Mobile phone accessory, method and storage medium for noise reduction and sound pickup

Abstract

The present application relates to audio processing technology, and discloses a mobile phone accessory, method and storage medium for noise reduction and sound pickup, including: a first microphone, a second microphone and an accessory body; an audio processing module and a communication connection module are integrated in the accessory body, and the communication connection module is electrically connected to a plug provided on the accessory body; when the plug is inserted into the mobile phone connection port, the mobile phone accessory obtains power from the mobile phone, the first microphone is used to collect environmental sounds, the second microphone is used to pick up user voices, the audio processing module performs noise reduction processing on user voices based on environmental sounds, and the communication connection module is used to transmit the user voices after noise reduction processing to the mobile phone. The present application aims to achieve that even if the mobile phone is in a strong noise environment, the environmental noise and the user voice can still be clearly distinguished, so as to suppress the noise part, thereby improving the quality of mobile phone calls.

Description

Technical Field

[0001] The present application relates to the technical field of audio processing, and in particular to a mobile phone accessory for noise reduction and sound pickup, a noise reduction and sound pickup method based on the mobile phone accessory, and a computer-readable storage medium. Background Art

[0002] When a mobile phone collects the user's voice during a call, the sound collected by the microphone often includes environmental noise (such as background human voices, background music, etc.) in addition to the user's voice. Therefore, in order to improve the call quality of mobile phones, mobile phone manufacturers generally introduce noise reduction and voice pickup algorithms in mobile phones. Through built-in technologies and algorithms, background noise in voice is identified and denoised to minimize the impact of background noise on call quality.

[0003] However, in a strong noise environment (such as crowded and noisy places), due to the complex sound sources (such as similar environmental noise in all collection directions of the microphone) and complex frequencies (such as noise covers all frequencies of sound), it is difficult to distinguish the noise from the collected voice relying solely on the microphone and built-in noise reduction algorithm configured in the mobile phone, and it is also difficult to ensure the quality of mobile phone calls.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of this application is to provide a mobile phone accessory with noise reduction and sound pickup, a noise reduction and sound pickup method based on the mobile phone accessory, and a computer-readable storage medium, aiming to achieve that even if the mobile phone is in a strong noise environment, it can still clearly distinguish between environmental noise and user voice, so as to suppress the noise part and thus improve the quality of mobile phone calls.

[0006] To achieve the above-mentioned purpose, the present application provides a mobile phone accessory for noise reduction and sound pickup, comprising a first microphone, a second microphone and an accessory body; wherein an audio processing module and a communication connection module are integrated in the accessory body, and the communication connection module is electrically connected to a plug provided on the accessory body;

[0007] The first microphone is fixedly connected to the accessory body through a fixing member, and is electrically connected to the audio processing module through a wire built into the fixing member;

[0008] The second microphone is electrically connected to the audio processing module, and a distance between the second microphone and the first microphone is greater than or equal to a preset distance;

[0009] When the plug is inserted into the mobile phone connection port, the mobile phone accessory is powered by the mobile phone, the first microphone is used to collect environmental sounds, the second microphone is used to pick up user voices, the audio processing module performs noise reduction processing on the user voices based on the environmental sounds, and the communication connection module is used to transmit the user voices after noise reduction processing to the mobile phone;

[0010] When the user uses the mobile phone connected to the mobile phone accessory to make a call, the first distance between the second microphone and the user's mouth is smaller than the second distance between the first microphone and the user's mouth.

[0011] Optionally, the second microphone is arranged on the accessory body, and when the plug is inserted into the mobile phone connection port, the sound receiving direction of the second microphone is toward the front side of the mobile phone.

[0012] Optionally, the second microphone is movably connected to the accessory body via a microphone rod.

[0013] Optionally, the mobile phone accessory also includes a mobile phone case; wherein the bottom side of the mobile phone case is adapted to the bottom side of the mobile phone where the mobile phone connection port is located, and the bottom side of the shell is integrally formed with the accessory body, and the plug passes through the bottom side of the shell; the first microphone and the fixing part are arranged on the back side of the shell.

[0014] Optionally, the audio processing module includes an input unit, a processing unit and an output unit;

[0015] The input unit is used to receive the ambient sound collected by the first microphone and the user voice collected by the second microphone;

[0016] The processing unit extracts noise features from ambient sound based on a built-in speech enhancement model, and uses the noise features to perform noise suppression on the user's speech;

[0017] The output unit is used to output the user voice after noise reduction processing to the communication connection module.

[0018] To achieve the above purpose, the present application also provides a noise reduction and sound pickup method based on a mobile phone accessory, wherein the mobile phone accessory is the mobile phone accessory for noise reduction and sound pickup as described above; the noise reduction and sound pickup method based on the mobile phone accessory comprises:

[0019] When the plug of the mobile phone accessory is inserted into the mobile phone connection port, the mobile phone accessory obtains power from the mobile phone and detects whether the mobile phone is in call mode;

[0020] If it is detected that the mobile phone is in call mode, the first microphone of the mobile phone accessory starts to collect ambient sound and the second microphone starts to collect user voice;

[0021] Based on the audio processing module of the mobile phone accessory, the user's voice is subjected to noise reduction processing by utilizing the ambient sound;

[0022] Based on the communication connection module of the mobile phone accessory, the noise-reduced user voice is transmitted to the mobile phone.

[0023] Optionally, the step of using the ambient sound to perform noise reduction processing on the user's voice based on the audio processing module of the mobile phone accessory includes:

[0024] Extracting noise features from ambient sound based on a speech enhancement model built into the audio processing module of the mobile phone accessory;

[0025] The noise characteristics are used to perform noise suppression on the user's voice.

[0026] Optionally, the step of extracting noise features in environmental sounds based on a speech enhancement model built into the audio processing module of the mobile phone accessory comprises:

[0027] After framing and windowing the ambient sound, the sound is output to a speech enhancement model built into the audio processing module of the mobile phone accessory;

[0028] The speech enhancement model is used to acquire and abstract the local and global features of the input data to obtain the noise characteristics.

[0029] Optionally, before the step of extracting noise features in environmental sounds based on the built-in speech enhancement model of the audio processing module of the mobile phone accessory, the step further includes:

[0030] A speech enhancement model is built based on the CNN (Convolutional Neural Networks) network, and the model pooling layer uses a self-attention pooling layer and the convolution layer uses a residual connection.

[0031] To achieve the above objectives, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the noise reduction and sound pickup method based on mobile phone accessories are implemented as described above.

[0032] The present application provides a mobile phone accessory for noise reduction and sound pickup, a noise reduction and sound pickup method based on the mobile phone accessory, and a computer-readable storage medium, which provide a mobile phone with an external mobile phone accessory for noise reduction and sound pickup, break through the original structural limitations of the mobile phone, and expand the mobile phone with a first microphone dedicated to collecting ambient sound and a second microphone dedicated to collecting user voice. In this way, even if the mobile phone is in a strong noise environment, it can still clearly distinguish between ambient noise and user voice, and suppress the noise part, effectively optimizing the noise reduction and sound pickup effect in mobile phone calls. Even in a strong noise environment, clear and stable call services can still be obtained, thereby improving the quality of mobile phone calls and thus improving user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a front structural diagram of a mobile phone accessory for noise reduction and sound pickup in one embodiment of the present application;

[0034] Figure 2 This is a schematic diagram of the side structure of a mobile phone accessory for noise reduction and sound pickup in one embodiment of the present application;

[0035] Figure 3 This is a schematic diagram of the back structure of a mobile phone accessory for noise reduction and sound pickup in one embodiment of the present application;

[0036] Figure 4 This is a schematic diagram of the circuit architecture of a mobile phone accessory for noise reduction and sound pickup in one embodiment of the present application;

[0037] Figure 5 This is a schematic structural diagram of a mobile phone accessory for noise reduction and sound pickup in another embodiment of the present application;

[0038] Figure 6 This is a front structural schematic diagram of a mobile phone accessory for noise reduction and sound pickup in another embodiment of the present application;

[0039] Figure 7 This is a schematic diagram of the back structure of a mobile phone accessory for noise reduction and sound pickup in another embodiment of the present application;

[0040] Figure 8 This is a schematic diagram of the steps of a noise reduction and sound pickup method based on mobile phone accessories in one embodiment of the present application.

[0041] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0042] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0043] In addition, if the descriptions of "first", "second", etc. are involved in this application, they are only used for descriptive purposes (such as for distinguishing the same or similar features), and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in this field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0044] In one embodiment, a mobile phone accessory for noise reduction and sound pickup is provided, referring to Figures 1 to 4 , the mobile phone accessory comprises a first microphone, a second microphone and an accessory body; wherein the accessory body is integrated with an audio processing module and a communication connection module, and the communication connection module is electrically connected to a plug provided on the accessory body;

[0045] The first microphone is fixedly connected to the accessory body through a fixing member, and is electrically connected to the audio processing module through a wire built into the fixing member;

[0046] The second microphone is electrically connected to the audio processing module, and a distance between the second microphone and the first microphone is greater than or equal to a preset distance;

[0047] When the plug is inserted into the mobile phone connection port, the mobile phone accessory is powered by the mobile phone, the first microphone is used to collect environmental sounds, the second microphone is used to pick up user voices, the audio processing module performs noise reduction processing on the user voices based on the environmental sounds, and the communication connection module is used to transmit the user voices after noise reduction processing to the mobile phone;

[0048] When the user uses the mobile phone connected to the mobile phone accessory to make a call, the first distance between the second microphone and the user's mouth is smaller than the second distance between the first microphone and the user's mouth.

[0049] In this embodiment, in the accessory body, the audio processing module and the communication connection module can be integrated into corresponding circuit boards. Figure 4The first microphone and the second microphone are electrically connected to the first input terminal and the second input terminal of the audio processing module respectively, and the output terminal of the audio processing module is electrically connected to the plug arranged on the accessory body.

[0050] Optionally, the type of the plug is determined by the type of the mobile phone connector to which the mobile phone accessory is adapted, and may be a USB (such as USB Type-C) plug, a Lightning plug, etc.

[0051] Optionally, the first microphone is fixedly connected to the accessory body via a fixing piece, and the fixing piece is hollow and can contain a built-in wire, so that the first microphone can be electrically connected to the audio processing module via the built-in wire of the fixing piece.

[0052] Optionally, the length of the fixing part may range from [1 / 3L, L), where L is the length of the mobile phone to which the mobile phone accessory is adapted.

[0053] Optional, see Figure 1 and Figure 2 , the second microphone may be disposed on the accessory body and connected to the audio processing module through a wire built into the accessory body; or, referring to Figure 5 The second microphone can also be movably connected to the accessory body through a microphone rod, and connected to the audio processing module through a built-in wire in the microphone rod.

[0054] Optionally, the first microphone is an omnidirectional microphone suitable for capturing a wide range of ambient sounds; the second microphone is a unidirectional microphone specifically used to accurately capture the user's voice. The distance between the second microphone and the first microphone is greater than or equal to a preset distance. By maintaining a certain distance between the second microphone and the first microphone, mutual interference between the two can be reduced. This helps ensure that the second microphone can capture the user's voice more accurately without being affected by the ambient noise collected by the first microphone.

[0055] Optionally, the preset distance can be set according to actual needs, but should not be less than the distance from the first microphone to the accessory body. For example, the preset distance can be set to be greater than or equal to the length of the fixing member.

[0056] Optionally, when the mobile phone accessory is in use, the plug of the mobile phone accessory can be inserted into the mobile phone connection port, and when the plug is inserted into the mobile phone connection port, the various components and modules on the mobile phone accessory can obtain power from the mobile phone. That is, once the plug is inserted into the mobile phone connection port, an electrical connection is established between the mobile phone accessory and the mobile phone, which means that the power of the mobile phone can be transmitted to the various components and modules of the mobile phone accessory through the wire port inside the plug. It should be understood that the plug can transmit power to the various components and modules of the mobile phone accessory through the corresponding power cord (not shown in the figure).

[0057] Optionally, after the plug is inserted into the mobile phone connection port, when the mobile phone is in call mode, the first microphone will continue to collect ambient sound.

[0058] Optionally, the connection portion between the plug and the accessory body may be flexible, fixed or rotatable. Wherein, when the connection portion between the plug and the accessory body is flexible or rotatable, the distance between the first microphone and / or the second microphone and the user's mouth may be adjusted by adjusting the connection portion of the plug.

[0059] Alternatively, when the connection between the plug and the accessory body is fixed, the extension direction of the fixing part is parallel to the direction in which the plug is inserted into the mobile phone, so that when the plug is inserted into the mobile phone connection port, the first microphone will be located on the back side of the mobile phone (i.e., the back side). Since when a user uses a mobile phone to make a call, the front side of the mobile phone (i.e., the front side or the screen side) is generally facing the user, the first microphone located on the back side of the mobile phone can avoid collecting the user's voice or reduce the collection of the user's voice, so as to more accurately collect the ambient sound and avoid interference or echo problems caused by the position of the first microphone during the call.

[0060] Optionally, after the plug is inserted into the mobile phone connector, when the mobile phone is in call mode, the second microphone can be aimed at the user's mouth to collect the corresponding user voice. This direct sound collection method can greatly improve the clarity and recognition rate of the voice, and provide better input quality for calls or voice recognition applications.

[0061] Among them, when the user uses the mobile phone connected to the mobile phone accessory to make a call, the setting position of the second microphone is closer to the user's mouth than the setting position of the first microphone; that is, when the user uses the mobile phone connected to the mobile phone accessory to make a call, the first distance between the second microphone and the user's mouth is smaller than the second distance between the first microphone and the user's mouth.

[0062] For example, taking the case where, when the plug is inserted into the mobile phone connection port, the first microphone is located on the back of the mobile phone, and the second microphone is arranged on the accessory body (the sound receiving direction of the second microphone is toward the front side of the mobile phone), when the user uses the mobile phone connected to the mobile phone accessory to make a call, because the front side of the mobile phone is facing the user at this time, the first distance between the second microphone and the user's mouth will be smaller than the second distance between the first microphone and the user's mouth (that is, the second microphone is closer to the user's mouth than the first microphone).

[0063] Optionally, the ambient sound collected by the first microphone and the user voice collected by the second microphone are both transmitted to the audio processing module, and the audio processing module performs noise reduction processing on the user voice based on the ambient sound.

[0064] Optionally, the audio processing module uses algorithms to analyze and estimate these environmental sounds in order to identify and quantify the characteristics of various noise components. Based on the environmental noise estimation obtained from the environmental sounds, the audio processing module can use noise cancellation algorithms to process the user's voice in real time. These algorithms may include adaptive filtering, spectral subtraction and other technologies, which can effectively suppress background noise while preserving the clarity and naturalness of the user's voice as much as possible.

[0065] Optionally, the user voice after noise reduction processing by the audio processing module will be transmitted to the mobile phone through the communication connection module. The communication connection module can be a data transmission end of the plug, which transmits the user voice after noise reduction processing to the mobile phone; of course, in view of the fact that real-time voice transmission based on the mobile phone connection port may have electrical interference, the communication connection module also includes a Bluetooth module. When the mobile phone Bluetooth is idle, the communication connection module can be connected to the mobile phone through the Bluetooth module and use Bluetooth communication technology to transmit the user voice after noise reduction processing to the mobile phone.

[0066] In one embodiment, an external mobile phone accessory for noise reduction and sound pickup is provided for the mobile phone, breaking through the original structural limitations of the mobile phone, and expanding the mobile phone with a first microphone dedicated to collecting environmental sounds and a second microphone dedicated to collecting user voices. In this way, even if the mobile phone is in a strong noise environment, it can still clearly distinguish between environmental noise and user voices, and suppress the noise part, effectively optimizing the noise reduction and sound pickup effect in mobile phone calls. Even in a strong noise environment, clear and stable call services can still be obtained, thereby improving the quality of mobile phone calls and thus improving user satisfaction.

[0067] Moreover, the mobile phone accessory for noise reduction and sound pickup provided in this embodiment is plug-and-play, without complicated installation steps or additional settings, which greatly improves the convenience of use and user experience. A call detection module (not shown in the figure) can be built into the mobile phone accessory. When the call detection module detects that the mobile phone is in call mode through the communication connection module, the first microphone, the second microphone and the audio processing module are automatically enabled for noise reduction and sound pickup; or, when the mobile phone is in call mode, a corresponding activation instruction can be sent to the mobile phone accessory. When the mobile phone accessory receives the activation instruction based on the communication connection module, the first microphone, the second microphone and the audio processing module are enabled for noise reduction and sound pickup.

[0068] In one embodiment, based on the above embodiment, referring to Figure 1 to Figure 2 The second microphone is arranged on the accessory body, and when the plug is inserted into the mobile phone connection port, the sound receiving direction of the second microphone is toward the front side of the mobile phone.

[0069] In this embodiment, the second microphone is disposed on the accessory body and is connected to the audio processing module via a wire built into the accessory body.

[0070] When the plug is inserted into the mobile phone connection port, the second microphone's sound collection direction faces the front side of the mobile phone. This design ensures that the second microphone can effectively capture the user's voice, because its sound collection direction corresponds to the position of the user's mouth when speaking, thereby providing clearer and more accurate voice input. In this way, the mobile phone accessory can perform noise reduction processing more accurately and transmit the processed voice signal to the mobile phone through the communication connection module to provide a high-quality call experience.

[0071] In one embodiment, based on the above embodiment, referring to Figure 5 The second microphone is movably connected to the accessory body through a microphone rod.

[0072] In this embodiment, the second microphone is movably connected to the accessory body through a microphone rod, and is connected to the audio processing module through a wire built into the microphone rod.

[0073] The microphone pole connection allows the second microphone to adjust its position and angle within a certain range to better adapt to different usage scenarios and user needs. Users can adjust the position of the second microphone according to personal preference or ambient noise conditions to obtain the best voice capture effect (such as bringing the second microphone closer to the user's mouth).

[0074] Optionally, a groove for storing the microphone rod and the second microphone can be provided on the accessory body (not shown in the figure). The groove provides a dedicated space so that the microphone rod and the second microphone can be easily and safely stored on the accessory body. Users can easily put them in or take them out without worrying about easy damage. The integrated design of the accessory body and the groove makes the entire structure more compact and easy to store, improving the overall user experience.

[0075] In one embodiment, based on the above embodiment, referring to Figure 6 to Figure 7 The mobile phone accessory also includes a mobile phone case; wherein the bottom side of the mobile phone case is adapted to the bottom side of the mobile phone where the mobile phone connection port is located, and the bottom side of the case is integrally formed with the accessory body, and the plug passes through the bottom side of the case; the first microphone and the fixing part are arranged on the back side of the case.

[0076] In this embodiment, the shape of the mobile phone case is adapted to the shape of the mobile phone to which the mobile phone accessory is suitable; at the same time, the bottom side of the mobile phone case is adapted to the bottom side of the mobile phone where the mobile phone connection port is located, and the bottom side of the case is integrally formed with the accessory body, and the plug passes through the bottom side of the case. This design allows the user to easily insert the plug into the mobile phone connection port, realizing the function of the mobile phone accessory while realizing the wrapping of the mobile phone by the mobile phone case to protect the mobile phone.

[0077] At the same time, the first microphone and the fixing member are arranged on the back side of the shell to receive the ambient sound.

[0078] In one embodiment, based on the above embodiment, the audio processing module includes an input unit, a processing unit and an output unit;

[0079] The input unit is used to receive the ambient sound collected by the first microphone and the user voice collected by the second microphone;

[0080] The processing unit extracts noise features from ambient sound based on a built-in speech enhancement model, and uses the noise features to perform noise suppression on the user's speech;

[0081] The output unit is used to output the user voice after noise reduction processing to the communication connection module.

[0082] In this embodiment, the input unit receives the ambient sound collected by the first microphone and the user voice collected by the second microphone, and transmits the ambient sound and the user voice to the processing unit in real time.

[0083] After receiving the ambient sound and user voice, the processing unit will use its built-in voice enhancement model to extract noise features. Then the processing unit will suppress the noise part based on the extracted noise features. This noise suppression process can improve the clarity and quality of the user's voice.

[0084] After the processing unit completes the noise reduction processing, the output unit is responsible for transmitting the optimized user voice to the communication connection module, so as to transmit the user voice after the noise reduction processing to the mobile phone through the communication connection module.

[0085] This structured audio processing module design not only effectively processes the sound input from different microphones, but also provides optimized noise suppression and voice clarity through built-in processing units and enhancement models, thereby significantly improving the quality of call voice.

[0086] On the basis of the above embodiments, the present application also proposes a noise reduction and sound pickup method based on mobile phone accessories, which is applied to the noise reduction and sound pickup mobile phone accessories described in the above embodiments; Figure 8 , the noise reduction and sound pickup method based on mobile phone accessories includes:

[0087] Step S10: When the plug of the mobile phone accessory is inserted into the mobile phone connection port, the mobile phone accessory obtains power from the mobile phone and detects whether the mobile phone is in call mode;

[0088] Step S20: If it is detected that the mobile phone is in call mode, the first microphone of the mobile phone accessory starts to collect ambient sound and the second microphone starts to collect user voice;

[0089] Step S30: Based on the audio processing module of the mobile phone accessory, the user's voice is subjected to noise reduction processing using the ambient sound;

[0090] Step S40: Based on the communication connection module of the mobile phone accessory, the noise-reduced user voice is transmitted to the mobile phone.

[0091] In this embodiment, the execution terminal of the embodiment can be a mobile phone accessory, or a mobile phone that is connected to and controls the mobile phone accessory; the following description takes the execution terminal as a mobile phone accessory as an example.

[0092] When the plug of the mobile phone accessory is inserted into the mobile phone connection port, the mobile phone accessory can obtain power from the mobile phone through the plug and start to detect whether the mobile phone is in call mode.

[0093] If it is detected that the mobile phone has turned on the call mode, the first microphone of the mobile phone accessory starts to collect the sound in the environment, and the second microphone starts to collect the user's voice, that is, the two microphones capture the noise of the surrounding environment and the voice signal emitted by the user respectively.

[0094] Optionally, the ambient sound collected by the first microphone and the user voice collected by the second microphone are both transmitted to the audio processing module, and the audio processing module performs noise reduction processing on the user voice based on the ambient sound.

[0095] Optionally, the audio processing module uses algorithms to analyze and estimate these environmental sounds in order to identify and quantify the characteristics of various noise components. Based on the environmental noise estimation obtained from the environmental sounds, the audio processing module can use noise cancellation algorithms to process the user's voice in real time. These algorithms may include adaptive filtering, spectral subtraction and other technologies, which can effectively suppress background noise while preserving the clarity and naturalness of the user's voice as much as possible.

[0096] Optionally, the user voice after noise reduction processing by the audio processing module will be transmitted to the mobile phone through the communication connection module. The communication connection module can be a data transmission end of the plug, which transmits the user voice after noise reduction processing to the mobile phone; of course, in view of the fact that real-time voice transmission based on the mobile phone connection port may have electrical interference, the communication connection module also includes a Bluetooth module. When the mobile phone Bluetooth is idle, the communication connection module can be connected to the mobile phone through the Bluetooth module and use Bluetooth communication technology to transmit the user voice after noise reduction processing to the mobile phone.

[0097] In one embodiment, an external mobile phone accessory for noise reduction and sound pickup is provided for the mobile phone, breaking through the original structural limitations of the mobile phone, and expanding the mobile phone with a first microphone dedicated to collecting environmental sounds and a second microphone dedicated to collecting user voices. In this way, even if the mobile phone is in a strong noise environment, it can still clearly distinguish between environmental noise and user voices, and suppress the noise part, effectively optimizing the noise reduction and sound pickup effect in mobile phone calls. Even in a strong noise environment, clear and stable call services can still be obtained, improving the quality of mobile phone calls, thereby improving user satisfaction.

[0098] In one embodiment, based on the above embodiment, the step of using the ambient sound to perform noise reduction processing on the user's voice by the audio processing module based on the mobile phone accessory includes:

[0099] Extracting noise features from ambient sound based on a speech enhancement model built into the audio processing module of the mobile phone accessory;

[0100] The noise characteristics are used to perform noise suppression on the user's voice.

[0101] In this embodiment, the audio processing module of the mobile phone accessory has a dedicated speech enhancement model built in. When the first microphone collects the ambient sound, the audio processing module uses this model to extract corresponding noise features from the ambient audio.

[0102] Optionally, the step of extracting noise features in environmental sounds based on a speech enhancement model built into the audio processing module of the mobile phone accessory comprises:

[0103] After framing and windowing the ambient sound, the sound is output to a speech enhancement model built into the audio processing module of the mobile phone accessory;

[0104] The speech enhancement model is used to acquire and abstract the local and global features of the input data to obtain the noise characteristics.

[0105] First, the audio processing module of the mobile phone accessory performs frame and window processing on the received ambient sound. This step divides the continuous audio signal into several short-term audio frames and applies a window function to each frame to reduce the spectrum leakage effect and improve the accuracy of spectrum analysis. The processed audio frames are used as input and sent to the built-in speech enhancement model of the audio processing module of the mobile phone accessory to analyze and extract local and global features in the input data.

[0106] Optionally, the speech enhancement model conducts in-depth analysis of the input data to obtain key features. These features may include spectral information, energy distribution, time-frequency characteristics of speech and noise, etc. By abstracting these features, the model can identify and extract relevant features of environmental noise, providing an accurate basis for subsequent noise suppression processing.

[0107] Optionally, the speech enhancement model is built based on a CNN network, which can extract and abstract local and global features of the input data layer by layer through structures such as convolutional layers and pooling layer activation functions.

[0108] Furthermore, based on the extracted noise features, the audio processing module performs noise suppression on the noise part:

[0109] First, the audio processing module will match and analyze the features extracted from the ambient noise with the currently collected user voice, including comparing the similarities or differences between the spectral information, energy distribution, and time-frequency characteristics of the noise features and the user voice; based on the results of feature matching, the audio processing module will perform real-time noise suppression on the user voice according to a pre-set noise suppression algorithm. These algorithms may include adaptive filters, spectral subtraction, frequency domain estimation and other technologies to reduce the interference of ambient noise on the user voice.

[0110] After noise reduction processing, the audio processing module transmits the optimized user voice to the communication connection module for output. This ensures that the voice communication through the mobile phone accessories is significantly improved in signal quality and clarity, allowing users to enjoy a high-quality call experience in various environmental conditions.

[0111] In some optional embodiments, as the ambient noise changes and the user's voice changes in real time, the audio processing module can also dynamically adjust the parameters or strategies of the noise suppression algorithm as needed to ensure that the best voice clarity and noise suppression effect are always maintained.

[0112] Optionally, the audio processing module obtains the spectral characteristics of the noise in the current environment through spectrum analysis, which includes detecting the energy distribution and intensity of the noise at different frequencies. According to the results of the spectrum analysis, the threshold of the adaptive filter is determined. The threshold can be set according to the energy intensity of the noise in different frequency bands, usually while being able to effectively suppress the noise while retaining the clarity of the user's voice as much as possible. For example, different threshold optional ranges are set for different frequency bands, and the corresponding value is selected from the threshold optional range according to the energy intensity of the frequency band where the noise is currently located (and the greater the energy intensity, the smaller the value). This helps to optimize the noise suppression process to ensure the clarity and effect of voice communication.

[0113] Optionally, the audio processing module can monitor and analyze the sound intensity of the user's voice in real time (the sound intensity can be represented by the amplitude or energy of the audio signal, usually quantified in decibels). Then, the gain of the spectrum subtraction algorithm is set according to the detected sound intensity, wherein the higher the sound intensity, the smaller the gain setting to avoid over-suppressing the voice signal; conversely, the lower the sound intensity, the larger the gain setting to ensure that the impact of background noise is effectively reduced. This can maintain a balance in the noise suppression effect in different voice input scenarios while optimizing the clarity and intelligibility of the voice.

[0114] In this way, the audio processing module can respond to changes in the environment and user input in real time and dynamically optimize the noise suppression processing, thereby ensuring that the voice quality during calls or speech recognition always remains at its best.

[0115] In one embodiment, based on the above embodiment, before the step of extracting noise features in environmental sounds based on the built-in speech enhancement model of the audio processing module of the mobile phone accessory, the step further includes:

[0116] A speech enhancement model is built based on the CNN network, and the model pooling layer uses self-attention pooling layer and the convolution layer uses residual connection.

[0117] In this embodiment, the speech enhancement model is constructed based on the CNN network as follows:

[0118] (1) Convolutional layer: The core of the CNN network is a multi-layer convolutional layer. These layers perform convolution operations on the input audio frames through a series of convolution kernels. Each convolution kernel can capture local features of different scales, such as changes in the spectrum and frequency information. Each convolution kernel produces a feature map that contains the spatial mapping of specific features in the input data. At the same time, in each convolutional layer, the residual connection technology is used to alleviate the gradient vanishing problem during the training process of the deep network, while retaining the original input information, improving the training efficiency and feature learning ability of the model.

[0119] (2) Pooling layer: A pooling layer is added after the convolution layer. The pooling layer reduces the spatial size of each feature map by downsampling while retaining the most important features. In the pooling stage, the speech enhancement model applies a self-attention pooling layer, which can automatically learn the global importance of each feature based on the input feature map and weight the pooling according to its importance. This can effectively capture long-distance dependencies and help improve the model's ability to handle complex features in the input data.

[0120] (3) Activation function: After the convolution and pooling operations, each convolution layer and pooling layer introduces a nonlinear activation function, such as ReLU (Rectified Linear Unit). The activation function helps the network learn complex nonlinear features and enhances the expressiveness of the model.

[0121] (4) Fully connected layers: After extracting and abstracting features through multiple convolutional layers and pooling layers, the CNN model can also include fully connected layers. Fully connected layers transform the feature maps of the previous layers into the final output. These layers can play an important role in integrating and learning complex relationships between different features.

[0122] (5) Training and optimization of speech enhancement models: After the model is built, it needs to be trained and optimized so that it can accurately extract and abstract the noise features in the input audio data. The training process usually involves using a labeled dataset and adjusting the model's parameters through optimization algorithms such as back propagation and gradient descent to maximize the speech enhancement effect.

[0123] Through the construction and training process of the above CNN network, the audio processing module of the mobile phone accessories can use the built-in speech enhancement model to effectively extract noise features from environmental sounds and provide accurate input data for subsequent noise suppression processing. This technology can not only significantly improve the quality of voice communication, but also provide clear and high-quality user voice output in noisy environments.

[0124] In addition, the present application also proposes a computer-readable storage medium, the computer-readable storage medium includes a computer program, and when the computer program is executed by a processor, the steps of the noise reduction and sound pickup method based on mobile phone accessories as described in the above embodiment are implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0125] In summary, a mobile phone accessory for noise reduction and sound pickup, a noise reduction and sound pickup method based on the mobile phone accessory, and a computer-readable storage medium provided in the embodiments of the present application provide an external mobile phone accessory for noise reduction and sound pickup for the mobile phone, break through the original structural limitations of the mobile phone, and expand the mobile phone with a first microphone dedicated to collecting ambient sound and a second microphone dedicated to collecting user voice. In this way, even if the mobile phone is in a strong noise environment, it can still clearly distinguish between ambient noise and user voice, and suppress the noise part, effectively optimizing the noise reduction and sound pickup effect in mobile phone calls. Even in a strong noise environment, clear and stable call services can still be obtained, thereby improving the quality of mobile phone calls and thus improving user satisfaction.

[0126] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0127] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0128] The above description is only a preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A mobile phone accessory for noise reduction and sound pickup, characterized in that: Includes a first microphone, a second microphone and an accessory body; The accessory body integrates an audio processing module and a communication connection module, and the communication connection module is electrically connected to a plug provided on the accessory body; The first microphone is fixedly connected to the accessory body through a fixing member, and is electrically connected to the audio processing module through a wire built into the fixing member; The second microphone is electrically connected to the audio processing module, and a distance between the second microphone and the first microphone is greater than or equal to a preset distance; When the plug is inserted into the mobile phone connection port, the mobile phone accessory is powered by the mobile phone, the first microphone is used to collect environmental sounds, the second microphone is used to pick up user voices, the audio processing module performs noise reduction processing on the user voices based on the environmental sounds, and the communication connection module is used to transmit the user voices after noise reduction processing to the mobile phone; Wherein, when the second microphone picks up the user's voice, the first distance between the second microphone and the user's mouth is smaller than the second distance between the first microphone and the user's mouth; The audio processing module includes an input unit, a processing unit and an output unit; The input unit is used to receive the ambient sound collected by the first microphone and the user voice collected by the second microphone; The processing unit extracts noise features from ambient sound based on a built-in speech enhancement model, and uses the noise features to suppress noise on the user's speech; wherein, after framing and windowing the ambient sound, the sound is output to the speech enhancement model built into the audio processing module of the mobile phone accessory; the speech enhancement model is used to acquire and abstract local and global features of the input data to obtain noise features; and the noise features are used to suppress noise on the user's speech; The output unit is used to output the user voice after noise reduction processing to the communication connection module.

2. The mobile phone accessory for noise reduction and sound pickup according to claim 1, characterized in that: The second microphone is arranged on the accessory body, and when the plug is inserted into the mobile phone connection port, the sound receiving direction of the second microphone is toward the front side of the mobile phone.

3. The mobile phone accessory for noise reduction and sound pickup according to claim 1, characterized in that: The second microphone is movably connected to the accessory body through a microphone rod.

4. The mobile phone accessory for noise reduction and sound pickup according to claim 1, characterized in that: The mobile phone accessory also includes a mobile phone case; wherein the bottom side of the mobile phone case is adapted to the bottom side of the mobile phone where the mobile phone connection port is located, and the bottom side of the shell is integrally formed with the accessory body, and the plug passes through the bottom side of the shell; the first microphone and the fixing part are arranged on the back side of the shell.

5. A noise reduction and sound pickup method based on mobile phone accessories, characterized in that: The mobile phone accessory is a mobile phone accessory for noise reduction and sound pickup according to any one of claims 1 to 4; the method for noise reduction and sound pickup based on the mobile phone accessory comprises: When the plug of the mobile phone accessory is inserted into the mobile phone connection port, the mobile phone accessory obtains power from the mobile phone and detects whether the mobile phone is in call mode; If it is detected that the mobile phone is in call mode, the first microphone of the mobile phone accessory starts to collect ambient sound and the second microphone starts to collect user voice; After framing and windowing the ambient sound, the sound is output to a speech enhancement model built into the audio processing module of the mobile phone accessory; Use the speech enhancement model to obtain and abstract the local and global features of the input data to obtain the noise characteristics; Performing noise suppression on the user's voice using the noise feature; Based on the communication connection module of the mobile phone accessory, the noise-reduced user voice is transmitted to the mobile phone.

6. The noise reduction and sound pickup method based on mobile phone accessories as claimed in claim 5, characterized in that: Before the step of extracting noise features from environmental sounds based on the built-in speech enhancement model of the audio processing module of the mobile phone accessory, the method further includes: A speech enhancement model is built based on the CNN network, and the model pooling layer uses self-attention pooling layer and the convolution layer uses residual connection.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the noise reduction and sound pickup method based on mobile phone accessories as claimed in claim 5 or 6 are implemented.

Images