Audio noise reduction method and system, wearable device and storage medium

Abstract

The invention provides an audio noise reduction method and system, wearable equipment and a storage medium, and belongs to the technical field of audio noise reduction, and the method comprises the steps: inputting environment noise into a target neural network model, and obtaining a target application scene; determining a target noise reduction mode from a plurality of standard noise reduction modes based on the target application scene, wherein the audio shielding effects corresponding to the plurality of standard noise reduction modes are different; and based on the target noise reduction mode, controlling a target device to carry out noise reduction processing on the environmental noise, wherein the target device is used for receiving the environmental noise and playing audio. According to the audio noise reduction method and system, the wearable device and the storage medium provided by the invention, the user experience can be improved.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of audio noise reduction, and more specifically, relates to an audio noise reduction method and system, a wearable device, and a storage medium. Background Art

[0002] In today's society, people are frequently disturbed by various environmental noises whether they are commuting, working, or relaxing and entertaining. During the commuting process, the roars of subways, the honks of cars, and the noises of bus engines not only affect people's experience of listening to audio content such as music and radio, but may also distract attention and affect travel safety. In the office environment, the sounds of computer fans, printer operations, and conversations among colleagues will reduce work efficiency and interfere with concentration.

[0003] With the development of technology, active noise reduction technology has emerged. Active noise reduction technology collects environmental noise through a microphone and then generates a sound wave with the opposite phase, and the two cancel each other out to achieve the purpose of noise reduction. Although the early active noise reduction technology could handle some noises, it had many defects. For example, the noise reduction algorithm was relatively single and could not be flexibly adjusted according to different noise scenarios. It was difficult to meet people's diverse needs in the face of complex and changeable noise environments.

[0004] Therefore, there is an urgent need for an intelligent and reliable noise reduction method. Summary of the Invention

[0005] The purpose of the present disclosure is to provide an audio noise reduction method and system, a wearable device, and a storage medium to improve the user experience.

[0006] In the first aspect of the embodiments of the present disclosure, an audio noise reduction method is provided, including: Inputting environmental noise into a target neural network model to obtain a target application scenario; Determining a target noise reduction mode from multiple standard noise reduction modes based on the target application scenario, and the audio shielding effects corresponding to the multiple standard noise reduction modes are different; Controlling a target device to perform noise reduction processing on environmental noise based on the target noise reduction mode, where the target device is used to receive environmental noise and play audio.

[0007] In the second aspect of the embodiments of the present disclosure, an audio noise reduction system is provided, including: A scenario determination module, configured to input environmental noise into a target neural network model to obtain a target application scenario; A noise reduction mode determination module, configured to determine a target noise reduction mode from multiple standard noise reduction modes based on the target application scenario, and the audio shielding effects corresponding to the multiple standard noise reduction modes are different; A noise reduction module, configured to control a target device to perform noise reduction processing on environmental noise based on a target noise reduction mode, where the target device is configured to receive environmental noise and play audio.

[0008] In a third aspect of the embodiments of the present disclosure, a wearable device is provided, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the above audio noise reduction method are implemented.

[0009] In a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above audio noise reduction method are implemented.

[0010] The beneficial effects of the audio noise reduction method, system, wearable device, and storage medium provided by the embodiments of the present disclosure are as follows: By inputting environmental noise into a target neural network model, the present disclosure can identify the current application scenario. According to the identified target application scenario, a noise reduction mode most suitable for the current environment is determined from multiple standard noise reduction modes, improving the noise reduction effect and thus enhancing the user experience. By identifying environmental noise and automatically adjusting the noise reduction mode, the present disclosure can ensure that users can enjoy clear and comfortable audio playback effects in various environments, enhancing the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0012] Figure 1 It is a schematic flowchart of an audio noise reduction method provided by an embodiment of the present disclosure; Figure 2 It is a structural block diagram of an audio noise reduction system provided by an embodiment of the present disclosure; Figure 3 It is a schematic block diagram of a wearable device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0013] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present disclosure. However, those skilled in the art should clearly understand that the present disclosure can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present disclosure.

[0014] To make the objectives, technical solutions, and advantages of the present disclosure clearer, the following will be described through specific embodiments in conjunction with the accompanying drawings.

[0015] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of an audio noise reduction method provided by an embodiment of the present disclosure. The method includes: S101: Input the ambient noise into the target neural network model to obtain the target application scenario.

[0016] In this embodiment, the ambient noise refers to various sound interferences existing in the surrounding environment, such as the sound of cars driving on the street, the sound of machines running in the factory, the noisy voices of people in the office, etc.

[0017] The neural network model is a mathematical model based on artificial intelligence technology. Through learning and training on a large amount of data, the neural network model can perform operations such as analyzing, classifying, and predicting the input data. In this application, the target neural network model can be a convolutional neural network. Considering that there are different types and characteristics of noise in different scenarios, for example, the noise characteristics during commuting include the announcement sound of the subway arriving at the station, the honking sound of cars, etc., while the sounds in the office are generally the sounds of typing on the keyboard, clicking the mouse, people walking, or people communicating. Therefore, the neural network model can be trained with a dataset composed of a large amount of audio and its corresponding scenarios. The target neural network model referred to in this application is the model obtained after training.

[0018] The target application scenario refers to the specific scenario where the user is currently located determined through the analysis of the input ambient noise by the neural network model, such as the commuting scenario, the office scenario, etc. Different application scenarios have different noise characteristics and user requirements.

[0019] S102: Determine the target noise reduction mode from multiple standard noise reduction modes based on the target application scenario, and the audio shielding effects corresponding to the multiple standard noise reduction modes are different.

[0020] In this embodiment, the standard noise reduction mode is a series of pre-set noise reduction processing methods. Each mode is designed for specific noise characteristics and user requirements and has different audio shielding effects, that is, different degrees or methods of suppressing ambient noise. For example, some modes may focus on reducing low-frequency noise, and some modes may pay more attention to retaining human voices, etc.

[0021] The target noise reduction mode refers to the specific noise reduction mode selected from multiple standard noise reduction modes according to the target application scenario and suitable for the current scenario, which is used to perform actual noise reduction processing on the ambient noise.

[0022] In this embodiment, the target noise reduction mode can be determined through a preset mapping table. The target noise reduction mode can be one or more. For example, when the application scenario is a commuting scenario, the corresponding noise reduction modes in the preset mapping table are the first noise reduction mode and the second noise reduction mode, then the first noise reduction mode and the second noise reduction mode are taken as the target noise reduction modes.

[0023] The differences in the audio shielding effect can be reflected in the differences in the overall noise reduction intensity or the noise reduction intensity for a certain frequency range.

[0024] S103: Control the target device to perform noise reduction processing on the environmental noise based on the target noise reduction mode. The target device is used to receive the environmental noise and play audio.

[0025] In this embodiment, the target device refers to a device that can receive environmental noise, perform noise reduction processing on it, and at the same time play audio (such as music, voice, etc.). Common ones are noise-canceling headphones and smart glasses with audio playback functions and noise reduction functions.

[0026] After determining the target noise reduction mode, the target device performs noise reduction processing on the environmental noise according to the control methods and strategies corresponding to each preset noise reduction mode.

[0027] It can be concluded from the above that by inputting the environmental noise into the target neural network model, the present disclosure can identify the current application scenario. According to the identified target application scenario, a most suitable noise reduction mode for the current environment is determined from multiple standard noise reduction modes, improving the noise reduction effect and thus enhancing the user experience. By identifying the environmental noise and automatically adjusting the noise reduction mode, the present disclosure can ensure that users can enjoy clear and comfortable audio playback effects in various environments, enhancing the user experience.

[0028] In an embodiment of the present disclosure, the target noise reduction mode includes the first noise reduction mode and the second noise reduction mode; the environmental noise includes commuting noise and broadcast noise; Controlling the target device to perform noise reduction processing on the environmental noise based on the target noise reduction mode includes: If the target application scenario is a commuting scenario, then control the target device to perform noise reduction processing on the commuting noise according to the first noise reduction mode, and control the target device to perform noise reduction processing on the broadcast noise according to the second noise reduction mode; the noise reduction intensity of the first noise reduction mode is greater than that of the second noise reduction mode.

[0029] In this embodiment, the first noise reduction mode is one of the target noise reduction modes, having a relatively strong noise reduction intensity, mainly used to process a specific type of environmental noise (i.e., commuting noise), and can largely suppress the commuting noise, providing a quieter listening environment for users.

[0030] The second noise reduction mode is also part of the target noise reduction mode, and its noise reduction intensity is less than that of the first noise reduction mode. It is mainly used to process another specific type of environmental noise (i.e., announcement noise). While reducing the noise, it will appropriately retain this type of sound so that users can receive relevant information.

[0031] Commuting noise refers to various noises generated during the commuting process, such as the driving noises of transportation vehicles like subways and buses, engine roars, and the chatter of other passengers.

[0032] Announcement noise refers to the sounds with information - transmitting functions in the commuting scenario, such as subway announcements, bus voice prompts, vehicle horn sounds, etc. Although they are also part of the environmental noise, they are important information that users need to hear.

[0033] The target application scenario is to analyze and judge information such as environmental noise through a trained neural network model to determine the specific scenario currently located. In this embodiment, the involved scenario is the commuting scenario, that is, the environment where people are during their daily commuting to and from work, traveling, etc.

[0034] The noise reduction intensity can be reflected in the amount of noise reduction. The amount of noise reduction is usually measured in decibels (dB). The amount of noise reduction is determined by comparing the sound pressure level difference of the environmental noise before and after noise reduction. For example, if the environmental noise before noise reduction is 60 dB and it is reduced to 40 dB after noise reduction, the amount of noise reduction is 20 dB. Generally speaking, the larger the amount of noise reduction, the higher the noise reduction intensity.

[0035] In this embodiment, different types of noises can be obtained by processing the environmental noise received by the target device through the first neural network model, so as to perform different noise reduction processes. Specifically, by collecting a large amount of commuting - scenario audio data, including commuting noise and announcement noise in different transportation vehicles, at different time periods, and in different environments. These data are labeled to clearly distinguish the time periods and characteristics of commuting noise and announcement noise. The neural network model obtained through the above - mentioned data training is the first neural network model.

[0036] The difference in the noise reduction intensity between the first noise reduction mode and the second noise reduction mode can be reflected in the different amounts of noise reduction. For example, the amount of noise reduction of the first noise reduction mode is 40 dB, and the amount of noise reduction of the second noise reduction mode can be 20 dB. The amount of noise reduction corresponding to the first noise reduction mode and the amount of noise reduction corresponding to the second noise reduction mode can be obtained through experiments. The logic is that it will neither make the announcement sound too harsh nor prevent users from clearly hearing the announcement information.

[0037] From the above, it can be concluded that the present disclosure can perform different noise reduction processes for different types of noises in the commuting scenario. The first noise reduction mode focuses on significantly suppressing commuting noises, such as vehicle driving noises, engine roars, etc., to provide a quieter auditory space for users. The second noise reduction mode moderately reduces announcement noises, such as subway announcements, bus voice prompts, etc., to ensure that users can clearly receive these important messages and avoid missing key stations or prompts. In this embodiment, through noise recognition and classification, and targeted noise reduction mode selection, the auditory experience of users during commuting is improved.

[0038] In an embodiment of the present disclosure, the target noise reduction mode includes a third noise reduction mode and a fourth noise reduction mode; Based on the target noise reduction mode to control the target device to perform noise reduction processing on environmental noise, it further includes: In response to the target device not receiving the first information and the second information, perform noise reduction processing on environmental noise according to the third noise reduction mode; In response to the target device receiving the first information, perform noise reduction processing on environmental noise according to the fourth noise reduction mode; The noise reduction intensity of the third noise reduction mode is greater than that of the fourth noise reduction mode; The first information includes a preset keyword, and the second information is the voice information of the person using the target device.

[0039] In this embodiment, the application scenario can be an office scenario, a commuting scenario, or other general scenarios. Preferably, this embodiment is applied to the office scenario. That is, as can be seen from S101 and S102, the target scenario is determined by the target neural network model, and the target noise reduction mode is obtained from a preset mapping table. Therefore, the third noise reduction mode and the fourth noise reduction mode include the application scenario, and it can be defined that the application scenarios corresponding to the third noise reduction mode and the fourth noise reduction mode are both office scenarios, or the application scenarios of the third noise reduction mode and the fourth noise reduction mode include the office scenario.

[0040] Both the third noise reduction mode and the fourth noise reduction mode are a kind of target noise reduction mode. The difference is that the noise reduction intensity of the third noise reduction mode is greater than that of the fourth noise reduction mode.

[0041] The first information includes a preset keyword, which refers to the keyword preset by the person using or wearing the target device. For example, it can be the user's name, common words for starting conversations in social situations such as "Hello", "Excuse me", etc. The second information refers to the voice information of the person using the target device.

[0042] When the target device does not receive the first information and does not receive the second information, the environmental noise can be noise-reduced according to a stronger noise reduction intensity to ensure a relatively quiet office environment. When the target device receives the first information, that is, receives a conversation invitation sent by other personnel or devices (i.e., a scenario where the user needs to have a conversation with others or devices), at this time, the target device can be controlled to perform noise reduction processing on the environmental noise according to the fourth noise reduction mode. The noise reduction intensity of the fourth noise reduction mode is less than that of the third noise reduction mode, ensuring that the user can receive external information and facilitating the judgment of whether it is indeed necessary for the user to conduct a conversation or whether it is a misactivation. The noise reduction intensity corresponding to the third noise reduction mode and the noise reduction intensity corresponding to the fourth noise reduction mode can be preset according to experiments. The logic is to ensure that quiet work can be carried out in the third noise reduction mode and the voice information during normal communication can be heard in the fourth noise reduction mode.

[0043] From the above, it can be concluded that the present disclosure can select a noise reduction mode according to whether the target device receives a preset keyword or the voice information of the person using the target device, making the noise reduction processing more in line with the actual needs of users and improving the convenience and flexibility of the present disclosure. In an office scenario, in this embodiment, a high-intensity noise reduction effect is provided through the third noise reduction mode, effectively shielding the noise interference inside and outside the office and creating a more focused and quiet working environment for users, enhancing the user experience. In this embodiment, when the target device receives the first information, it means that there may be a conversation invitation initiated by others or devices. At this time, it automatically switches to the fourth noise reduction mode to reduce the noise reduction intensity, ensuring that the user can clearly hear the conversation content outside, facilitating timely response and communication, not only ensuring that the user can smoothly access the conversation when needed but also avoiding missing important information due to excessive noise reduction, enhancing the user experience.

[0044] In an embodiment of the present disclosure, the audio noise reduction method further includes: In response to the target device not receiving the second information within the first time period after receiving the first information, adjusting the fourth noise reduction mode to the third noise reduction mode and controlling the target device to perform noise reduction processing on the environmental noise; In response to the target device receiving the second information within the first time period after receiving the first information, controlling the target device to perform noise reduction processing on the environmental noise based on the transparent noise reduction mode; The audio shielding effects of the transparent noise reduction mode and the third noise reduction mode are different.

[0045] The target noise reduction mode further includes: the transparent noise reduction mode.

[0046] In this embodiment, continuing the foregoing dialogue scenario, if the target device does not receive the second information within the first time period after receiving the first information, it means that this dialogue invitation does not require the user to reply verbally and can be answered by body movements such as nodding or gestures, or it may be a mis-trigger of the target device. At this time, after the first time period, the fourth noise reduction mode can be adjusted back to the third noise reduction mode, and the target device can be controlled to perform noise reduction processing on environmental noise according to the third noise reduction mode. The first time period can be preset according to experience, for example, it can be 4 seconds, and the user can also adjust it according to needs.

[0047] Another situation is that the target device receives the second information within the first time period after receiving the first information, that is, the user needs to reply verbally. At this time, the target device can be controlled to perform noise reduction processing on environmental noise according to the transparent noise reduction mode.

[0048] The characteristic of the transparent noise reduction mode is that it allows the external environmental sounds to be transmitted into the user's ears more naturally, while performing a certain degree of processing and optimization on the environmental noise, rather than strongly shielding the environmental noise like the third noise reduction mode. In this mode, the user can clearly hear the surrounding sounds, including the voices of others and warning sounds in the environment, while reducing some unnecessary background noise interference, facilitating the user to interact and communicate with the surrounding environment.

[0049] The audio shielding effects of the transparent noise reduction mode and the third noise reduction mode are different, which is reflected in different noise reduction intensities for different frequency ranges.

[0050] From the above, it can be concluded that the present disclosure can adjust the noise reduction mode according to the timing logic of the target device receiving information, improving the interaction experience between the user and the device, making the noise reduction processing more in line with the actual needs of the user, and enhancing the convenience and flexibility of use. In this embodiment, when the user does not need to reply verbally, it automatically switches back to the third noise reduction mode with high-intensity noise reduction to ensure that the user can continue to work in a quiet environment; while when the user needs to reply verbally, it switches to the transparent noise reduction mode, enabling the user to clearly hear the surrounding environmental sounds, facilitating smooth communication with the dialogue partner, and improving the user experience.

[0051] In an embodiment of the present disclosure, the target device includes a left noise reduction device and a right noise reduction device; Controlling the target device to perform noise reduction processing on environmental noise based on the transparent noise reduction mode includes: Determining the sound source area of the first information based on the target device; In response to the sound source area being the left channel area, controlling the left noise reduction device to perform noise reduction processing on environmental noise based on the transparent noise reduction mode, and controlling the right noise reduction device to perform noise reduction processing on environmental noise based on the fifth noise reduction mode; In response to the sound source area being the right channel area, control the right noise reduction device to perform noise reduction processing on environmental noise based on the transparent noise reduction mode, and control the left noise reduction device to perform noise reduction processing on environmental noise based on the fifth noise reduction mode; In response to the sound source area being the middle area, control the left and right noise reduction devices to perform noise reduction processing on environmental noise based on the transparent noise reduction mode; The audio shielding effects of the fifth noise reduction mode and the transparent noise reduction mode are different.

[0052] In this embodiment, the target device may be a noise-canceling headphone, the left noise reduction device may be the left earphone, and the right noise reduction device may be the right earphone. The sound source area refers to the position area in space where the sound source of the first information is emitted, and is divided into a left channel area, a right channel area, and a middle area. By judging the sound source position, the target device can more specifically adjust the noise reduction modes of the left and right noise reduction devices.

[0053] In this embodiment, it is possible to determine whether it is the left channel area, the right channel area, or the middle area based on the microphone array technology or based on the sound intensity difference. Taking the microphone array technology as an example, multiple microphones are set on the target device (such as headphones), usually with at least one microphone near each of the left and right ears. When the sound source emits sound, due to the different distances, the sound will reach each microphone at different times. For example, when the sound source is in the left channel area, the microphone near the left ear will receive the sound earlier than the microphone near the right ear. By calculating the time difference of the sound reaching different microphones, the approximate direction of the sound source can be determined, and then the sound source area can be judged. The area of the first information can be determined according to the time difference and multiple thresholds.

[0054] Specifically, calculate the time difference t between the sound received by the left ear microphone and the right ear microphone. Multiple time difference thresholds are preset, which can be determined based on a large number of experiments and actual application scenarios. For example, set thresholds t1 and t2 to divide different area ranges.

[0055] If t ≤ t1, it means that the sound reaches the left ear microphone first and the time difference is small, and it can be judged that the sound source is located in the left channel area.

[0056] If t1 < t < t2, it indicates that the time difference of the sound reaching the left and right ear microphones is in the middle range, and it can be judged that the sound source is located in the middle area.

[0057] If t ≥ t2, it means that the sound reaches the right ear microphone first and the time difference is large, and it can be judged that the sound source is located in the right channel area.

[0058] After determining the sound source area of the first piece of information, if the sound source area is not the middle area, the device close to the sound source area can be adjusted to the transparent noise reduction mode, and the device on the other side can be adjusted to the fifth noise reduction mode. Adjusting the device close to the sound source area to the transparent noise reduction mode allows the user to clearly capture the sound source of the first piece of information, such as the voice of others, on that side of the ear, ensuring smooth communication. The fifth noise reduction mode can effectively process the environmental noise on the side away from the sound source, reducing other unnecessary noise interference in the surrounding environment, so that when the user focuses on communicating with the person in the sound source direction, they will not be distracted by the noisy sounds from other directions.

[0059] When the sound source area of the first piece of information is the middle area, the transparent noise reduction mode controls the left and right noise reduction devices to perform noise reduction processing on the environmental noise, indicating that the position of the sender of the first piece of information (i.e., the initiator of the conversation invitation) is in a certain area in front or a certain area behind the user at this time. At this time, both noise reduction devices are adjusted to the transparent noise reduction mode to improve the user experience.

[0060] The target noise reduction mode includes the fifth noise reduction mode, which is another noise reduction mode with a different audio shielding effect from the transparent noise reduction mode. The noise reduction intensity of the fifth noise reduction mode is set according to the environmental noise intensity received by the device that enables this noise reduction mode.

[0061] For example, before controlling the right noise reduction device to perform noise reduction processing on the environmental noise based on the fifth noise reduction mode, it further includes: Determining the noise reduction intensity of the fifth noise reduction mode based on the environmental noise intensity received by the right noise reduction device; Before controlling the left noise reduction device to perform noise reduction processing on the environmental noise based on the fifth noise reduction mode, it further includes: Determining the noise reduction intensity of the fifth noise reduction mode based on the environmental noise intensity received by the left noise reduction device.

[0062] In this embodiment, the noise reduction intensity of the fifth noise reduction mode can be determined by the first formula, and the first formula can be: , where is the noise reduction intensity of the left (right) noise reduction device in the fifth noise reduction mode, with the unit of decibel. is the environmental noise intensity received by the left (right) noise reduction device, with the unit of decibel. is the reference noise intensity, which can be the noise intensity in a common quiet environment, with the unit of decibel. is the proportionality coefficient, and its value range is , which is used to adjust the sensitivity of the noise reduction intensity to changes in the environmental noise, is the maximum noise reduction intensity that the device can provide, which depends on the hardware performance of the device. It is the minimum noise reduction intensity of the device in the fifth noise reduction mode, and a base value can be set according to actual requirements. It is a preset maximum noise intensity threshold. When the ambient noise intensity reaches or exceeds this threshold, the device will perform noise reduction with the maximum noise reduction intensity.

[0063] The formula logic is: when At this time, the ambient noise intensity is relatively low, below the reference noise intensity, indicating that the environment is relatively quiet. The device only needs to turn on the minimum noise reduction intensity That's it, to avoid excessive noise reduction from affecting the user's perception of the surrounding environment. When , the ambient noise intensity is between the reference noise intensity and the maximum noise intensity threshold, and the noise reduction intensity will increase linearly with the increase of the ambient noise intensity , and the proportionality coefficient determines the speed of increase of the noise reduction intensity. The larger the value, the faster the noise reduction intensity increases with the increase of the noise intensity. When At this time, the ambient noise intensity reaches or exceeds the maximum noise intensity threshold, and the device will perform noise reduction with the maximum noise reduction intensity to minimize the impact of ambient noise on the user.

[0064] It can be concluded from the above that the present disclosure can intelligently adjust the noise reduction modes of the left and right noise reduction devices according to the sound source area, enabling the user to clearly perceive the direction and position of the sound source while maintaining a certain noise reduction effect, making the noise reduction process more in line with the actual needs of the user, and enhancing the convenience and comfort of use.

[0065] In a conversation scenario, when the user needs to communicate with others, the present disclosure can adjust the noise reduction device near the sound source area to the transparent noise reduction mode, enabling the user to clearly hear the other party's voice while reducing other unnecessary noise interference in the surrounding environment, enabling the user to focus more on the communication with the other party and reducing the interference of external noise.

[0066] In an embodiment of the present disclosure, the audio noise reduction method further includes: In response to the noise reduction modes of the left noise reduction device and / or the right noise reduction device being the transparent noise reduction mode, and no first information and second information being received within the second time period, controlling the left noise reduction device and the right noise reduction device to perform noise reduction processing on the ambient noise based on the third noise reduction mode.

[0067] In this embodiment, when the noise reduction mode of the left noise reduction device and / or the right noise reduction device is the transparent noise reduction mode, it proves that the user is in a conversation state at this time. When the first information and the second information are not received during the second time period, it indicates that the user has ended the conversation at this time. At this time, the left noise reduction device and the right noise reduction device should be restored to the third noise reduction mode, and the target device (i.e., the left noise reduction device and the right noise reduction device) should be controlled according to the third noise reduction mode to perform noise reduction processing on environmental noise.

[0068] In an embodiment of the present disclosure, the audio noise reduction method further includes: In response to the target device being in a call state, before the call state ends, control the target device to perform noise reduction processing on environmental noise according to the third noise reduction mode.

[0069] In this embodiment, whether the target device is in a call state can be judged by the states of the microphone and the speaker. During a call, the microphone will be in a state of continuously collecting sound, and the speaker will be in a state of playing sound. It is possible to infer whether the device is in a call state by detecting the working states of the microphone and the speaker.

[0070] Considering that during a call, clear voice communication is the primary goal. The third noise reduction mode has a relatively high noise reduction intensity, which can suppress surrounding environmental noises, such as wind noise, keyboard tapping sounds, crowd noises, etc., to the greatest extent. Enabling this mode during a call can reduce the interference of these noises on the call voice, making the voice heard by the other party clearer and purer, improving the call quality, and avoiding the reduction of call quality caused by unclear transmission of important information due to environmental noise or the conversion of the headphone state caused by someone calling one's name at this time.

[0071] From the above, it can be concluded that when the target device is in a call state, the present disclosure can intelligently perform high-intensity noise reduction processing on environmental noise according to the third noise reduction mode, reducing the interference of environmental noise on the call voice, enabling both parties in the call to clearly hear the voice of the other party, thereby improving the call quality. After the call ends or the user ends the conversation, the present disclosure can switch the noise reduction mode from the transparent noise reduction mode back to the third noise reduction mode, which not only improves the convenience of the user but also enables the user to enjoy the most suitable noise reduction effect in different usage scenarios, thus optimizing the overall user experience.

[0072] Corresponding to the audio noise reduction method in the above embodiment, Figure 2 is a structural block diagram of an audio noise reduction system provided by an embodiment of the present disclosure. For the sake of convenience of description, only the parts related to the embodiments of the present disclosure are shown. Refer to Figure 2 and the audio noise reduction system 20 includes: a scene determination module 21, a noise reduction mode determination module 22, and a noise reduction module 23.

[0073] Among them, the scenario determination module 21 is configured to input environmental noise into the target neural network model to obtain the target application scenario; The noise reduction mode determination module 22 is configured to determine the target noise reduction mode from multiple standard noise reduction modes based on the target application scenario, and the audio shielding effects corresponding to the multiple standard noise reduction modes are different; The noise reduction module 23 is configured to control the target device to perform noise reduction processing on environmental noise based on the target noise reduction mode, and the target device is used to receive environmental noise and play audio.

[0074] In an embodiment of the present disclosure, the target noise reduction mode includes a first noise reduction mode and a second noise reduction mode; the environmental noise includes commuting noise and broadcast noise; The noise reduction module 23 is specifically configured to, if the target application scenario is a commuting scenario, control the target device to perform noise reduction processing on commuting noise according to the first noise reduction mode, and control the target device to perform noise reduction processing on broadcast noise according to the second noise reduction mode; the noise reduction intensity of the first noise reduction mode is greater than that of the second noise reduction mode.

[0075] In an embodiment of the present disclosure, the target noise reduction mode includes a third noise reduction mode and a fourth noise reduction mode; The noise reduction module 23 is specifically further configured to, in response to the target device not receiving the first information and the second information, perform noise reduction processing on environmental noise according to the third noise reduction mode; In response to the target device receiving the first information, perform noise reduction processing on environmental noise according to the fourth noise reduction mode; The noise reduction intensity of the third noise reduction mode is greater than that of the fourth noise reduction mode; The first information includes a preset keyword, and the second information is the voice information of the person using the target device.

[0076] In an embodiment of the present disclosure, the audio noise reduction system 20 further includes: a dialogue noise reduction module, configured to, in response to the target device not receiving the second information within the first time period after receiving the first information, adjust the fourth noise reduction mode to the third noise reduction mode, and control the target device to perform noise reduction processing on environmental noise; In response to the target device receiving the second information within the first time period after receiving the first information, control the target device to perform noise reduction processing on environmental noise based on the transparent noise reduction mode; The transparent noise reduction mode and the third noise reduction mode have different audio shielding effects.

[0077] In an embodiment of the present disclosure, the target device includes a left noise reduction device and a right noise reduction device; The dialogue noise reduction module is further configured to determine the sound source area of the first information based on the target device; In response to the sound source area being the left channel area, control the left noise reduction device to perform noise reduction processing on environmental noise based on the transparent noise reduction mode, and control the right noise reduction device to perform noise reduction processing on environmental noise based on the fifth noise reduction mode; In response to the sound source area being the right channel area, control the right noise reduction device to perform noise reduction processing on environmental noise based on the transparent noise reduction mode, and control the left noise reduction device to perform noise reduction processing on environmental noise based on the fifth noise reduction mode; In response to the sound source area being the middle area, control the left noise reduction device and the right noise reduction device to perform noise reduction processing on environmental noise based on the transparent noise reduction mode; The audio shielding effects of the fifth noise reduction mode and the transparent noise reduction mode are different.

[0078] In an embodiment of the present disclosure, the audio noise reduction system 20 further includes: a noise reduction intensity determination module, configured to determine the noise reduction intensity of the fifth noise reduction mode based on the environmental noise intensity received by the right noise reduction device; Determine the noise reduction intensity of the fifth noise reduction mode based on the environmental noise intensity received by the left noise reduction device.

[0079] In an embodiment of the present disclosure, the audio noise reduction system 20 further includes: a call noise reduction module, configured to, in response to the target device being in a call state, before the call state ends, control the target device to perform noise reduction processing on environmental noise according to the third noise reduction mode.

[0080] See Figure 3 , Figure 3 is a schematic block diagram of a wearable device provided by an embodiment of the present disclosure. As Figure 3 shown, the wearable device 300 in this embodiment may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The above-mentioned processors 301, input devices 302, output devices 303, and memories 304 complete communication with each other through a communication bus 305. The memory 304 is used to store computer programs, and the computer programs include program instructions. The processor 301 is configured to execute the program instructions stored in the memory 304. Among them, the processor 301 is configured to call the program instructions to execute the functions of each module / unit in the above system embodiments, such as Figure 2 the functions of the modules 21 to 23 shown.

[0081] It should be understood that in the embodiments of the present disclosure, the so-called processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0082] The input device 302 may include a touchpad, a fingerprint acquisition sensor (for acquiring the fingerprint information and the direction information of the fingerprint of the user), a microphone, etc., and the output device 303 may include a display (such as an LCD), a speaker, etc.

[0083] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A part of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0084] In a specific implementation, the processor 301, the input device 302, and the output device 303 described in the embodiments of the present disclosure may execute the implementation manners described in the first embodiment and the second embodiment of the audio noise reduction method provided by the embodiments of the present disclosure, and may also execute the implementation manner of the wearable device described in the embodiments of the present disclosure, which will not be elaborated herein.

[0085] In another embodiment of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a processor, all or part of the processes in the methods of the above embodiments are implemented. It can also be completed by instructing relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0086] The computer-readable storage medium can be the internal storage unit of the wearable device in any of the foregoing embodiments, such as the hard disk or memory of the wearable device. The computer-readable storage medium can also be an external storage device of the wearable device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the wearable device. Further, the computer-readable storage medium can also include both the internal storage unit and the external storage device of the wearable device. The computer-readable storage medium is used to store the computer program and other programs and data required by the wearable device. The computer-readable storage medium can also be used to temporarily store the data that has been output or will be output.

[0087] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.

[0088] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the wearable device and the unit described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0089] In several embodiments provided by the present application, it should be understood that the disclosed wearable devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling or direct coupling or communication connection between each other can be an indirect coupling or communication connection through some interfaces or units, or can also be an electrical, mechanical or other form of connection.

[0090] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present disclosure.

[0091] In addition, each functional unit in various embodiments of the present disclosure can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0092] The above is only the specific implementation manner of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present disclosure can easily think of various equivalent modifications or replacements, and these modifications or replacements should be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. An audio noise reduction method, characterized in that: include: Input the environmental noise into the target neural network model to obtain the target application scenario; Determining a target noise reduction mode from a plurality of standard noise reduction modes based on the target application scenario, the plurality of standard noise reduction modes corresponding to different audio shielding effects; The target device is controlled to perform noise reduction processing on the environmental noise based on the target noise reduction mode, and the target device is used to receive the environmental noise and play audio.

2. The audio noise reduction method according to claim 1, characterized in that: The target noise reduction mode includes a first noise reduction mode and a second noise reduction mode; the environmental noise includes commuting noise and broadcasting noise; The controlling the target device to perform noise reduction processing on the ambient noise based on the target noise reduction mode includes: If the target application scenario is a commuting scenario, the target device is controlled to perform noise reduction processing on commuting noise according to the first noise reduction mode, and the target device is controlled to perform noise reduction processing on broadcasting noise according to the second noise reduction mode; The noise reduction strength of the first noise reduction mode is greater than the noise reduction strength of the second noise reduction mode.

3. The audio noise reduction method according to claim 1, wherein: The target noise reduction mode includes a third noise reduction mode and a fourth noise reduction mode; The controlling the target device to perform noise reduction processing on the ambient noise based on the target noise reduction mode also includes: In response to the target device not receiving the first information and the second information, performing noise reduction processing on the environmental noise according to a third noise reduction mode; In response to the target device receiving the first information, performing noise reduction processing on the environmental noise according to a fourth noise reduction mode; The noise reduction intensity of the third noise reduction mode is greater than the noise reduction intensity of the fourth noise reduction mode; The first information includes preset keywords, and the second information is voice information of a person using the target device.

4. The audio noise reduction method according to claim 3, characterized in that: Also includes: In response to the target device not receiving the second information within a first period of time after receiving the first information, adjusting the fourth noise reduction mode to the third noise reduction mode, and controlling the target device to perform noise reduction processing on the ambient noise; In response to the target device receiving the second information within a first period of time after receiving the first information, controlling the target device to perform noise reduction processing on the ambient noise based on the transparent noise reduction mode; The audio shielding effect of the transparent noise reduction mode is different from that of the third noise reduction mode.

5. The audio noise reduction method according to claim 4, characterized in that: The target device includes a left noise reduction device and a right noise reduction device; The controlling the ambient noise of the target device to perform noise reduction processing based on the transparent noise reduction mode includes: determining a sound source area of ​​the first information based on the target device; In response to the sound source area being the left channel area, controlling the left noise reduction device to perform noise reduction processing on the ambient noise based on the transparent noise reduction mode, and controlling the right noise reduction device to perform noise reduction processing on the ambient noise based on the fifth noise reduction mode; In response to the sound source area being the right channel area, controlling the right noise reduction device to perform noise reduction processing on the ambient noise based on the transparent noise reduction mode, and controlling the left noise reduction device to perform noise reduction processing on the ambient noise based on the fifth noise reduction mode; In response to the sound source area being the middle area, controlling the left noise reduction device and the right noise reduction device to perform noise reduction processing on the ambient noise based on the transparent noise reduction mode; The fifth noise reduction mode has a different audio shielding effect from the transparent noise reduction mode.

6. The audio noise reduction method according to claim 5, characterized in that: Before controlling the right noise reduction device to perform noise reduction processing on the ambient noise based on the fifth noise reduction mode, the method further includes: Determining the noise reduction intensity of the fifth noise reduction mode based on the intensity of the ambient noise received by the right noise reduction device; Before controlling the left noise reduction device to perform noise reduction processing on the ambient noise based on the fifth noise reduction mode, the method further includes: The noise reduction intensity of the fifth noise reduction mode is determined based on the intensity of the ambient noise received by the left noise reduction device.

7. The audio noise reduction method according to claim 3, characterized in that: Also includes: In response to the target device being in a call state, before the call state ends, the target device is controlled to perform noise reduction processing on the environmental noise according to the third noise reduction mode.

8. An audio noise reduction system, characterized in that: include: A scene determination module is used to input the environmental noise into the target neural network model to obtain the target application scene; A noise reduction mode determination module, configured to determine a target noise reduction mode from a plurality of standard noise reduction modes based on the target application scenario, wherein the plurality of standard noise reduction modes correspond to different audio shielding effects; The noise reduction module is used to control the target device to perform noise reduction processing on the environmental noise based on the target noise reduction mode, and the target device is used to receive the environmental noise and play audio.

9. A wearable device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images