Noise reduction method and device, electronic equipment, storage medium and computer program product

Abstract

The invention relates to a noise reduction method and device, electronic equipment, a storage medium and a computer program product, and the noise reduction method comprises the steps: obtaining call audio data sent by a first processor in response to the starting of a call; based on a preset voiceprint model, performing voiceprint noise reduction processing on the call audio data to obtain target audio data; and calling by using the target audio data. When the call is started, the call audio data sent by the first processor is acquired, and the voiceprint noise reduction processing is performed on the call audio data according to the preset voiceprint model, so that the call can be performed according to the target audio data subjected to the voiceprint noise reduction processing, and the noise reduction in the call process is realized. The call audio data is sent by the first processor, and the voiceprint noise reduction processing is independent of the first processor, so that the operation performance of each processor is fully utilized, the noise reduction effect and applicability are ensured, the power consumption is reduced, and the call quality and the user experience are improved.

Description

Technical Field

[0001] This disclosure relates to the field of voice calls, specifically to a noise reduction method, apparatus, electronic device, storage medium, and computer program product. Background Technology

[0002] In recent years, with the continuous development of audio processing technology and the rapid iteration of communication equipment, electronic devices with voice call functions have been widely used in people's daily lives and work. To eliminate interference from background noise and other disturbances, it is usually necessary to perform noise reduction processing on the call audio during the call to ensure good call quality.

[0003] However, noise reduction methods using related technologies suffer from problems such as poor noise reduction effect, insufficient applicability, and excessive power consumption, resulting in a poor user experience. Summary of the Invention

[0004] To overcome the problems existing in related technologies, this disclosure provides a noise reduction method, apparatus, electronic device, storage medium, and computer program product.

[0005] According to a first aspect of the present disclosure, a noise reduction method is provided, the noise reduction method comprising:

[0006] In response to initiating a call, the system acquires the call audio data sent by the first processor.

[0007] Based on a preset voiceprint model, the call audio data is subjected to voiceprint noise reduction processing to obtain target audio data.

[0008] The call is conducted using the target audio data.

[0009] In some embodiments of this disclosure, the noise reduction method further includes:

[0010] In response to the initiation of the call, a first instruction is sent to the first processor, the first instruction being used to instruct the first processor to send multi-channel audio data of the call.

[0011] In some embodiments of this disclosure, the multi-channel call audio data includes first channel data and second channel data, wherein the first channel data is the original audio data and the second channel data is the processed data after echo cancellation processing by the first processor;

[0012] The step of performing voiceprint noise reduction processing on the call audio data based on a preset voiceprint model to obtain target audio data includes:

[0013] Based on the preset voiceprint model, voiceprint noise reduction processing is performed on the multi-channel call audio data, and the target audio data for a single channel is generated based on the processed audio data.

[0014] In some embodiments of this disclosure, the noise reduction method further includes:

[0015] In response to the user's preset activation operation, a second instruction is generated, which is used to instruct the activation of the voiceprint noise reduction function;

[0016] In response to the second instruction, the voiceprint noise reduction flag is set to indicate that the voiceprint noise reduction function is enabled.

[0017] In some embodiments of this disclosure, the step of acquiring call audio data sent by the first processor in response to initiating a call includes:

[0018] In response to the start of a call and the indication of the voiceprint noise reduction flag indicating that the voiceprint noise reduction function is enabled, the call audio data sent by the first processor is acquired.

[0019] In some embodiments of this disclosure, the preset activation operation includes clicking the icon control corresponding to the voiceprint noise reduction function in the interactive interface.

[0020] In some embodiments of this disclosure, the noise reduction method further includes:

[0021] In response to starting recording, obtain the voiceprint registration audio data sent by the first processor;

[0022] Based on the voiceprint registration audio data, the preset voiceprint model is generated.

[0023] In some embodiments of this disclosure, the noise reduction method further includes:

[0024] In response to the user's preset registration operation, a third instruction is generated, which is used to instruct the voiceprint registration function to be enabled;

[0025] In response to the third instruction, the voiceprint registration flag is set to an identifier indicating that the voiceprint registration function is enabled.

[0026] In some embodiments of this disclosure, the step of obtaining the voiceprint registration audio data sent by the first processor in response to starting recording includes:

[0027] In response to the start of recording and the activation of the voiceprint registration flag indicating that the voiceprint registration function is enabled, the voiceprint registration audio data sent by the first processor is acquired.

[0028] In some embodiments of this disclosure, the preset registration operation includes clicking the icon control corresponding to the voiceprint registration function in the interactive interface.

[0029] In some embodiments of this disclosure, the noise reduction method further includes:

[0030] Detect whether the voiceprint registration audio data within a preset time interval meets the preset registration conditions;

[0031] In response to the fact that the voiceprint registration audio data does not meet the preset registration conditions, a fourth instruction is issued, which is used to instruct the display of a first prompt message in the interactive interface, and the first prompt message is used to prompt the user that the voiceprint registration has failed.

[0032] and / or,

[0033] The noise reduction method further includes:

[0034] In response to the successful generation of the preset voiceprint model, a fifth instruction is issued, which is used to instruct the display of a second prompt message in the interactive interface, and the second prompt message is used to prompt the user that the voiceprint registration was successful.

[0035] In some embodiments of this disclosure, the first processor includes an audio digital signal processor.

[0036] According to a second aspect of the present disclosure, a noise reduction method is provided, the noise reduction method comprising:

[0037] In response to initiating a call, receive raw audio data acquired by the audio data acquisition device;

[0038] Based on the original audio data, call audio data is generated;

[0039] The call audio data is sent to the second processor so that the second processor performs voiceprint noise reduction processing on the call audio data.

[0040] In some embodiments of this disclosure, generating call audio data based on the original audio data includes:

[0041] In response to a first instruction sent by the second processor, multi-channel call audio data is generated.

[0042] In some embodiments of this disclosure, the multi-channel call audio data includes first channel data and second channel data, and generating the multi-channel call audio data includes:

[0043] The original audio data is used as the data for the first channel.

[0044] The original audio data is subjected to echo cancellation processing to obtain processed data, which is then used as the second channel data.

[0045] In some embodiments of this disclosure, the noise reduction method further includes:

[0046] In response to starting recording, it receives voiceprint registration audio data acquired by the audio data collector;

[0047] The voiceprint registration audio data is sent to the second processor so that the second processor generates a preset voiceprint model based on the voiceprint registration audio data.

[0048] In some embodiments of this disclosure, the second processor includes a central processing unit.

[0049] According to a third aspect of the present disclosure, a noise reduction device is provided, the noise reduction device comprising:

[0050] The acquisition module is used to acquire call audio data sent by the first processor in response to the start of a call;

[0051] A noise reduction module is used to perform voiceprint noise reduction processing on the call audio data based on a preset voiceprint model to obtain target audio data.

[0052] A call module, which is used to conduct a call using the target audio data.

[0053] According to a fourth aspect of the present disclosure, a noise reduction device is provided, the noise reduction device comprising:

[0054] A receiving module, wherein the receiving module is used to receive raw audio data acquired by the audio data collector in response to the initiation of a call;

[0055] A first generation module is used to generate call audio data based on the original audio data;

[0056] A first sending module is configured to send the call audio data to a second processor, so that the second processor performs voiceprint noise reduction processing on the call audio data.

[0057] According to a fifth aspect of the present disclosure, an electronic device is provided, the electronic device comprising:

[0058] processor;

[0059] Memory used to store processor-executable instructions;

[0060] The processor is configured to perform the noise reduction method as described in the first or second aspect.

[0061] According to a sixth aspect of the present disclosure, a non-transitory computer-readable storage medium is provided, wherein when instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the noise reduction method as described in the first or second aspect.

[0062] According to a seventh aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the noise reduction method as described in the first or second aspect.

[0063] The technical solutions provided by the embodiments of this disclosure can include the following beneficial effects: when a call is initiated, by acquiring the call audio data sent by the first processor and performing voiceprint noise reduction processing on the call audio data according to a preset voiceprint model, the call can be conducted using the target audio data after voiceprint noise reduction processing, thus achieving noise reduction during the call process. The call audio data is sent by the first processor, and the voiceprint noise reduction processing is performed independently of the first processor, fully utilizing the computing performance of each processor, ensuring noise reduction effect and applicability, reducing power consumption, and improving call quality and user experience.

[0064] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. Attached Figure Description

[0065] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0066] Figure 1 This is a flowchart illustrating a noise reduction method according to an exemplary embodiment.

[0067] Figure 2 This is a flowchart illustrating a noise reduction method according to another exemplary embodiment.

[0068] Figure 3 This is a schematic diagram illustrating an interactive interface according to an exemplary embodiment.

[0069] Figure 4 This is a flowchart illustrating a noise reduction method according to another exemplary embodiment.

[0070] Figure 5 This is a flowchart illustrating a noise reduction method according to another exemplary embodiment.

[0071] Figure 6 This is a flowchart illustrating a noise reduction method according to another exemplary embodiment.

[0072] Figure 7 This is a schematic diagram of an interactive interface according to another exemplary embodiment.

[0073] Figure 8 This is a schematic diagram of an interactive interface according to another exemplary embodiment.

[0074] Figure 9 This is a flowchart illustrating a noise reduction method according to another exemplary embodiment.

[0075] Figure 10 This is a flowchart illustrating the generation of multi-channel call audio data according to an exemplary embodiment.

[0076] Figure 11 This is a flowchart illustrating a noise reduction method according to another exemplary embodiment.

[0077] Figure 12 This is a flowchart illustrating a noise reduction method according to another exemplary embodiment.

[0078] Figure 13 This is a flowchart illustrating a noise reduction method according to another exemplary embodiment.

[0079] Figure 14 This is a block diagram illustrating a noise reduction device according to an exemplary embodiment.

[0080] Figure 15 This is a block diagram of a noise reduction device according to another exemplary embodiment.

[0081] Figure 16 This is a block diagram of an electronic device according to an exemplary embodiment.

[0082] In the picture:

[0083] 10-Acquisition module; 20-Noise reduction module; 30-Talk module; 40-Receiving module; 50-First generation module; 60-First transmission module; 101-Processing component; 102-Memory; 103-Power component; 104-Multimedia component; 105-Audio component; 106-Input / output interface; 107-Sensor component; 108-Communication component; 109-Processor. Detailed Implementation

[0084] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0085] In recent years, with the continuous development of audio processing technology and the rapid iteration of communication equipment, electronic devices with voice call functions, such as mobile phones and laptops, have been widely used in people's daily lives and work. When users make voice calls through electronic devices, noise such as background noise can interfere with the call process. Therefore, it is usually necessary to perform noise reduction processing on the audio used in the call to ensure good call quality.

[0086] In related technologies, for example, an audio digital signal processor (ADSP) can be used to acquire audio data during the operation of the Voice over Internet Protocol (VoIP) function, and voiceprint recognition and voiceprint noise reduction technology can be used to eliminate noise in the audio data to achieve voiceprint noise reduction.

[0087] However, noise reduction methods using related technologies integrate the voiceprint noise reduction algorithm entirely within the audio digital signal processor. The computing power of the audio digital signal processor cannot meet the high performance requirements of the voiceprint noise reduction algorithm, and the noise reduction function is only applicable to the handheld call mode of electronic devices. This will lead to problems such as poor noise reduction effect, insufficient applicability, and excessive power consumption, resulting in a poor user experience.

[0088] Based on this, an exemplary embodiment of this disclosure provides a noise reduction method. When a call is initiated, the method acquires call audio data sent by a first processor and performs voiceprint noise reduction processing on the call audio data according to a preset voiceprint model. This enables the call to proceed using the target audio data after voiceprint noise reduction processing, thus achieving noise reduction during the call. The call audio data is sent by the first processor, and the voiceprint noise reduction processing is performed independently of the first processor, fully utilizing the computing power of each processor, ensuring noise reduction effectiveness and applicability, reducing power consumption, and improving call quality and user experience.

[0089] In one exemplary embodiment, a noise reduction method is provided, applied to a second processor of an electronic device. The electronic device can be, for example, a mobile phone, in-vehicle infotainment system, tablet computer, laptop computer, or other device with call functionality. The second processor can be, for example, a central processing unit (CPU). (See reference...) Figure 1 As shown, the noise reduction methods include:

[0090] S100: In response to starting a call, obtain the call audio data sent by the first processor.

[0091] In step S100, the user can initiate a VoIP call, such as a voice call, a video call including a voice call, or a conference call, through various applications included in the electronic device. When a call is initiated, the second processor obtains the call audio data sent by the first processor. For example, the first processor can be an Audio Digital Signal Processor (ADSP), and the second processor can read the call audio data sent by the first processor in the Audio Hardware Abstraction Layer (AHAL). The call audio data is the audio data during the call, and can be, for example, audio data processed by the first processor. The audio data formed by the call audio data can include human voices and noise such as background noise.

[0092] S200: Based on a preset voiceprint model, perform voiceprint noise reduction processing on the call audio data to obtain the target audio data.

[0093] In step S200, voiceprint recognition is a technology that uses the sound wave spectrum to identify individuals. Voiceprints have the characteristics of specificity and relative stability. A preset voiceprint model can be used for voiceprint recognition. For example, audio data including the voice of a specific user can be used as a sample, and a preset voiceprint model can be generated through neural network training. In subsequent use, the voice of the specific user can be identified and extracted using the preset voiceprint model.

[0094] After receiving the call audio data sent by the first processor, a preset voiceprint model can be loaded by the second processor. Voiceprint noise reduction processing is then performed on the call audio data based on the preset voiceprint model to obtain the target audio data after voiceprint noise reduction. The resulting audio data eliminates noise such as background noise. The electronic device can store multiple voiceprint models and use one as the default preset voiceprint model. When a user makes a call and voiceprint noise reduction is performed based on the preset voiceprint model, the user's voice can be manually selected or automatically identified as the preset voiceprint model to ensure that the user's voice is preserved in the resulting audio data.

[0095] For example, after acquiring the call audio data, voiceprint noise reduction initialization can be performed, the voiceprint model file corresponding to the preset voiceprint model can be loaded, and in the audio hardware abstraction layer, voiceprint noise reduction processing can be performed on each frame of call audio data through the preset voiceprint model and the corresponding voiceprint noise reduction algorithm, so as to identify and retain the audio data in the call audio data that is compatible with the preset voiceprint model, and obtain the target audio data.

[0096] It should be noted that, unlike related technologies that only acquire audio data through an audio digital signal processor and perform voiceprint noise reduction on the audio data, the noise reduction method of this application sends the call audio data through a first processor and performs voiceprint noise reduction on the hardware abstraction layer through a second processor with stronger computing performance. This can make full use of the computing performance of the second processor, improve the overall computing efficiency, and ensure the noise reduction effect and the applicability of the noise reduction method.

[0097] S300, making calls using target audio data.

[0098] In step S300, the target audio data after voiceprint noise reduction is used for the call. For example, the obtained target audio data can be passed to the upper-level application for the call, and the target audio data can be passed to other participants in the call through the network transmission function of VoIP. The target audio data is used to form the noise-reduced audio, so that other participants in the call can hear the human voice after some noise has been eliminated.

[0099] In this embodiment, when a call is initiated, the call audio data sent by the first processor is acquired, and voiceprint noise reduction processing is performed on the call audio data according to a preset voiceprint model. This allows the call to proceed using the target audio data after voiceprint noise reduction processing, thus achieving noise reduction during the call. The call audio data is sent by the first processor, and the voiceprint noise reduction processing is performed independently of the first processor, fully utilizing the computing power of each processor, ensuring noise reduction effect and applicability, reducing power consumption, and improving call quality and user experience.

[0100] In some embodiments, the noise reduction method further includes: in response to initiating a call, sending a first instruction to a first processor, the first instruction being used to instruct the first processor to send multi-channel call audio data.

[0101] In response to initiating a call, before acquiring the call audio data sent by the first processor, the second processor may also send a first instruction to the first processor. This first instruction instructs the first processor to send multi-channel call audio data, ensuring that the call audio data acquired by the second processor is multi-channel audio data. For example, when a call is initiated, the second processor sends the first instruction to the first processor to instruct the single-channel recording invoked by the VoIP call to switch to multi-channel recording and to cause the first processor to send multi-channel call audio data. This ensures that the call audio data acquired by the second processor includes audio data from at least two channels, providing sufficient data for the voiceprint noise reduction algorithm.

[0102] In this embodiment, by sending a first instruction to the first processor, the first processor can be instructed to send multi-channel call audio data, so that the call audio data obtained by the second processor is multi-channel audio data, so as to provide the voiceprint noise reduction algorithm with a sufficient amount of data, ensuring the stability and accuracy of the voiceprint noise reduction process, thereby ensuring the noise reduction effect, improving call quality and user experience.

[0103] In some embodiments, the multi-channel call audio data includes first channel data and second channel data, wherein the first channel data is the original audio data and the second channel data is the processed data after echo cancellation processing by the first processor.

[0104] The multi-channel call audio data sent by the first processor includes first channel data and second channel data. The first channel data is the raw audio data, which can be acquired by the audio data acquisition device of the electronic device and directly sent to the second processor by the first processor. The second channel data is the processed data after echo cancellation processing by the first processor. For example, the raw audio data can be acquired by the audio data acquisition device of the electronic device, and the first processor can perform echo cancellation processing on the raw audio data to obtain the processed data, which is then sent to the second processor by the first processor.

[0105] Based on a preset voiceprint model, voiceprint noise reduction processing is performed on call audio data to obtain target audio data, including: based on the preset voiceprint model, voiceprint noise reduction processing is performed on multi-channel call audio data, and single-channel target audio data is generated based on the processed audio data.

[0106] Once the second processor acquires the call audio data, which includes the first channel data and the second channel data, it can perform voiceprint noise reduction processing on the multi-channel call audio data according to the preset voiceprint model, and restore the processed audio data to the initial single-channel audio data format of the VoIP call to obtain the target audio data.

[0107] In this embodiment, the multi-channel call audio data includes raw audio data and data processed by the first processor for echo cancellation. This provides a sufficient amount of data for the voiceprint noise reduction algorithm, ensuring the stability and accuracy of the voiceprint noise reduction process, thereby guaranteeing the noise reduction effect and improving call quality and user experience. By performing voiceprint noise reduction processing on the multi-channel call audio data and generating single-channel target audio data based on the processed audio data, it is ensured that the target audio data after voiceprint noise reduction processing can be used for calls.

[0108] In some embodiments, reference Figure 2 As shown, the noise reduction method also includes:

[0109] S410, in response to the user's preset activation operation, generates a second instruction, which is used to instruct the activation of the voiceprint noise reduction function.

[0110] In step S410, when the user makes a preset activation operation, it means that the user wants to enable the voiceprint noise reduction function before or during the call. When the user's preset activation operation is detected, the second processor generates a second instruction to instruct the user to enable the voiceprint noise reduction function.

[0111] For example, in response to a user's preset activation operation, the second processor calls the system interface AudioManager.Setparameters that controls audio behavior. In the application layer, it generates a second instruction, such as "vpnr=on", through the AudioManager.Setparameters interface and sends the second instruction to the audio hardware abstraction layer to indicate that the voiceprint noise reduction function is enabled.

[0112] S420, in response to the second instruction, sets the voiceprint noise reduction flag to an identifier indicating that the voiceprint noise reduction function is enabled.

[0113] In step S420, in response to the generated second instruction, the second processor sets the voiceprint noise reduction flag to an identifier indicating that the voiceprint noise reduction function is enabled, so that it can be determined whether the voiceprint noise reduction function is enabled based on the identifier of the voiceprint noise reduction flag, thereby determining whether to acquire the call audio data sent by the first processor and perform subsequent voiceprint noise reduction processing.

[0114] For example, when the audio hardware abstraction layer receives the second instruction "vpnr=on", the second processor sets the voiceprint noise reduction flag to indicate that the voiceprint noise reduction function is enabled, thus enabling the voiceprint noise reduction function.

[0115] In this embodiment, when a user's preset activation operation is detected, a second instruction is generated. In response to the generated second instruction, the voiceprint noise reduction flag is set to indicate that the voiceprint noise reduction function is enabled. This allows subsequent determination of whether the voiceprint noise reduction function is enabled based on the flag's value. Users can enable the voiceprint noise reduction function through a preset activation operation, using target audio data processed by voiceprint noise reduction for calls. This achieves noise reduction during calls, ensuring noise reduction effectiveness and applicability, reducing power consumption, and improving call quality and user experience.

[0116] In some embodiments, in response to starting a call, acquiring call audio data sent by a first processor includes: in response to starting a call and the voiceprint noise reduction flag indicating that the voiceprint noise reduction function is enabled, acquiring call audio data sent by the first processor.

[0117] When a call is initiated, it is necessary to check whether the voiceprint noise reduction flag indicates that the voiceprint noise reduction function is enabled. If the voiceprint noise reduction flag indicates that the voiceprint noise reduction function is enabled, it means that the voiceprint noise reduction function is enabled during the call. In this case, the second processor obtains the call audio data sent by the first processor and performs subsequent voiceprint noise reduction processing. If the voiceprint noise reduction flag does not indicate that the voiceprint noise reduction function is enabled, it means that the voiceprint noise reduction function is not enabled during the call. In this case, the second processor does not obtain call audio data or perform subsequent voiceprint noise reduction processing.

[0118] For example, when a call is initiated, the second processor accesses the voiceprint noise reduction flag in the audio hardware abstraction layer. If there is an identifier indicating that the voiceprint noise reduction function is enabled, it means that the voiceprint noise reduction flag is turned on. At this time, the second processor obtains the call audio data sent by the first processor and performs voiceprint noise reduction processing on the call audio data to obtain the target audio data used for the call.

[0119] In this embodiment, when a call is initiated and the voiceprint noise reduction flag indicates that the voiceprint noise reduction function is enabled, the second processor obtains the call audio data sent by the first processor. This allows the second processor to obtain the call audio data sent by the first processor when the user enables the voiceprint noise reduction function through a preset activation operation, providing a basis for voiceprint noise reduction processing. This avoids the automatic execution of the voiceprint noise reduction process when the voiceprint noise reduction function is not enabled, and realizes the control of enabling and disabling the voiceprint noise reduction function.

[0120] In some embodiments, the preset activation operation includes clicking the icon control corresponding to the voiceprint noise reduction function in the interactive interface.

[0121] The preset activation operation for enabling the voiceprint noise reduction function may include clicking the icon control corresponding to the voiceprint noise reduction function in the interactive interface of the electronic device. For example, in... Figure 3In the interactive interface shown, the icon control corresponding to the voiceprint noise reduction function can be the button control where "Ultimate" is located. When the electronic device recognizes that the user clicks the button control corresponding to "Ultimate" in the interactive interface, it can generate a second instruction through the second processor and, in response to the second instruction, set the voiceprint noise reduction flag to an identifier indicating that the voiceprint noise reduction function is enabled.

[0122] In this embodiment, the preset activation operation includes clicking the icon control corresponding to the voiceprint noise reduction function in the interactive interface. Users can interact with the electronic device by clicking the icon control corresponding to the voiceprint noise reduction function in the interactive interface. When the electronic device recognizes that the user has clicked the icon control corresponding to the voiceprint noise reduction function in the interactive interface, it generates a second instruction through the second processor and responds to the second instruction by setting the voiceprint noise reduction flag bit to an identifier that indicates that the voiceprint noise reduction function is enabled, thereby enabling the voiceprint noise reduction function.

[0123] In some embodiments, reference Figure 4 As shown, the noise reduction method also includes:

[0124] S510, in response to starting recording, obtains the voiceprint registration audio data sent by the first processor.

[0125] In step S510, the user can register their voiceprint using the recording function of the electronic device. When recording for voiceprint registration is started, the second processor obtains the voiceprint registration audio data sent by the first processor. For example, the voiceprint registration audio data could be audio data obtained by recording the user reading a specific field aloud. The second processor can read the voiceprint registration audio data sent by the first processor in the audio hardware abstraction layer to obtain the voiceprint registration audio data.

[0126] S520: Generate a preset voiceprint model based on the registered audio data.

[0127] In step S520, a preset voiceprint model can be generated based on the voiceprint registration audio data. For example, the second processor can pass the acquired voiceprint registration audio data frame by frame to the voiceprint recording algorithm in the audio hardware abstraction layer, so that the voiceprint recording algorithm can generate a corresponding preset voiceprint model file based on the voiceprint registration audio data, and store the voiceprint model file in the electronic device. When a call is subsequently initiated, the generated preset voiceprint model can be used as a basis to perform voiceprint noise reduction processing on the call audio data.

[0128] In this embodiment, when recording is started, the voiceprint registration audio data sent by the first processor is obtained, and a preset voiceprint model is generated based on the voiceprint registration audio data. This realizes the acquisition of the preset voiceprint model. When a call is started later, the generated preset voiceprint model can be used as a basis to perform voiceprint noise reduction processing on the call audio data, thereby realizing noise reduction during the call process, ensuring the noise reduction effect and applicability, reducing power consumption, and improving call quality and user experience.

[0129] In some embodiments, reference Figure 5 As shown, the noise reduction method also includes:

[0130] S610, in response to the user's preset registration operation, generates a third instruction, which is used to instruct the voiceprint registration function to be enabled.

[0131] In step S610, when the user performs a preset registration operation, it means that the user wants to enable the voiceprint registration function and register the voiceprint. When the user's preset registration operation is recognized, the second processor generates a third instruction to instruct the user to enable the voiceprint registration function.

[0132] For example, in response to the user's preset registration operation, the second processor calls the system interface AudioManager.Setparameters that controls audio behavior, generates a third instruction such as "vpnr_enroll=on" through the AudioManager.Setparameters interface in the application layer, and sends the third instruction to the audio hardware abstraction layer to indicate that the voiceprint registration function is enabled.

[0133] S620, in response to the third instruction, sets the voiceprint registration flag to an identifier indicating that the voiceprint registration function is enabled.

[0134] In step S620, in response to the generated third instruction, the second processor sets the voiceprint registration flag to an identifier indicating that the voiceprint registration function is enabled, so that it can be determined whether the voiceprint registration function is enabled based on the identifier of the voiceprint registration flag, thereby determining whether to obtain the voiceprint registration audio data sent by the first processor and perform subsequent generation of the preset voiceprint model.

[0135] For example, when the audio hardware abstraction layer receives the third instruction "vpnr_enroll=on", the second processor sets the voiceprint registration flag to indicate that the voiceprint registration function is enabled, thus enabling the voiceprint registration function.

[0136] In this embodiment, when a user's preset registration operation is detected, a third instruction is generated. In response to the generated third instruction, the voiceprint registration flag is set to indicate that the voiceprint registration function is enabled. This allows subsequent determination of whether the voiceprint registration function is enabled based on the flag. Users can enable the voiceprint registration function through a preset registration operation. When the voiceprint registration function is enabled, the user obtains the voiceprint registration audio data sent by the first processor and generates a corresponding preset voiceprint model. This provides a basis for voiceprint noise reduction processing during subsequent calls, improving call quality and user experience.

[0137] In some embodiments, in response to starting recording, receiving voiceprint registration audio data sent by a first processor includes: in response to starting recording and the voiceprint registration flag indicating that the voiceprint registration function is enabled, obtaining the voiceprint registration audio data sent by the first processor.

[0138] When recording begins, it is necessary to check whether the voiceprint registration flag indicates that the voiceprint registration function is enabled. If the voiceprint registration flag indicates that the voiceprint registration function is enabled, it means that the voiceprint registration function has been enabled during the recording process. In this case, the second processor obtains the voiceprint registration audio data sent by the first processor and proceeds with the subsequent generation of the preset voiceprint model. If the voiceprint registration flag does not indicate that the voiceprint registration function is enabled, it means that the voiceprint registration function has not been enabled during the recording process. In this case, the second processor does not obtain the voiceprint registration audio data or proceed with the generation of the preset voiceprint model.

[0139] For example, when recording is started, the second processor accesses the voiceprint registration flag in the audio hardware abstraction layer. If there is an identifier indicating that the voiceprint registration function is enabled, it means that the voiceprint registration flag is turned on. At this time, the second processor obtains the voiceprint registration audio data sent by the first processor and generates the corresponding preset voiceprint model based on the voiceprint registration audio data.

[0140] In this embodiment, when recording is enabled and the voiceprint registration flag indicates that the voiceprint registration function is enabled, the second processor obtains the voiceprint registration audio data sent by the first processor. This allows the second processor to obtain the voiceprint registration audio data sent by the first processor when the user enables the voiceprint registration function through a preset registration operation, providing a basis for the generation of the preset voiceprint model. This avoids the automatic execution of the preset voiceprint model generation process when the voiceprint registration function is not enabled, and realizes the control of enabling and disabling the voiceprint registration function.

[0141] In some embodiments, the preset registration operation includes clicking the icon control corresponding to the voiceprint registration function in the interactive interface.

[0142] The preset registration operation for enabling the voiceprint registration function may include clicking the icon control corresponding to the voiceprint registration function in the interactive interface of the electronic device. For example, if the preset voiceprint model required for voiceprint noise reduction processing is missing when enabling the voiceprint noise reduction function, a third prompt message such as "Do you want to register your voiceprint?" can be displayed in the interactive interface of the electronic device. The third prompt message may include button controls corresponding to "OK" and "Cancel", and the button control corresponding to "OK" can be used as the icon control corresponding to the voiceprint registration function. When the electronic device recognizes that the user clicks the button control corresponding to "OK" in the interactive interface, it can generate a third instruction through the second processor and, in response to the third instruction, set the voiceprint registration flag bit to an identifier indicating that the voiceprint registration function is enabled.

[0143] In this embodiment, the preset registration operation includes clicking the icon control corresponding to the voiceprint registration function in the interactive interface. Users can interact with the electronic device by clicking the icon control corresponding to the voiceprint registration function in the interactive interface. When the electronic device recognizes that the user has clicked the icon control corresponding to the voiceprint registration function in the interactive interface, it generates a third instruction through the second processor and responds to the third instruction by setting the voiceprint registration flag bit to an identifier that indicates that the voiceprint registration function is enabled, thereby enabling the voiceprint registration function.

[0144] In some embodiments, reference Figure 6 As shown, the noise reduction method also includes:

[0145] S710: Detect whether the voiceprint registration audio data within the preset time interval meets the preset registration conditions.

[0146] In step S710, if the environment after recording is started is too noisy or the user speaks too fast, the voiceprint registration will fail. The second processor can detect whether the voiceprint registration audio data within the preset time interval meets the preset registration conditions to determine whether the voiceprint registration audio data can meet the requirements for generating the preset voiceprint model.

[0147] For example, the time corresponding to one frame of voiceprint registration audio data is, for example, 20ms. Each time, 15 frames of voiceprint registration audio data within a preset time interval of 0.3s are extracted and passed to the voiceprint recording algorithm. The voiceprint recording algorithm can return a detection result to indicate whether the voiceprint registration audio data within each time interval meets the preset registration conditions. The preset registration conditions can be, for example, that the ambient noise is lower than the noise threshold and the speech rate is within the preset speech rate range.

[0148] S720, in response to the fact that the voiceprint registration audio data does not meet the preset registration conditions, issues a fourth instruction, which is used to instruct the display of a first prompt message in the interactive interface, and the first prompt message is used to prompt the user that the voiceprint registration has failed.

[0149] In step S720, when the detection result indicates that the voiceprint registration audio data does not meet the preset registration conditions, it means that the voiceprint registration audio data cannot generate an accurate preset voiceprint model. At this time, the second processor issues a fourth instruction. The fourth instruction is used to instruct the display of a first prompt message on the interactive interface of the electronic device. The first prompt message is used to inform the user that the voiceprint registration has failed.

[0150] For example, refer to Figure 7 or Figure 8 As shown, the interactive interface can display the first prompt message "Please re-record in a quiet background" or "Speech speed too fast, please re-record" to indicate that the voiceprint registration failed and you need to restart recording to register your voiceprint again.

[0151] In this embodiment, by detecting whether the voiceprint registration audio data within a preset time interval meets the preset registration conditions, and issuing a fourth instruction when the voiceprint registration audio data does not meet the preset registration conditions, the fourth instruction can instruct the display of a first prompt message on the interactive interface to notify the user that voiceprint registration has failed. This can be used when the environment is too noisy or the user's speech is too fast, making it difficult to generate a preset voiceprint model from the voiceprint registration audio data. The user can then restart recording and attempt voiceprint registration according to the prompt, ensuring the generation of an accurate preset voiceprint model and providing a basis for subsequent voiceprint noise reduction processing.

[0152] In some embodiments, the noise reduction method further includes: in response to the successful generation of a preset voiceprint model, issuing a fifth instruction, the fifth instruction being used to instruct the display of a second prompt message in the interactive interface, the second prompt message being used to prompt the user that the voiceprint registration was successful.

[0153] When a preset voiceprint model is successfully generated based on the voiceprint registration audio data, a fifth instruction is issued through the second processor. The fifth instruction is used to instruct the display of a second prompt message in the interactive interface of the electronic device. The second prompt message is used to prompt the user that the voiceprint registration is successful. After receiving the prompt that the voiceprint registration is successful, the user can enable the voiceprint noise reduction function to perform voiceprint noise reduction processing on the call audio data through the preset voiceprint model when a call is started.

[0154] In this embodiment, when the preset voiceprint model is successfully generated, a fifth instruction is issued to indicate that the second prompt information is displayed in the interactive interface. The second prompt information can notify the user that the voiceprint registration is successful, so that the user can enable the voiceprint noise reduction function after receiving the prompt, and perform voiceprint noise reduction processing on the call audio data through the preset voiceprint model when the call is started, thereby improving the user experience.

[0155] In some embodiments, the first processor includes an audio digital signal processor.

[0156] In this embodiment, the audio digital signal processor is used as the first processor, which can send call audio data through the audio data signal processor, and make the voiceprint noise reduction processing independent of the audio digital signal processor. This fully utilizes the computing power of the audio digital signal processor and the second processor, ensuring the noise reduction effect and applicability, reducing power consumption, and improving call quality and user experience.

[0157] In one exemplary embodiment, a noise reduction method is provided, applied to a first processor of an electronic device. The electronic device may be, for example, a mobile phone, in-vehicle infotainment system, tablet computer, laptop computer, or other device with call functionality. The first processor may be, for example, an Audio Digital Signal Processor (ADSP). (See reference...) Figure 9 As shown, the noise reduction methods include:

[0158] S800, in response to initiating a call, receives raw audio data acquired by the audio data acquisition unit.

[0159] In step S800, the user can initiate a VoIP (Voice over Internet Protocol) call mode, such as a voice call, a video call including a voice call, and a conference call, through various applications included in the electronic device. When a call is initiated, the first processor receives raw audio data acquired by an audio data acquisition device. For example, the audio data acquisition device may include a microphone, and the first processor can receive the raw audio data acquired by the microphone at the hardware layer. The raw audio data is the audio data during the call, and the raw audio data has not been processed. The audio formed by the raw audio data may include human voices, echoes, and noise such as background noise.

[0160] S900 generates call audio data based on the original audio data.

[0161] In step S900, the first processor generates corresponding call audio data based on the original audio data. The call audio data is the audio data after the original audio data has been processed by the first processor.

[0162] S1000: Send call audio data to the second processor so that the second processor can perform voiceprint noise reduction processing on the call audio data.

[0163] In step S1000, the first processor sends call audio data to the second processor. After receiving the call audio data, the second processor can perform voiceprint noise reduction processing on the call audio data. For example, the second processor can read the call audio data sent by the first processor in the audio hardware abstraction layer, and perform voiceprint noise reduction processing on the call audio data according to a preset voiceprint model to obtain the target audio data after voiceprint noise reduction processing.

[0164] In this embodiment, when a call is initiated, raw audio data is received from an audio data acquisition device, and call audio data is generated based on the raw audio data. This call audio data is then sent to a second processor, enabling the second processor to perform voiceprint noise reduction processing on the call audio data. The call is then conducted using the target audio data after voiceprint noise reduction processing, thus achieving noise reduction during the call. The first processor only receives the raw audio data and generates and sends the call audio data, while the second processor performs voiceprint noise reduction processing. This fully utilizes the computing power of both the first and second processors, ensuring noise reduction effectiveness and applicability, reducing power consumption, and improving call quality and user experience.

[0165] In some embodiments, generating call audio data based on raw audio data includes: generating multi-channel call audio data in response to a first instruction sent by a second processor.

[0166] The second processor can also send a first instruction to the first processor. The first instruction is used to instruct the first processor to send multi-channel call audio data. When the first processor receives the first instruction sent by the second processor, the first processor can generate multi-channel call audio data based on the original audio data, so that the call audio data obtained by the second processor is multi-channel audio data, which can provide enough data for the voiceprint noise reduction algorithm used by the second processor for voiceprint noise reduction processing.

[0167] In this embodiment, in response to the first instruction sent by the second processor, the first processor generates multi-channel call audio data, so that the call audio data obtained by the second processor is multi-channel audio data, which can provide a sufficient amount of data for the voiceprint noise reduction algorithm used by the second processor to perform voiceprint noise reduction processing, ensuring the stability and accuracy of the voiceprint noise reduction process, thereby ensuring the noise reduction effect and improving call quality and user experience.

[0168] In some embodiments, the multi-channel call audio data includes first channel data and second channel data, as referenced. Figure 10 As shown, multi-channel call audio data is generated, including:

[0169] S910, use the raw audio data as the first channel data.

[0170] S920. Perform echo cancellation processing on the original audio data to obtain processed data, and use the processed data as the second channel data.

[0171] In steps S910 and S920, the raw audio data received by the audio data acquisition device received by the first processor is used as the first channel data, and the processed data obtained by echo cancellation processing of the raw audio data is used as the second channel data. The first channel data and the second channel data are sent to the second processor as multi-channel call audio data, so that the call audio data acquired by the second processor includes the raw audio data and the processed data.

[0172] In this embodiment, the first channel data and the second channel data are used as multi-channel call audio data. This ensures that the multi-channel call audio data sent by the first processor includes the original audio data and the data processed by the first processor after echo cancellation. This provides a sufficient amount of data for the voiceprint noise reduction algorithm used by the second processor to perform voiceprint noise reduction processing, ensuring the stability and accuracy of the voiceprint noise reduction process. This, in turn, guarantees the noise reduction effect and improves call quality and user experience.

[0173] In some embodiments, reference Figure 11 As shown, the noise reduction method also includes:

[0174] S1100: In response to starting recording, receives the voiceprint registration audio data acquired by the audio data acquisition device.

[0175] In step S1100, the user can register their voiceprint using the recording function of the electronic device. When recording for voiceprint registration is started, the first processor receives the voiceprint registration audio data acquired by the audio data acquisition device. For example, the voiceprint registration audio data can be audio data obtained by recording the user reading a specific field aloud. The audio data acquisition device can include, for example, a microphone, and the first processor can receive the voiceprint registration audio data acquired by the microphone at the hardware layer.

[0176] S1200: Send voiceprint registration audio data to the second processor so that the second processor can generate a preset voiceprint model based on the voiceprint registration audio data.

[0177] In step S1200, the first processor sends the voiceprint registration audio data to the second processor. The second processor can read the voiceprint registration audio data sent by the first processor in the audio hardware abstraction layer, and generate a preset voiceprint model based on the voiceprint registration audio data. When a call is subsequently initiated, the generated preset voiceprint model can be used as a basis to perform voiceprint noise reduction processing on the call audio data.

[0178] In this embodiment, when recording is started, the audio data of the voiceprint registration is received by the audio data acquisition device and sent to the second processor. The second processor can then generate a preset voiceprint model based on the voiceprint registration audio data, thus realizing the acquisition of the preset voiceprint model. When a call is subsequently started, the generated preset voiceprint model can be used as a basis to perform voiceprint noise reduction processing on the call audio data, thereby achieving noise reduction during the call process, ensuring the noise reduction effect and applicability, reducing power consumption, and improving call quality and user experience.

[0179] In some embodiments, the second processor includes a central processing unit.

[0180] In this embodiment, the central processing unit is used as the second processor. The first processor can send call audio data to the central processing unit, and the central processing unit can perform voiceprint noise reduction processing on the call audio data. This fully utilizes the computing power of the first processor and the central processing unit, ensuring the noise reduction effect and applicability, reducing power consumption, and improving call quality and user experience.

[0181] In one exemplary embodiment, a noise reduction method is provided, applied to a central processing unit, with reference to... Figure 12 As shown, the noise reduction methods include:

[0182] S1. In response to the user's preset registration operation, a third instruction is generated, which is used to instruct the voiceprint registration function to be enabled.

[0183] S2. In response to the third instruction, set the voiceprint registration flag to an identifier indicating that the voiceprint registration function is enabled;

[0184] S3. In response to the start of recording and the voiceprint registration flag indicating that the voiceprint registration function is enabled, obtain the voiceprint registration audio data sent by the audio digital signal processor.

[0185] S4. Generate a preset voiceprint model based on the registered audio data.

[0186] S5. In response to the user's preset activation operation, generate a second instruction, which is used to instruct the activation of the voiceprint noise reduction function.

[0187] S6. In response to the second instruction, set the voiceprint noise reduction flag to an identifier indicating that the voiceprint noise reduction function is enabled;

[0188] S7. In response to the start of a call and the voiceprint noise reduction flag indicating that the voiceprint noise reduction function is enabled, the call audio data sent by the audio digital signal processor is obtained.

[0189] S8. Based on the preset voiceprint model, perform voiceprint noise reduction processing on the call audio data to obtain the target audio data;

[0190] S9. Make a call using the target audio data.

[0191] In this embodiment, when a call is initiated, the call audio data sent by the audio digital signal processor is acquired, and voiceprint noise reduction processing is performed on the call audio data according to a preset voiceprint model. This allows the call to proceed using the target audio data after voiceprint noise reduction processing, thus achieving noise reduction during the call. The call audio data is sent by the audio digital signal processor, and the central processing unit (CPU) performs voiceprint noise reduction processing on the call audio data. This fully utilizes the computing power of the audio digital signal processor and the CPU, ensuring noise reduction effectiveness and applicability, reducing power consumption, and improving call quality and user experience.

[0192] In one exemplary embodiment, a noise reduction method is provided, applied to an audio digital signal processor, with reference to... Figure 13 As shown, the noise reduction methods include:

[0193] S11. In response to starting recording, receive the voiceprint registration audio data acquired by the audio data collector;

[0194] S12. Send the voiceprint registration audio data to the central processing unit so that the central processing unit can generate a preset voiceprint model based on the voiceprint registration audio data.

[0195] S13. In response to starting a call, receive raw audio data acquired by the audio data acquisition unit;

[0196] S14. In response to the first instruction sent by the central processing unit, the raw audio data is used as the first channel data;

[0197] S15. Perform echo cancellation on the original audio data to obtain processed data, and use the processed data as the second channel data.

[0198] S16. Send call audio data to the central processing unit so that the central processing unit can perform voiceprint noise reduction processing on the call audio data. The call audio data includes first channel data and second channel data.

[0199] In this embodiment, when a call is initiated, raw audio data is received from an audio data acquisition unit, and call audio data is generated based on this raw audio data. This call audio data is then sent to the central processing unit (CPU). The CPU performs voiceprint noise reduction processing on the call audio data, and the call is conducted using the target audio data after voiceprint noise reduction, thus achieving noise reduction during the call. The audio digital signal processor (ADSP) only receives the raw audio data and generates and sends the call audio data, while the CPU performs voiceprint noise reduction processing. This fully utilizes the computing power of both the ADSP and the CPU, ensuring noise reduction effectiveness and applicability, reducing power consumption, and improving call quality and user experience.

[0200] In one exemplary embodiment, a noise reduction device is provided, applied to a second processor, with reference to... Figure 14 As shown, the noise reduction device includes an acquisition module 10, a noise reduction module 20, and a call module 30. The acquisition module 10 is used to acquire call audio data sent by the first processor in response to the initiation of a call. The noise reduction module 20 is used to perform voiceprint noise reduction processing on the call audio data based on a preset voiceprint model to obtain target audio data. The call module 30 is used to conduct the call using the target audio data.

[0201] In this embodiment, when a call is initiated, the acquisition module 10 acquires the call audio data sent by the first processor, and the noise reduction module 20 performs voiceprint noise reduction processing on the call audio data according to a preset voiceprint model. The call module 30 can then use the target audio data after voiceprint noise reduction processing to conduct the call, thus achieving noise reduction during the call process. The call audio data is sent by the first processor, and the voiceprint noise reduction processing is performed independently of the first processor, fully utilizing the computing power of each processor, ensuring noise reduction effect and applicability, reducing power consumption, and improving call quality and user experience.

[0202] In one embodiment, the noise reduction device further includes a second transmitting module, which is configured to: in response to initiating a call, send a first instruction to a first processor, the first instruction being used to instruct the first processor to send multi-channel call audio data.

[0203] In one embodiment, the multi-channel call audio data includes first channel data and second channel data. The first channel data is the original audio data, and the second channel data is the processed data after echo cancellation processing by the first processor.

[0204] In one embodiment, the noise reduction module 20 is further configured to: perform voiceprint noise reduction processing on multi-channel call audio data based on a preset voiceprint model, and generate single-channel target audio data based on the processed audio data.

[0205] In one embodiment, the noise reduction device further includes a second generation module, which is configured to: generate a second instruction in response to a user's preset activation operation, the second instruction being used to indicate the activation of the voiceprint noise reduction function; and set the voiceprint noise reduction flag bit to an identifier representing the activation of the voiceprint noise reduction function in response to the second instruction.

[0206] In one embodiment, the acquisition module 10 is further configured to: in response to the start of a call and the identification of the voiceprint noise reduction flag indicating that the voiceprint noise reduction function is enabled, acquire the call audio data sent by the first processor.

[0207] In one embodiment, the preset activation operation includes clicking the icon control corresponding to the voiceprint noise reduction function in the interactive interface.

[0208] In one embodiment, the noise reduction device further includes a third generation module, which is used to: in response to starting recording, acquire voiceprint registration audio data sent by the first processor; and generate a preset voiceprint model based on the voiceprint registration audio data.

[0209] In one embodiment, the second generation module is further configured to: generate a third instruction in response to a user's preset registration operation, the third instruction being used to instruct the voiceprint registration function to be enabled; and set the voiceprint registration flag bit to an identifier indicating that the voiceprint registration function is enabled in response to the third instruction.

[0210] In one embodiment, the third generation module is further configured to: in response to enabling recording and the voiceprint registration flag indicating that the voiceprint registration function is enabled, acquire the voiceprint registration audio data sent by the first processor.

[0211] In one embodiment, the preset registration operation includes clicking the icon control corresponding to the voiceprint registration function in the interactive interface.

[0212] In one embodiment, the noise reduction device further includes a prompting module, which is used to: detect whether the voiceprint registration audio data within a preset time interval meets the preset registration conditions; and in response to the voiceprint registration audio data not meeting the preset registration conditions, issue a fourth instruction, which is used to instruct the display of a first prompt message in the interactive interface, the first prompt message being used to prompt the user that the voiceprint registration has failed.

[0213] In one embodiment, the prompting module is further configured to: in response to the successful generation of a preset voiceprint model, issue a fifth instruction, the fifth instruction being used to instruct the display of a second prompt message in the interactive interface, the second prompt message being used to prompt the user that the voiceprint registration was successful.

[0214] In one embodiment, the first processor includes an audio digital signal processor.

[0215] In one exemplary embodiment, a noise reduction device is provided, applied to a first processor, with reference to... Figure 15 As shown, the noise reduction device includes a receiving module 40, a first generating module 50, and a first transmitting module 60. The receiving module 40 is used to receive raw audio data acquired by an audio data acquisition unit in response to the initiation of a call. The first generating module 50 is used to generate call audio data based on the raw audio data. The first transmitting module 60 is used to send the call audio data to a second processor, so that the second processor performs voiceprint noise reduction processing on the call audio data.

[0216] In this embodiment, when a call is initiated, the receiving module 40 receives the raw audio data acquired by the audio data acquisition device, and the first generation module 50 generates call audio data based on the raw audio data. Then, the first sending module 60 sends the call audio data to the second processor, enabling the second processor to perform voiceprint noise reduction processing on the call audio data. The call is then conducted using the target audio data after voiceprint noise reduction processing, thus achieving noise reduction during the call. The first processor only receives the raw audio data and generates and sends the call audio data, while the second processor performs voiceprint noise reduction processing. This fully utilizes the computing power of both the first and second processors, ensuring noise reduction effectiveness and applicability, reducing power consumption, and improving call quality and user experience.

[0217] In one embodiment, the first generation module 50 is further configured to: generate multi-channel call audio data in response to a first instruction sent by the second processor.

[0218] In one embodiment, the first generation module 50 is further configured to: use the original audio data as the first channel data; perform echo cancellation processing on the original audio data to obtain processed data, and use the processed data as the second channel data.

[0219] In one embodiment, the noise reduction device further includes a third sending module, which is configured to: receive voiceprint registration audio data acquired by an audio data acquisition device in response to starting recording; and send the voiceprint registration audio data to a second processor so that the second processor generates a preset voiceprint model based on the voiceprint registration audio data.

[0220] In one embodiment, the second processor includes a central processing unit.

[0221] In one exemplary embodiment, an electronic device is provided, which may be, for example, a mobile phone, a vehicle-mounted system, a tablet computer, a laptop computer, or other devices with call functionality.

[0222] refer to Figure 16 As shown, the electronic device may include one or more of the following components: processing component 101, memory 102, power component 103, multimedia component 104, audio component 105, input / output (I / O) interface 106, sensor component 107, and communication component 108.

[0223] Processing component 101 typically controls the overall operation of an electronic device, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 101 may include one or more processors 109 to execute instructions to perform all or part of the steps of the methods described above. Furthermore, processing component 101 may include one or more modules to facilitate interaction between processing component 101 and other components. For example, processing component 101 may include a multimedia module to facilitate interaction between multimedia component 104 and processing component 101.

[0224] Memory 102 is configured to store various types of data to support the operation of the electronic device. Examples of such data include instructions for any application or method used to operate on the electronic device, contact data, phonebook data, messages, pictures, videos, etc. Memory 102 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0225] Power component 103 provides power to various components of the electronic device. Power component 103 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device.

[0226] Multimedia component 104 includes a screen that provides an output interface between the electronic device and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of touch or swipe actions but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 104 includes a front-facing camera and / or a rear-facing camera. When the electronic device is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0227] Audio component 105 is configured to output and / or input audio signals. For example, audio component 105 includes a microphone (MIC) configured to receive external audio signals when the electronic device is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 102 or transmitted via communication component 108. In some embodiments, audio component 105 also includes a speaker for outputting audio signals.

[0228] I / O interface 106 provides an interface between processing component 101 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0229] Sensor assembly 107 includes one or more sensors for providing state assessments of various aspects of the electronic device. For example, sensor assembly 107 can detect the on / off state of the electronic device, the relative positioning of components such as the display and keypad of the electronic device, changes in the position of the electronic device or a component of the electronic device, the presence or absence of user contact with the electronic device, the orientation or acceleration / deceleration of the electronic device, and temperature changes of the electronic device. Sensor assembly 107 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 107 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 107 may also include an accelerometer, a gyroscope, a magnetometer, a pressure sensor, or a temperature sensor.

[0230] Communication component 108 is configured to facilitate wired or wireless communication between electronic devices and other devices. Devices can access wireless networks based on communication standards, such as WiFi, 2G, or 3G, or combinations thereof. In one exemplary embodiment, communication component 108 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 108 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0231] In an exemplary embodiment, the electronic device may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the noise reduction method applied to the electronic device described above.

[0232] In one exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 102 including instructions, which can be executed by a processor 109 of an electronic device to perform the noise reduction method applied to the electronic device described above. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc. When the instructions in the storage medium are executed by the processor 109 of the electronic device, the electronic device is able to perform the noise reduction method shown in the above embodiments.

[0233] In one exemplary embodiment, a computer program product is also provided, including a computer program that, when executed by processor 109, implements the above-described noise reduction method.

[0234] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0235] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A noise reduction method, characterized in that, The noise reduction method includes: In response to initiating a call, the system acquires the call audio data sent by the first processor. Based on a preset voiceprint model, the call audio data is subjected to voiceprint noise reduction processing to obtain target audio data. The call is conducted using the target audio data.

2. The noise reduction method according to claim 1, characterized in that, The noise reduction method further includes: In response to the initiation of the call, a first instruction is sent to the first processor, the first instruction being used to instruct the first processor to send multi-channel audio data of the call.

3. The noise reduction method according to claim 2, characterized in that, The multi-channel call audio data includes first channel data and second channel data. The first channel data is the original audio data, and the second channel data is the processed data after echo cancellation processing by the first processor. The step of performing voiceprint noise reduction processing on the call audio data based on a preset voiceprint model to obtain target audio data includes: Based on the preset voiceprint model, voiceprint noise reduction processing is performed on the multi-channel call audio data, and the target audio data for a single channel is generated based on the processed audio data.

4. The noise reduction method according to claim 1, characterized in that, The noise reduction method further includes: In response to the user's preset activation operation, a second instruction is generated, which is used to instruct the activation of the voiceprint noise reduction function; In response to the second instruction, the voiceprint noise reduction flag is set to indicate that the voiceprint noise reduction function is enabled.

5. The noise reduction method according to claim 4, characterized in that, The step of responding to initiating a call by acquiring call audio data sent by the first processor includes: In response to the start of a call and the indication of the voiceprint noise reduction flag indicating that the voiceprint noise reduction function is enabled, the call audio data sent by the first processor is acquired.

6. The noise reduction method according to claim 4, characterized in that, The preset activation operation includes clicking the icon control corresponding to the voiceprint noise reduction function in the interactive interface.

7. The noise reduction method according to claim 1, characterized in that, The noise reduction method further includes: In response to starting recording, obtain the voiceprint registration audio data sent by the first processor; Based on the voiceprint registration audio data, the preset voiceprint model is generated.

8. The noise reduction method according to claim 7, characterized in that, The noise reduction method further includes: In response to the user's preset registration operation, a third instruction is generated, which is used to instruct the voiceprint registration function to be enabled; In response to the third instruction, the voiceprint registration flag is set to an identifier indicating that the voiceprint registration function is enabled.

9. The noise reduction method according to claim 8, characterized in that, The response to start recording and obtaining the voiceprint registration audio data sent by the first processor includes: In response to the start of recording and the activation of the voiceprint registration flag indicating that the voiceprint registration function is enabled, the voiceprint registration audio data sent by the first processor is acquired.

10. The noise reduction method according to claim 8, characterized in that, The preset registration operation includes clicking the icon control corresponding to the voiceprint registration function in the interactive interface.

11. The noise reduction method according to claim 7, characterized in that, The noise reduction method further includes: Detect whether the voiceprint registration audio data within a preset time interval meets the preset registration conditions; In response to the fact that the voiceprint registration audio data does not meet the preset registration conditions, a fourth instruction is issued, which is used to instruct the display of a first prompt message in the interactive interface, and the first prompt message is used to prompt the user that the voiceprint registration has failed. and / or, The noise reduction method further includes: In response to the successful generation of the preset voiceprint model, a fifth instruction is issued, which is used to instruct the display of a second prompt message in the interactive interface, and the second prompt message is used to prompt the user that the voiceprint registration was successful.

12. The noise reduction method according to any one of claims 1 to 11, characterized in that, The first processor includes an audio digital signal processor.

13. A noise reduction method, characterized in that, The noise reduction method includes: In response to initiating a call, receive raw audio data acquired by the audio data acquisition device; Based on the original audio data, call audio data is generated; The call audio data is sent to the second processor so that the second processor performs voiceprint noise reduction processing on the call audio data.

14. The noise reduction method according to claim 13, characterized in that, The process of generating call audio data based on the original audio data includes: In response to a first instruction sent by the second processor, multi-channel call audio data is generated.

15. The noise reduction method according to claim 14, characterized in that, The multi-channel call audio data includes first channel data and second channel data. Generating the multi-channel call audio data includes: The original audio data is used as the data for the first channel. The original audio data is subjected to echo cancellation processing to obtain processed data, which is then used as the second channel data.

16. The noise reduction method according to claim 13, characterized in that, The noise reduction method further includes: In response to starting recording, it receives voiceprint registration audio data acquired by the audio data collector; The voiceprint registration audio data is sent to the second processor so that the second processor generates a preset voiceprint model based on the voiceprint registration audio data.

17. The noise reduction method according to any one of claims 13 to 16, characterized in that, The second processor includes a central processing unit.

18. A noise reduction device, characterized in that, The noise reduction device includes: The acquisition module is used to acquire call audio data sent by the first processor in response to the start of a call; A noise reduction module is used to perform voiceprint noise reduction processing on the call audio data based on a preset voiceprint model to obtain target audio data. A call module, which is used to conduct a call using the target audio data.

19. A noise reduction device, characterized in that, The noise reduction device includes: A receiving module, wherein the receiving module is used to receive raw audio data acquired by the audio data collector in response to the initiation of a call; A first generation module is used to generate call audio data based on the original audio data; A first sending module is configured to send the call audio data to a second processor, so that the second processor performs voiceprint noise reduction processing on the call audio data.

20. An electronic device, characterized in that, The electronic device includes: processor; Memory used to store processor-executable instructions; The processor is configured to perform the noise reduction method as described in any one of claims 1 to 12 or 13 to 17.

21. A non-transitory computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device is able to perform the noise reduction method as described in any one of claims 1 to 12 or 13 to 17.

22. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the noise reduction method as described in any one of claims 1 to 12 or 13 to 17.

Images