S11, the process of determining the user as the target user includes the following steps:

Step S111: Identify the voiceprint feature of the user during the call.

Step S112: Match the voiceprint feature with a preset reference voiceprint corresponding to the target user.

Specifically, for example, the target user, that is, the reference voiceprint of the user to which the headset belongs is pre-stored in the headset, and then the user's voiceprint feature actually collected during the call is matched with the pre-stored reference voiceprint feature of the target user, It is beneficial to accurately determine whether the user is the target user, that is, whether the user belongs to the headset.

Step S113: If the matching degree is higher than the preset matching degree threshold, determine the user as the target user.

Specifically, that is, if the matching degree between the voiceprint feature of the user actually collected during the call and the pre-stored target user's reference voiceprint feature is higher than the preset matching degree threshold, the user is determined to be the target user, that is, the user to which the headset belongs. , so that the user identity can be accurately identified, the target user can be determined, and misidentification can be prevented.

In a specific embodiment, the preset matching degree threshold is, for example, a preset value, and its value is based on, for example, determining as accurately as possible whether the user who is talking is the target user. It is understandable that the preset matching degree threshold value should not be too high or too low. If the value is too high, the target user may not be recognized due to environmental disturbances, and there will be an error of abandonment; if the value is too low, it may The voices of other users who are not the target user are recognized as the target user, resulting in a false acceptance error.

In a specific embodiment, the preset matching degree threshold is, for example, 95%.

In a specific embodiment, the process of detecting whether the user is on a call includes, for example: first, identifying the calling user as a target user, not other users. For example, the voiceprint feature of the target user, that is, the reference voiceprint, is pre-recorded in the headset, and the user's voiceprint feature actually collected during the call is compared with the reference voiceprint. If the comparison result reaches a certain confidence level, If it is 95%, it is determined that the user who is talking is the target user, that is, the user to which the headset belongs, thereby effectively avoiding misrecognition and improving the recognition accuracy of the target user. Further, it is identified whether the volume of the target user is higher than a preset volume threshold, such as 40 decibels, and if so, it is determined that the user is making a call, and at this time, the headset exits the active noise reduction mode. Otherwise, it is considered that the user is not talking, and the headset continues to maintain the active noise reduction mode.

In an embodiment of the present disclosure, in step S3, determining a process that satisfies the conditions for enabling environmental noise reduction according to the sound energy and the ambient noise energy includes: if the ratio of the user's sound energy to the ambient noise energy is greater than a preset signal-to-noise ratio If the threshold is set, it is determined that the conditions for enabling ambient noise reduction are met, and the headset starts the ambient noise reduction mode. Otherwise, that is, the ratio of the user's sound energy to the ambient noise energy is less than or equal to the preset signal-to-noise ratio threshold, it is determined that the conditions for enabling ambient noise reduction are not met, and the headset does not enable the ambient noise reduction mode.

In a specific embodiment, the preset signal-to-noise ratio threshold is a preset value, which is based on, for example, determining as accurately as possible whether the earphone satisfies the ambient noise reduction condition according to the relationship between sound energy and ambient noise energy. In a specific example, the preset signal-to-noise ratio threshold is, for example, a value greater than 1, such as 1.5.

Specifically, after obtaining the user's sound energy and environmental noise energy, a signal-to-noise ratio threshold can be set according to the sound energy and environmental noise energy, expressed as: sound energy/environmental noise energy, that is, the ratio of sound energy to environmental noise energy . It is understandable that the environmental noise reduction process is self-destructive to the useful sound wave signal, so when the user's sound energy is less than or equal to the environmental noise energy, the environmental noise reduction mode is generally not turned on, otherwise the user's voice will be eliminated. In other words, the preset signal-to-noise ratio threshold is generally set to a value greater than 1, such as 1.5. That is to say, when the actual signal-to-noise ratio threshold is detected, that is, the ratio of the collected sound energy to the ambient noise energy is greater than the preset signal-to-noise ratio threshold, such as 1.5, the ambient noise reduction mode is automatically activated to reduce ambient noise. Therefore, it can provide clear and high-quality voice signals for the other party and improve the quality of the call.

Therefore, in the noise reduction method according to the embodiment of the present disclosure, when it is detected that the user is speaking by himself, the active noise reduction ANC function is automatically turned off to present a natural background noise state, so that the user can effectively control the volume; further It can automatically determine whether to activate the environmental noise reduction ENC function according to the current environmental noise, so as to provide a relatively high-quality voice signal for the caller and improve the call quality.

It should be understood that although the steps in the flowcharts of FIGS. 1-3 are shown in sequence according to the arrows, these steps are not necessarily executed in the sequence shown by the arrows. Unless explicitly stated herein, the execution of these steps is not strictly limited to the order, and these steps may be performed in other orders. Moreover, at least a part of the steps in FIGS. 1-3 may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed and completed at the same time, but may be executed at different times. These sub-steps or stages are not necessarily completed at the same time. The order of execution of the steps is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a part of sub-steps or stages of other steps.

In one embodiment, as shown in FIG. 4, a noise reduction device is provided. In this embodiment, the noise reduction device is mainly applied to an audio device, such as an earphone, for illustration. It can be understood that the earphone may be a wired earphone, or a earphone using wireless communication, such as a Bluetooth earphone.

As shown in FIG. 4 , the noise reduction device 100 includes: a first control module 110 , an acquisition module 120 and a second control module 130 .

The first control module 110 is configured to control the headset to exit the active noise reduction mode when it is detected that the user is talking when the headset is in the active noise reduction mode.

The obtaining module 120 is configured to obtain the sound energy of the user and the ambient noise energy of the environment where the user is located during the call.

Specifically, the acquisition module 120 includes, for example, an audio collection and processing device such as a microphone, which can collect the user's voice during the call and the ambient noise of the user's environment through the microphone and other audio collection and processing devices, and analyze the corresponding volume levels. Specifically, the sound wave energy corresponding to the user's voice, that is, the user's sound energy, and the sound wave energy corresponding to the ambient noise in the environment where the user is located, that is, the ambient noise energy, can be obtained through analysis.

The second control module 130 is configured to control the earphone to activate the ambient noise reduction mode when it is determined according to the sound energy and the ambient noise energy that the conditions for enabling ambient noise reduction are satisfied.

Specifically, the headset activates the environmental noise reduction mode, that is, the headset can accurately calculate the direction of the user's speech through the dual-microphone array, and remove various interfering noises in the environment while protecting the target voice in the main direction.

It is understandable that when the user is talking through the headset, there are various noises in the environment, which may interfere with the voice of the call, so that the other party of the call cannot receive high-quality voice signals, thereby reducing the quality of the call. Therefore, in the embodiment of the present disclosure, when the user talks through the headset, according to the sound energy and ambient noise energy obtained by the acquisition module 120, the second control module 130 determines whether the startup environment noise reduction condition is satisfied. Noise conditions, control the headset to start the environmental noise reduction mode, so as to suppress or eliminate various noises in the environment, realize adaptive environmental noise reduction, improve the anti-interference of environmental noise during the call, and ensure high-quality voice for the other party. signal to improve call quality. If the conditions for enabling ambient noise reduction are not met, the corresponding action is not performed, that is, the ambient noise reduction mode is not activated.

In the above noise reduction device 100, when it is detected that the user is using the headset to talk, the headset is controlled to exit the active noise reduction mode, that is, the active noise reduction function is automatically turned off during the call, so as to provide the user with background noise as a reference, which is beneficial for the user to better. Control the volume to avoid discomfort to the people around you or the caller due to the loud sound. In addition, according to the acquired sound energy and ambient noise energy of the user during the call, when it is determined that the conditions for enabling ambient noise reduction are met, the headset is controlled to enable the ambient noise reduction function, that is, adaptive ambient noise reduction is realized, thereby avoiding the impact of ambient noise on the call sound. Interference, which is beneficial to improve the high-quality voice signal to the other party of the call, thereby improving the quality of the call.

In an embodiment of the present disclosure, the first control module 110 detects a process in which the user is talking, specifically including: determining that the user is the target user, and when the target user's volume during the call is higher than a preset volume threshold, determining A user is detected on a call.

Specifically, the target user is, for example, the user to which the headset belongs, that is, it is determined that the user currently talking is the user to which the headset belongs, so as to avoid misoperation caused by false detection and improve reliability. For example, when it detects other people who are talking, control the headset to exit the active noise reduction mode, causing misoperation.

It is understandable that in some places with relatively small space or areas with relatively dense flow of people, such as shopping malls, there are many people, and the crowd density is large, and the distance between them is relatively small. At this time, if the user is not talking, but listening to music, the headset is in active noise reduction mode. If someone is talking around the user, the headset may recognize the call sound and mistakenly think it is due to the small distance between them. When the user is on a call, he may exit the active noise reduction mode, causing misoperation. In fact, the user is listening to music, and exiting the active noise reduction mode at this time will greatly affect the user's experience and reduce the user's experience. Therefore, in the embodiment of the present disclosure, it is preferred to determine the user who is talking as the target user, that is, the user to which the headset belongs, so as to prevent misidentification and misoperation from affecting the user experience and experience, and improve reliability.

Further, after it is determined that the user who is talking is the target user, it is also necessary to determine whether the volume of the target user during the call satisfies a certain condition, that is, to determine whether the volume of the target user during the call is higher than the preset volume threshold. If so, it is determined that the target user is talking, thereby further avoiding misidentification and misoperation, and improving reliability. If not, that is, when the target user's volume during the call is less than or equal to the preset volume threshold, it is determined that the target user is not talking, no operation is performed, and the headset continues to maintain the active noise reduction mode.

In an embodiment of the present disclosure, the process of determining the user as the target user by the first control module 110 specifically includes: identifying the voiceprint feature of the user during the call; comparing the voiceprint feature with a preset benchmark corresponding to the target user The voiceprint is matched; when the matching degree is higher than the preset matching degree threshold, the user is determined as the target user.

Specifically, for example, the target user, that is, the reference voiceprint of the user to which the headset belongs is pre-stored in the headset, and then the user's voiceprint feature actually collected during the call is matched with the pre-stored target user's reference voiceprint feature, It is beneficial to accurately determine whether the user is the target user, that is, whether the user belongs to the headset. If the matching degree between the voiceprint feature of the user actually collected during the call and the reference voiceprint feature of the pre-stored target user is higher than the preset matching degree threshold, the user is determined as the target user, that is, the user to which the headset belongs, so that accurate Identify user identities, determine target users, and prevent misidentification.

In a specific embodiment, the process of the first control module 110 detecting whether the user is on a call includes, for example: first, identifying the calling user as the target user, not other users. For example, the voiceprint feature of the target user, that is, the reference voiceprint, is pre-recorded in the headset, and the user's voiceprint feature actually collected during the call is compared with the reference voiceprint. If the comparison result reaches a certain level of confidence, If it is 95%, it is determined that the user who is talking is the target user, that is, the user to which the headset belongs, thereby effectively avoiding misrecognition and improving the recognition accuracy of the target user. Further, it is identified whether the volume of the target user is higher than a preset volume threshold, such as 40 decibels, and if so, it is determined that the user is making a call, and at this time, the headset exits the active noise reduction mode. Otherwise, it is considered that the user is not talking, and the headset continues to maintain the active noise reduction mode.

In an embodiment of the present disclosure, the second control module 130 determines the process of satisfying the conditions for enabling environmental noise reduction according to the sound energy and the ambient noise energy, and specifically includes: when the ratio of the user's sound energy to the ambient noise energy is greater than a preset signal When the noise ratio threshold is set, it is determined that the conditions for enabling ambient noise reduction are met, and the headset starts the ambient noise reduction mode. Otherwise, that is, the ratio of the user's sound energy to the ambient noise energy is less than or equal to the preset signal-to-noise ratio threshold, it is determined that the conditions for enabling ambient noise reduction are not met, and the headset does not enable the ambient noise reduction mode.

Specifically, after obtaining the user's sound energy and environmental noise energy, a signal-to-noise ratio threshold can be set according to the sound energy and environmental noise energy, expressed as: sound energy/environmental noise energy, that is, the ratio of sound energy to environmental noise energy . It is understandable that the environmental noise reduction process is self-destructive to the useful sound wave signal, so when the user's sound energy is less than or equal to the environmental noise energy, the environmental noise reduction mode is generally not turned on, otherwise the user's voice will be eliminated. In other words, the preset SNR threshold is generally set to a value greater than 1, such as 1.5. That is to say, when the actual signal-to-noise ratio threshold is detected, that is, the ratio of the collected sound energy to the ambient noise energy is greater than the preset signal-to-noise ratio threshold, such as 1.5, the ambient noise reduction mode is automatically activated to reduce ambient noise. Therefore, it can provide clear and high-quality voice signals for the other party and improve the quality of the call.

Therefore, the noise reduction device 100 of the embodiment of the present disclosure, when using the headset to talk, if it is detected that the user is talking, the active noise reduction ANC function is automatically turned off, showing a natural background noise state, so that the user can effectively control the volume; Further, it can automatically determine whether to activate the environmental noise reduction ENC function according to the current environmental noise, so as to provide a relatively high-quality voice signal for the other party of the call and improve the quality of the call.

For the specific definition of the noise reduction apparatus 100, reference may be made to the definition of the noise reduction method above, which will not be repeated here. Each module in the above-mentioned noise reduction device may be implemented in whole or in part by software, hardware and combinations thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

In one embodiment, an audio device is provided, and the audio device may be an earphone, and the internal structure diagram thereof may be as shown in FIG. 5 . The audio device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the audio device is used to provide computing and control capabilities. The memory of the audio device includes a non-volatile storage medium and an internal memory. The nonvolatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the execution of the operating system and computer programs in the non-volatile storage medium. The communication interface of the audio device is used for wired or wireless communication with an external terminal, and the wireless communication can be realized by WIFI, operator network, near field communication (NFC), Bluetooth or other technologies. The computer program when executed by a processor implements a noise reduction method. The display screen of the audio equipment may be a liquid crystal display screen or an electronic ink display screen, and the input device of the audio equipment may be a touch layer covered on the display screen, or a button, a trackball or a touchpad set on the casing of the audio equipment , or an external keyboard, trackpad, or mouse.

Those skilled in the art can understand that the structure shown in FIG. 5 is only a block diagram of a partial structure related to the solution of the present disclosure, and does not constitute a limitation on the audio device to which the solution of the present disclosure is applied. The specific audio device may be Include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components.

In one embodiment, the noise reduction apparatus provided by the present disclosure may be implemented in the form of a computer program, and the computer program may run on the audio device as shown in FIG. 5 . The memory of the audio device may store various program modules that constitute the noise reduction apparatus, for example, the first control module 110, the acquisition module 120, and the second control module 130 shown in FIG. 4 . The computer program constituted by each program module causes the processor to execute the steps in the noise reduction method of each embodiment of the present disclosure described in this specification.

For example, the audio device shown in FIG. 5 may execute the aforementioned step S1 through the first control module 110 in the noise reduction apparatus shown in FIG. 4 . The audio device may perform the aforementioned step S2 through the obtaining module 120 . The audio device may perform the aforementioned step S3 through the second control module 130 .

In one embodiment, an audio device is provided, comprising a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

Step S2: Acquire the sound energy and ambient noise energy of the user during the call.

In one embodiment, the processor further implements the following steps when executing the computer program:

Step S11: Determine the user as the target user.

Step S111: Identify the voiceprint feature of the user during the call.

In one embodiment, when the processor executes the computer program, the processor further implements the following steps: if the ratio of the user's sound energy to the ambient noise energy is greater than a preset signal-to-noise ratio threshold, it is determined that a condition for enabling ambient noise reduction is satisfied.

The audio device of the embodiment of the present disclosure controls the headset to exit the active noise reduction mode when it is detected that the user is using the headset to talk, that is, the active noise reduction function is automatically turned off during the call, so as to provide the user with background noise as a reference, which is beneficial to the user. It can control the volume level to avoid the discomfort caused by the surrounding people or the other party due to the loud sound. In addition, according to the acquired sound energy and ambient noise energy of the user during the call, when it is determined that the conditions for enabling ambient noise reduction are met, the headset is controlled to enable the ambient noise reduction function, that is, adaptive ambient noise reduction is realized, thereby avoiding the impact of ambient noise on the call sound. Interference, which is beneficial to improve the high-quality voice signal to the other party of the call, thereby improving the quality of the call.

In one embodiment, a computer-readable storage medium is provided on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

In one embodiment, the computer program further implements the following steps when executed by the processor:

Step S11: Determine the user as the target user.

Step S111: Identify the voiceprint feature of the user during the call.

In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: if the ratio of the user's sound energy to the ambient noise energy is greater than a preset signal-to-noise ratio threshold, it is determined that a condition for enabling ambient noise reduction is satisfied.

The computer-readable storage medium of the embodiment of the present disclosure controls the headset to exit the active noise reduction mode when it is detected that the user is using the headset to talk, that is, the active noise reduction function is automatically turned off during the call, so as to provide the user with background noise as a reference, which is beneficial to The user can better control the volume and avoid the discomfort caused by the loudness of the surrounding people or the other party in the call. In addition, according to the acquired sound energy and ambient noise energy of the user during the call, when it is determined that the conditions for enabling ambient noise reduction are met, the headset is controlled to enable the ambient noise reduction function, that is, adaptive ambient noise reduction is realized, thereby avoiding the impact of ambient noise on the call sound. Interference, which is beneficial to improve the high-quality voice signal to the other party of the call, thereby improving the quality of the call.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage In the medium, when the computer program is executed, it may include the processes of the above-mentioned method embodiments. Wherein, any reference to memory, database or other media used in the various embodiments provided by the present disclosure may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, or optical memory, and the like. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as Static Random Access Memory (SRAM) and Dynamic Random Access Memory (DRAM).

The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, all It is considered to be the range described in this specification.

The above-mentioned embodiments only represent several embodiments of the present disclosure, and the descriptions thereof are specific and detailed, but should not be construed as limiting the scope of the invention patent. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of the present disclosure, several modifications and improvements can also be made, which all belong to the protection scope of the present disclosure. Accordingly, the scope of protection of the present disclosure should be determined by the appended claims.

Industrial Applicability

The noise reduction method provided by the present disclosure enables the user to control the headset to exit the active noise reduction mode and activate the environmental noise reduction function to avoid the interference of the environmental noise on the call sound when the user uses the headset to make a call, which is beneficial to provide high-quality voice to the other party of the call. signal, improve the call quality, and has strong industrial practicability.

Claims

A noise reduction method, applied to earphones, characterized in that the method comprises:

When the headset is in the active noise reduction mode, if it is detected that the user is talking, controlling the headset to exit the active noise reduction mode;

Obtain the voice energy and ambient noise energy of the user during the call;

If it is determined according to the sound energy and the ambient noise energy that the conditions for enabling ambient noise reduction are met, the earphone is controlled to enable the ambient noise reduction mode.
The method according to claim 1, wherein the process of detecting that the user is talking includes:

determining that the user is a target user;

If the volume of the target user during the call is higher than a preset volume threshold, it is determined that the user is on a call.
The method according to claim 2, wherein the process of determining the user as a target user comprises:

Identify the voiceprint feature of the user during the call;

matching the voiceprint feature with a preset reference voiceprint corresponding to the target user;

If the matching degree is higher than a preset matching degree threshold, it is determined that the user is the target user.
The method according to claim 2, wherein the method further comprises:

detecting the volume of the target user during the call;

If the volume of the target user during the call is less than or equal to a preset volume threshold, it is determined that the target user is not talking.
The method according to claim 1, wherein the controlling the headset to activate an ambient noise reduction mode comprises:

Calculate the orientation of the user's speech through a dual-microphone array;

determining target speech and ambient noise based on the location where the user speaks;

The ambient noise is removed.
The method according to claim 1, wherein the method further comprises:

determining the sound energy and ambient noise energy;

If the sound energy and ambient noise energy do not meet the activation environment noise reduction condition, the ambient noise reduction mode is not activated.
The method according to any one of claims 1-6, characterized in that, the process of determining, according to the sound energy and ambient noise energy, that a condition for enabling ambient noise reduction is met, comprises:

If the ratio of the user's sound energy to the environmental noise energy is greater than a preset signal-to-noise ratio threshold, it is determined that the activation environment noise reduction condition is satisfied.
A noise reduction device, applied to earphones, characterized in that the device comprises:

a first control module, configured to control the headset to exit the active noise reduction mode when it is detected that the user is talking when the headset is in the active noise reduction mode;

an acquisition module for acquiring the user's voice energy and ambient noise energy during the call;

The second control module is configured to control the earphone to activate the ambient noise reduction mode when it is determined according to the sound energy and the ambient noise energy that the conditions for enabling ambient noise reduction are satisfied.
The device according to claim 8, wherein the first control module is specifically configured to: determine that the user is a target user, and the volume of the target user during the call is higher than a preset volume threshold When , it is determined that the user is on a call.
The device according to claim 9, wherein the first control module is specifically configured to:

Identify the voiceprint feature of the user during the call;

matching the voiceprint feature with a preset reference voiceprint corresponding to the target user;

When the matching degree is higher than a preset matching degree threshold, it is determined that the user is the target user.
The device according to claim 9, wherein the second control module is further configured to:

detecting the volume of the target user during the call;

If the volume of the target user during the call is less than or equal to a preset volume threshold, it is determined that the target user is not talking.
The device according to claim 8, wherein the second control module is specifically used for:

Calculate the orientation of the user's speech through a dual-microphone array;

determining target speech and ambient noise based on the location where the user speaks;

The ambient noise is removed.
The device according to claim 8, wherein the second control module is further configured to:

determining the sound energy and ambient noise energy;

If the sound energy and ambient noise energy do not satisfy the activation environment noise reduction condition, the ambient noise reduction mode is not activated.
The device according to any one of claims 8-13, wherein the second control module is specifically configured to: when the ratio of the user's sound energy to the ambient noise energy is greater than a preset signal-to-noise ratio When the ratio is greater than the threshold, it is determined that the startup environment noise reduction condition is satisfied.
An audio device, comprising a memory and a processor, wherein the memory stores a computer program, wherein the processor implements the steps of the noise reduction method according to any one of claims 1 to 7 when the processor executes the computer program .
A computer-readable storage medium on which a computer program is stored, characterized in that, when the computer program is executed by a processor, the steps of the noise reduction method according to any one of claims 1 to 7 are implemented.