Vehicle-mounted voice noise reduction method, device, electronic equipment and storage medium

Abstract

The embodiment of the present invention discloses a vehicle-mounted voice noise reduction method, device, electronic device and storage medium. The vehicle-mounted voice noise reduction method comprises: obtaining vehicle-mounted audio data, and performing initial noise reduction processing on the vehicle-mounted audio data to obtain vehicle-mounted voice data to be noise-reduced; obtaining external vehicle environment audio data, and performing noise reduction processing on the vehicle-mounted voice data to be noise-reduced again according to the external vehicle environment audio data to obtain target vehicle-mounted voice data; and controlling the vehicle-mounted voice system according to the target vehicle-mounted voice data. The technical solution of the embodiment of the present invention can improve the noise filtering effect, accurately identify the voice in the vehicle environment, and improve the user experience.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of automotive electronic application technology, and in particular to a vehicle-mounted voice noise reduction method, device, electronic equipment and storage medium. Background Art

[0002] The application of in-vehicle voice recognition in real life has become more and more common. Since the microphone in the car not only collects human voices, but also environmental sounds (such as media sounds played by the car audio entertainment system and environmental noise, etc.), the sound signal and environmental noise emitted by the sound unit of the in-vehicle device itself need to be eliminated during the voice recognition process to retain the effective voice command signal.

[0003] At present, speech noise reduction solutions are mainly used to eliminate media sounds played by car audio and entertainment systems and basic noises with low amplitudes. Their ability to eliminate high-amplitude environmental noises is obviously insufficient, that is, when high-amplitude environmental noise exists, the noise filtering effect is poor. Summary of the invention

[0004] The embodiments of the present invention provide a vehicle-mounted voice noise reduction method, device, electronic device and storage medium, which can improve the noise filtering effect, accurately recognize the voice in the vehicle environment, and improve the user experience.

[0005] In a first aspect, an embodiment of the present invention provides a vehicle-mounted voice noise reduction method, comprising:

[0006] Acquire vehicle audio data, and perform primary noise reduction processing on the vehicle audio data to obtain vehicle voice data to be subjected to noise reduction;

[0007] Acquire the external environment audio data, and perform noise reduction processing on the noise-reduced vehicle voice data again according to the external environment audio data to obtain the target vehicle voice data;

[0008] The vehicle voice system is controlled according to the target vehicle voice data.

[0009] In a second aspect, an embodiment of the present invention further provides a vehicle-mounted speech noise reduction device, comprising:

[0010] The vehicle voice data module to be subjected to noise reduction is used to obtain the vehicle audio data and perform primary noise reduction processing on the vehicle audio data to obtain the vehicle voice data to be subjected to noise reduction;

[0011] The target vehicle voice data acquisition module is used to acquire the external environment audio data, and perform noise reduction processing on the noise-reduced vehicle voice data again according to the external environment audio data to obtain the target vehicle voice data;

[0012] The vehicle voice system control module is used to control the vehicle voice system according to the target vehicle voice data.

[0013] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0014] one or more processors;

[0015] A storage device for storing one or more programs;

[0016] When the one or more programs are executed by the one or more processors, the one or more processors implement the vehicle-mounted speech noise reduction method provided by any embodiment of the present invention.

[0017] In a fourth aspect, an embodiment of the present invention further provides a computer storage medium on which a computer program is stored, and when the program is executed by a processor, the vehicle-mounted speech noise reduction method provided by any embodiment of the present invention is implemented.

[0018] The technical solution of this embodiment obtains vehicle audio data and performs a primary noise reduction process on the vehicle audio data to obtain vehicle voice data to be noise-reduced, and then obtains the external vehicle environment audio data, and performs a noise reduction process on the vehicle voice data to be noise-reduced again according to the external vehicle environment audio data to obtain the target vehicle voice data, thereby controlling the vehicle voice system according to the target vehicle voice data. By performing a primary noise reduction process on the vehicle audio data, the recognition of the voice in the vehicle voice data to be noise-reduced can be improved, and by using the external vehicle environment audio data to perform a secondary noise reduction process on the vehicle voice data to be noise-reduced, the high-amplitude noise in the vehicle voice data to be noise-reduced can be further filtered out to obtain the target vehicle voice data with the best voice recognition effect, and the target vehicle voice data can be used to accurately control the vehicle voice system, thereby solving the problem of poor noise filtering effect of the existing voice noise reduction scheme, improving the noise filtering effect, accurately identifying the voice in the vehicle environment, and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a flow chart of a vehicle-mounted voice noise reduction method provided by Embodiment 1 of the present invention;

[0020] Figure 2 is a flow chart of a vehicle-mounted voice noise reduction method provided by Embodiment 2 of the present invention;

[0021] Figure 3 is an algorithm flow chart of a vehicle-mounted voice noise reduction method provided by Embodiment 2 of the present invention;

[0022] Figure 4 This is a schematic diagram of audio waveform comparison provided by Embodiment 2 of the present invention;

[0023] Figure 5It is a schematic diagram of audio waveforms corresponding to the external vehicle environment audio data and the vehicle voice data to be de-noised provided by the second embodiment of the present invention;

[0024] Figure 6 is a waveform diagram of a differential audio provided by the second embodiment of the present invention;

[0025] Figure 7 is a schematic diagram of a vehicle-mounted voice noise reduction device provided in Embodiment 3 of the present invention;

[0026] Figure 8 A schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0027] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention.

[0028] It should also be noted that, for ease of description, only the part relevant to the present invention but not all content is shown in the accompanying drawings. It should be mentioned before discussing exemplary embodiments in more detail that some exemplary embodiments are described as processing or methods depicted as flow charts. Although the flow chart describes each operation (or step) as sequential processing, many operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of each operation can be rearranged. When its operation is completed, the processing can be terminated, but it can also have additional steps not included in the accompanying drawings. The processing can correspond to methods, functions, procedures, subroutines, subprograms, etc.

[0029] Embodiment 1

[0030] Figure 1 This is a flow chart of a vehicle-mounted voice noise reduction method provided by the first embodiment of the present invention. This embodiment is applicable to the case of accurately recognizing voice in a vehicle-mounted environment. The method can be executed by a vehicle-mounted voice noise reduction device, which can be implemented by software and / or hardware and can generally be integrated in an electronic device. The electronic device can be a vehicle-mounted terminal device, etc. The embodiment of the present invention does not limit the type of electronic device that executes the vehicle-mounted voice noise reduction method. Accordingly, Figure 1 As shown, the method includes the following operations:

[0031] S110: Acquire vehicle audio data, and perform primary noise reduction processing on the vehicle audio data to obtain vehicle voice data to be subjected to noise reduction.

[0032] The vehicle audio data may be audio data collected by a sound collection device installed in the vehicle, that is, audio data of sounds existing in the vehicle environment. The initial noise reduction processing may be the first noise reduction processing performed on the vehicle audio data, which is used to remove the audio data played by the vehicle system and the audio data generated by the ambient noise in the vehicle. The vehicle voice data to be denoised may be audio data after the vehicle audio data has completed the initial noise reduction processing, which is used for the second noise reduction processing.

[0033] In an embodiment of the present invention, a sound signal can be collected by a sound collection device installed in the vehicle, and the sound signal can be converted into a signal in a desired form (such as an electrical signal, etc.) to obtain vehicle-mounted audio data, and the vehicle-mounted audio data can be further subjected to primary noise reduction processing to remove the audio played by the vehicle-mounted system and the audio data generated by the ambient noise in the vehicle from the vehicle-mounted audio data, so as to obtain the vehicle-mounted voice data to be denoised.

[0034] S120, obtaining the external vehicle environment audio data, and performing noise reduction processing on the vehicle voice data to be subjected to noise reduction according to the external vehicle environment audio data, to obtain the target vehicle voice data.

[0035] The vehicle external environment audio data may be audio data collected by a sound collection device installed outside the vehicle, that is, audio data generated by the vehicle external environment. The target vehicle voice data may be voice data obtained by further performing noise reduction processing on the vehicle voice data to be subjected to noise reduction according to the vehicle external environment audio data.

[0036] In an embodiment of the present invention, a sound signal can be collected by a sound collection device installed outside the vehicle, and the sound signal can be converted into a signal in a desired form to obtain audio data of the vehicle environment. Then, the audio data generated by the noise of the vehicle environment outside the vehicle in the vehicle voice data to be de-noised can be filtered out by using the audio data of the vehicle environment outside the vehicle, so as to achieve a second noise reduction process on the vehicle voice data to be de-noised and obtain the target vehicle voice data. Since the noise of the vehicle environment outside the vehicle is generally high-amplitude noise, that is, the audio data of the vehicle environment outside the vehicle includes audio data generated by high-amplitude noise, the audio data of the vehicle environment outside the vehicle can be used to perform a second noise reduction process on the vehicle voice data to be de-noised, so as to achieve the filtering of audio data matching the high-amplitude environmental noise and improve the noise filtering effect.

[0037] S130: Control the vehicle voice system according to the target vehicle voice data.

[0038] The vehicle voice system may be a system that controls the operation of the vehicle function module according to the voice signal. The vehicle function module may be a module in the vehicle system that operates according to the control instructions of the vehicle voice system, such as the air conditioning system, audio player and lighting device in the vehicle system.

[0039] In the embodiment of the present invention, the target vehicle-mounted voice data may be sent to the vehicle-mounted voice system, and then the vehicle-mounted voice system may be controlled to send a control instruction to the vehicle-mounted function module according to the target vehicle-mounted voice data.

[0040] Optionally, the vehicle voice system can compare the target vehicle voice data with a pre-configured standard voice or standard text. If the target vehicle voice data successfully matches the pre-configured standard voice or standard text, a control instruction is sent to the vehicle function module according to the standard voice or standard text matching the target vehicle voice data. The standard voice can be all voice samples that the vehicle voice system can recognize. The standard text can be the text corresponding to the standard voice.

[0041] The technical solution of this embodiment obtains vehicle audio data and performs a primary noise reduction process on the vehicle audio data to obtain vehicle voice data to be noise-reduced, and then obtains the external vehicle environment audio data, and performs a noise reduction process on the vehicle voice data to be noise-reduced again according to the external vehicle environment audio data to obtain the target vehicle voice data, thereby controlling the vehicle voice system according to the target vehicle voice data. By performing a primary noise reduction process on the vehicle audio data, the recognition of the voice in the vehicle voice data to be noise-reduced can be improved, and by using the external vehicle environment audio data to perform a secondary noise reduction process on the vehicle voice data to be noise-reduced, the high-amplitude noise in the vehicle voice data to be noise-reduced can be further filtered out to obtain the target vehicle voice data with the best voice recognition effect, and the target vehicle voice data can be used to accurately control the vehicle voice system, thereby solving the problem of poor noise filtering effect of the existing voice noise reduction scheme, improving the noise filtering effect, accurately identifying the voice in the vehicle environment, and improving the user experience.

[0042] Embodiment 2

[0043] Figure 2 is a flow chart of a vehicle-mounted voice noise reduction method provided by Embodiment 2 of the present invention. This embodiment is specific based on the above embodiment. In this embodiment, a specific optional implementation method for obtaining the audio data of the vehicle external environment is provided, such as Figure 2 As shown, the method of the embodiment of the present invention specifically includes:

[0044] S210: Acquire vehicle audio data, and perform primary noise reduction processing on the vehicle audio data to obtain vehicle voice data to be subjected to noise reduction.

[0045] S220: Acquire external vehicle environment audio data.

[0046] In an optional embodiment of the present invention, S220 may specifically include:

[0047] S221. When it is determined that the vehicle-mounted voice data to be denoised is a target waveform, determine a vehicle operating state.

[0048] The target waveform may be a continuous waveform within a preset time length, which is a non-human voice waveform. The preset time length may be set according to actual noise reduction needs, such as 5s, 3s or 2s. The vehicle operating state may be the operating state of the vehicle. Optionally, the vehicle operating state may include but is not limited to the window state and the speed range.

[0049] In an embodiment of the present invention, the waveform that matches the vehicle-mounted voice data to be denoised can be first determined, and then it can be determined whether the waveform that matches the vehicle-mounted voice data to be denoised is a target waveform. If the waveform that matches the vehicle-mounted voice data to be denoised is the target waveform, it can be determined that there is a non-human voice waveform in the vehicle-mounted voice data to be denoised, and it is necessary to perform noise reduction processing on the vehicle-mounted voice data to be denoised again, and further determine the vehicle operating state of the current vehicle to determine the noise reduction processing strategy according to the vehicle operating state of the current vehicle. If the waveform that matches the vehicle-mounted voice data to be denoised is not the target waveform, that is, there is no non-human voice waveform in the vehicle-mounted voice data to be denoised, there is no need to further determine the vehicle operating state, and there is no need to perform noise reduction processing on the vehicle-mounted voice data to be denoised again.

[0050] S222: When it is determined that the vehicle operating state is the target vehicle operating state, turn on the external microphone.

[0051] The external microphone may be a sound collection device installed outside the vehicle. The target vehicle operating state may be a vehicle operating state that causes the vehicle voice data to be de-noised to be subjected to a further de-noising process before human voices can be recognized. Exemplarily, the target vehicle operating state may include, but is not limited to, a window open state and / or a current vehicle speed exceeding a preset vehicle speed range.

[0052] In the embodiment of the present invention, it can be further confirmed whether the vehicle operating state of the current vehicle is the target vehicle operating state. If the vehicle operating state of the current vehicle is the target vehicle operating state, the external microphone of the current vehicle is awakened to put the external microphone of the current vehicle into a working state. If the current vehicle operating state is not the target vehicle operating state, the external microphone remains in a dormant state to save power.

[0053] S223: Acquire external environment audio data through an external microphone.

[0054] In the embodiment of the present invention, if the external microphone of the current vehicle is in the awake state, the external environment audio data is acquired through the external microphone.

[0055] The vehicle exterior environment audio data may include at least one of tire noise audio data, wind noise audio data, and engine noise. The tire noise audio data may be audio data generated by tire friction in the vehicle exterior environment audio data. The wind noise audio data may be audio data generated by wind noise outside the vehicle in the vehicle exterior environment audio data. The engine noise may be audio data generated by the current vehicle engine in the vehicle exterior environment audio data.

[0056] S230: Perform noise reduction processing again on the vehicle voice data to be subjected to noise reduction according to the vehicle external environment audio data to obtain target vehicle voice data.

[0057] In an optional embodiment of the present invention, based on the external environment audio data, the vehicle-mounted voice data to be denoised is subjected to noise reduction processing again to obtain the target vehicle-mounted voice data, which may include: obtaining the audio resolution interval; based on the external environment audio data within the audio resolution interval and the vehicle-mounted voice data to be denoised, the vehicle-mounted voice data to be denoised is subjected to noise reduction processing again to obtain the target vehicle-mounted voice data.

[0058] The audio resolution interval may be the minimum length of a text word that matches the voice without being split. For example, the audio resolution interval may be 10 seconds or the like.

[0059] In an embodiment of the present invention, an audio resolution interval can be set according to the audio resolution of the sound collection device, so as to obtain the external vehicle environment audio data and the vehicle voice data to be denoised within the same audio resolution interval, and the vehicle voice data to be denoised can be denoised again using the external vehicle environment audio data within the same audio resolution interval to obtain the target vehicle voice data.

[0060] In an optional embodiment of the present invention, based on the external vehicle environment audio data within the audio resolution interval and the vehicle-mounted voice data to be denoised, the vehicle-mounted voice data to be denoised is subjected to denoising processing again to obtain target vehicle-mounted voice data, which may include: determining the target external vehicle environment audio data and the target vehicle-mounted voice data to be denoised based on the current time and the audio resolution interval; determining the differential calculation result between the target external vehicle environment audio data and the target vehicle-mounted voice data to be denoised; and determining the target vehicle-mounted voice data based on the differential calculation result.

[0061] The target vehicle external environment audio data and the target vehicle voice data to be de-noised are in the same audio resolution interval, the vehicle external environment audio data generated before the current moment is the target vehicle external environment audio data, and the vehicle voice data to be de-noised generated after the current moment is the target vehicle voice data to be de-noised. The difference calculation result can be the result of waveform difference processing of the target vehicle external environment audio data and the target vehicle voice data to be de-noised.

[0062] In an embodiment of the present invention, target external vehicle environment audio data and target vehicle-mounted voice data to be noise-reduced can be obtained according to the current time and the audio resolution interval, and then the waveform corresponding to the target external vehicle environment audio data is used as the subtrahend, and the waveform corresponding to the target vehicle-mounted voice data to be noise-reduced is used as the minuend, and the two waveforms are differentially calculated to obtain a differential calculation result, and the audio data corresponding to the differential calculation result is further used as the target vehicle-mounted voice data.

[0063] Optionally, the current moment may be located within the middle half, one third, or one quarter of the audio resolution interval where the target vehicle exterior environment audio data and the target vehicle voice data to be de-noised are located. Exemplarily, assuming that the current moment is 11:20:20, the audio resolution interval where the target vehicle exterior environment audio data and the target vehicle voice data to be de-noised are located may be 11:20:17-11:20:27, or 11:20:15-11:20:25, etc. The embodiment of the present invention does not limit the specific time range of the audio resolution interval where the target vehicle exterior environment audio data and the target vehicle voice data to be de-noised are located at the current moment.

[0064] In an optional embodiment of the present invention, determining the target external vehicle environment audio data and the target vehicle voice data to be denoised according to the current moment and the audio resolution interval may include: determining the first audio resolution differential interval and the second audio resolution differential interval according to the audio resolution interval; using the external vehicle environment audio data within the first audio resolution differential interval before the current moment as the target external vehicle environment audio data; and using the vehicle voice data to be denoised within the second audio resolution differential interval after the current moment as the target vehicle voice data to be denoised.

[0065] The duration corresponding to the first audio resolution differential interval may be a decimal multiple of the duration corresponding to the audio resolution interval. For example, the audio resolution differential interval may be 0.5s or 0.3s, etc. The sum of the duration corresponding to the first audio resolution differential interval and the duration corresponding to the second audio resolution differential interval may be an integer multiple of the audio resolution interval.

[0066] In an embodiment of the present invention, the first audio resolution differential interval and the second audio resolution differential interval can be determined according to the actual denoising needs and the audio resolution interval, and then the outdoor environment audio data within the first audio resolution differential interval before the current moment is used as the target outdoor environment audio data, and the in-vehicle voice data to be denoised within the second audio resolution differential interval after the current moment is used as the target in-vehicle voice data to be denoised.

[0067] In an optional embodiment of the present invention, determining the target external vehicle environment audio data and the target vehicle voice data to be denoised according to the current moment and the audio resolution interval may include: determining the first audio resolution differential interval and the second audio resolution differential interval according to the audio resolution interval; determining the external vehicle environment audio equalization data according to the external vehicle environment audio data within the first audio resolution differential interval before the current moment, and using the external environment audio equalization data as the target external vehicle environment audio data; using the vehicle voice data to be denoised within the target multiples of the second audio resolution differential interval after the current moment as the target vehicle voice data to be denoised.

[0068] The vehicle exterior environment audio equalization data may be a data average of the vehicle exterior environment audio data within the first audio resolution difference interval before the current moment. The target multiple may be a preset integer greater than 0.

[0069] In an embodiment of the present invention, after determining the first audio resolution differential interval and the second audio resolution differential interval, the vehicle exterior environment audio data within the first audio resolution differential interval before the current moment can be obtained, and the data mean of the vehicle exterior environment audio data within the first audio resolution differential interval can be calculated to obtain the vehicle exterior environment audio balanced data, and then the external environment audio balanced data is used as the target vehicle exterior environment audio data, and the vehicle-mounted voice data to be denoised within the target multiples of the second audio resolution differential interval after the current moment is further used as the target vehicle-mounted voice data to be denoised.

[0070] S240: Control the vehicle voice system according to the target vehicle voice data.

[0071] Figure 3 is an algorithm flow chart of a vehicle-mounted speech noise reduction method provided by Embodiment 2 of the present invention, such as Figure 3 As shown, a microphone can be used to collect sound to obtain vehicle audio data including human voice and ambient sound (audio played by the vehicle system and ambient noise in the car, etc.), and basic noise reduction (initial noise reduction processing) can be performed on the vehicle audio data to obtain a noise-reduced audio waveform (an audio waveform that matches the vehicle voice data to be noise-reduced), so as to determine whether the noise-reduced audio waveform is the target waveform. If the audio waveform is not the target waveform, the vehicle voice data to be noise-reduced is sent to the voice recognition module to recognize the human voice in the vehicle voice data to be noise-reduced through the voice recognition module. If the audio waveform is the target waveform, it is determined whether the windows / speed of the current vehicle are in the target vehicle operating state. If the current vehicle is not in the target vehicle operating state, the vehicle voice data to be noise-reduced is sent to the voice recognition module. Exemplarily, the comparison of the audio waveforms of wind noise and (wind noise + human voice) can be seen in Figure 4 .

[0072] If the audio waveform is the target waveform, and the current vehicle is in the target vehicle operating state (windows open and / or high speed), it can be determined that the vehicle voice data to be de-noised includes a large amount of external environmental noise, and then the external microphone recording is enabled to obtain the external environmental audio data, and the current time is taken as n. Because the external environmental noise corresponding to the external environmental audio data, such as tire noise, wind noise and engine noise, has a relatively continuous and stable characteristic, and changes very little in a very short time, and because the audio obtained after basic noise reduction has eliminated the media sound in the car, the audio at this time (vehicle voice data to be de-noised) is the superposition of human voice and tire noise, wind noise and engine noise. Further, the audio resolution interval is set to 10s, and the external environmental audio data 5ms before the current moment and the vehicle voice data to be de-noised 5ms after the current moment are subjected to real-time differential subtraction operations, that is, the external environmental audio data in the (n-5ms)-(n) time period are subjected to differential subtraction operations with the vehicle voice data to be de-noised in the (n)-(n+5ms) time period. The audio waveforms corresponding to the external environment audio data and the vehicle voice data to be de-noised can be found in Figure 5 .

[0073] The in-vehicle voice data to be denoised is the audio containing tire noise, wind noise and other noises as well as human voices. The audio recorded by the microphone outside the car containing only tire noise, wind noise and other noises is subtracted. The obtained differential audio (target in-vehicle voice data) only includes human voices. The waveform of the differential audio can be seen in Figure 6 The differentiated audio is sent to the speech recognition module in real time for semantic recognition. At this time, the user's wake-up speech in the car can have a higher wake-up rate and recognition rate.

[0074] The technical solution of this embodiment obtains the vehicle-mounted audio data and performs the initial noise reduction processing on the vehicle-mounted audio data to obtain the vehicle-mounted voice data to be noise-reduced, and then when it is determined that the vehicle-mounted voice data to be noise-reduced is the target waveform, the vehicle operating state is determined, and when it is determined that the vehicle operating state is the target vehicle operating state, the external vehicle microphone is turned on, thereby obtaining the external vehicle environment audio data through the external vehicle microphone, and further based on the external vehicle environment audio data, the vehicle-mounted voice data to be noise-reduced is noise-reduced again to obtain the target vehicle-mounted voice data, thereby controlling the vehicle-mounted voice system according to the target vehicle-mounted voice data. In this solution, when the vehicle-mounted voice data to be noise-reduced is the target waveform and the target vehicle operating state, the external vehicle environment audio data is obtained through the external vehicle microphone, which can ensure the normal use of the vehicle-mounted voice system under extreme working conditions. By performing initial noise reduction processing on the in-vehicle audio data, the recognition of the voice in the in-vehicle voice data to be noise reduced can be improved. By using the audio data of the outside vehicle environment, the in-vehicle voice data to be noise reduced can be subjected to further noise reduction processing, and the high-amplitude noise in the in-vehicle voice data to be noise reduced can be further filtered out, so as to obtain the target in-vehicle voice data with the best voice recognition effect, and realize the accurate control of the in-vehicle voice system by the target in-vehicle voice data, thus solving the problem of poor noise filtering effect of the existing voice noise reduction scheme, improving the noise filtering effect, accurately identifying the voice in the in-vehicle environment, and improving the user experience.

[0075] It should be noted that any arrangement and combination of the technical features in the above embodiments also falls within the protection scope of the present invention.

[0076] Embodiment 3

[0077] Figure 7 is a schematic diagram of a vehicle-mounted speech noise reduction device provided by Embodiment 3 of the present invention, such as Figure 7 As shown, the device includes: a vehicle voice data module 310 to be de-noised, a target vehicle voice data acquisition module 320 and a vehicle voice system control module 330, wherein:

[0078] The vehicle voice data module 310 to be subjected to noise reduction is used to obtain vehicle audio data and perform primary noise reduction processing on the vehicle audio data to obtain vehicle voice data to be subjected to noise reduction;

[0079] The target vehicle voice data acquisition module 320 is used to acquire the external vehicle environment audio data, and perform noise reduction processing on the noise-reduced vehicle voice data again according to the external vehicle environment audio data to obtain the target vehicle voice data;

[0080] The vehicle voice system control module 330 is used to control the vehicle voice system according to the target vehicle voice data.

[0081] The technical solution of this embodiment obtains vehicle audio data and performs a primary noise reduction process on the vehicle audio data to obtain vehicle voice data to be noise-reduced, and then obtains the external vehicle environment audio data, and performs a noise reduction process on the vehicle voice data to be noise-reduced again according to the external vehicle environment audio data to obtain the target vehicle voice data, thereby controlling the vehicle voice system according to the target vehicle voice data. By performing a primary noise reduction process on the vehicle audio data, the recognition of the voice in the vehicle voice data to be noise-reduced can be improved, and by using the external vehicle environment audio data to perform a secondary noise reduction process on the vehicle voice data to be noise-reduced, the high-amplitude noise in the vehicle voice data to be noise-reduced can be further filtered out to obtain the target vehicle voice data with the best voice recognition effect, and the target vehicle voice data can be used to accurately control the vehicle voice system, thereby solving the problem of poor noise filtering effect of the existing voice noise reduction scheme, improving the noise filtering effect, accurately identifying the voice in the vehicle environment, and improving the user experience.

[0082] Optionally, the target vehicle-mounted voice data acquisition module 320 is specifically used to determine the vehicle operating state when it is determined that the vehicle-mounted voice data to be denoised is a target waveform; when it is determined that the vehicle operating state is the target vehicle operating state, turn on the external vehicle microphone; and obtain the external vehicle environment audio data through the external vehicle microphone.

[0083] Optionally, the target vehicle voice data acquisition module 320 is specifically used to obtain an audio resolution interval; based on the external vehicle environment audio data within the audio resolution interval and the vehicle voice data to be denoised, the vehicle voice data to be denoised is subjected to denoising processing again to obtain the target vehicle voice data.

[0084] Optionally, the target vehicle voice data acquisition module 320 is specifically used to determine the target external vehicle environment audio data and the target vehicle voice data to be denoised according to the current time and the audio resolution interval; determine the differential calculation result between the target external vehicle environment audio data and the target vehicle voice data to be denoised; and determine the target vehicle voice data based on the differential calculation result.

[0085] Optionally, the target vehicle voice data acquisition module 320 is specifically used to determine the first audio resolution differential interval and the second audio resolution differential interval according to the audio resolution interval; use the external vehicle environment audio data within the first audio resolution differential interval before the current moment as the target external vehicle environment audio data; and use the vehicle voice data to be denoised within the second audio resolution differential interval after the current moment as the target vehicle voice data to be denoised.

[0086] Optionally, the target vehicle voice data acquisition module 320 is specifically used to determine the first audio resolution differential interval and the second audio resolution differential interval according to the audio resolution interval; determine the external vehicle environment audio equalization data according to the external vehicle environment audio data within the first audio resolution differential interval before the current moment, and use the external environment audio equalization data as the target external vehicle environment audio data; and use the vehicle voice data to be denoised within the target multiples of the second audio resolution differential interval after the current moment as the target vehicle voice data to be denoised.

[0087] The vehicle exterior environment audio data includes at least one of tire noise audio data, wind noise audio data and engine noise.

[0088] The above-mentioned vehicle-mounted speech noise reduction device can execute the vehicle-mounted speech noise reduction method provided by any embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not fully described in this embodiment, please refer to the vehicle-mounted speech noise reduction method provided by any embodiment of the present invention.

[0089] Since the vehicle-mounted voice noise reduction device introduced above is a device that can execute the vehicle-mounted voice noise reduction method in the embodiment of the present invention, based on the vehicle-mounted voice noise reduction method introduced in the embodiment of the present invention, the technical personnel in this field can understand the specific implementation of the vehicle-mounted voice noise reduction device of this embodiment and its various variations, so how the vehicle-mounted voice noise reduction device implements the vehicle-mounted voice noise reduction method in the embodiment of the present invention is not introduced in detail here. As long as the technical personnel in this field implement the device used by the vehicle-mounted voice noise reduction method in the embodiment of the present invention, it belongs to the scope of protection of this application.

[0090] Embodiment 4

[0091] Figure 8 A schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Figure 8 A block diagram of an electronic device 412 suitable for implementing embodiments of the present invention is shown. Figure 8 The electronic device 412 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0092] like Figure 8 As shown, the electronic device 412 is in the form of a general purpose computing device. The components of the electronic device 412 may include, but are not limited to: one or more processors 416, a storage device 428, and a bus 418 connecting different system components (including the storage device 428 and the processor 416).

[0093] Bus 418 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MCA) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0094] The electronic device 412 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 412, including volatile and non-volatile media, removable and non-removable media.

[0095] The storage device 428 may include computer system readable media in the form of volatile memory, such as RAM (Random Access Memory) 430 and / or cache memory 432. The electronic device 412 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 434 may be used to read and write non-removable, non-volatile magnetic media ( Figure 8 not shown, usually called a "hard drive"). Although Figure 8 Not shown in the figure, a disk drive for reading and writing a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing a removable non-volatile optical disk (e.g., a read-only optical disk (Compact Disc-Read Only Memory, CD-ROM), a digital video disk (Digital Video Disc-Read Only Memory, DVD-ROM) or other optical media) may be provided. In these cases, each drive may be connected to the bus 418 via one or more data medium interfaces. The storage device 428 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0096] A program 436 having a set (at least one) of program modules 426 may be stored, for example, in a storage device 428, such program modules 426 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination thereof may include an implementation of a network environment. Program modules 426 generally perform the functions and / or methods of the embodiments described herein.

[0097] The electronic device 412 may also communicate with one or more external devices 414 (e.g., keyboard, pointing device, camera, display 424, etc.), and may also communicate with one or more devices that enable a user to interact with the electronic device 412, and / or communicate with any device that enables the electronic device 412 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication may be performed through the I / O interface 422. In addition, the electronic device 412 may also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN) and / or public network, such as the Internet) through the network adapter 420. As shown, the network adapter 420 communicates with other modules of the electronic device 412 through the bus 418. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 412, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, disk arrays (Redundant Arrays of Independent Disks, RAID) systems, tape drives, and data backup storage systems.

[0098] The processor 416 executes various functional applications and data processing by running the program stored in the storage device 428, for example, implementing the vehicle-mounted voice noise reduction method provided in the above-mentioned embodiment of the present invention: obtaining vehicle-mounted audio data, and performing initial noise reduction processing on the vehicle-mounted audio data to obtain vehicle-mounted voice data to be noise-reduced; obtaining external environment audio data, and performing noise reduction processing on the vehicle-mounted voice data to be noise-reduced again according to the external environment audio data to obtain target vehicle-mounted voice data; and controlling the vehicle-mounted voice system according to the target vehicle-mounted voice data.

[0099] The technical solution of this embodiment obtains vehicle audio data and performs a primary noise reduction process on the vehicle audio data to obtain vehicle voice data to be noise-reduced, and then obtains the external vehicle environment audio data, and performs a noise reduction process on the vehicle voice data to be noise-reduced again according to the external vehicle environment audio data to obtain the target vehicle voice data, thereby controlling the vehicle voice system according to the target vehicle voice data. By performing a primary noise reduction process on the vehicle audio data, the recognition of the voice in the vehicle voice data to be noise-reduced can be improved, and by using the external vehicle environment audio data to perform a secondary noise reduction process on the vehicle voice data to be noise-reduced, the high-amplitude noise in the vehicle voice data to be noise-reduced can be further filtered out to obtain the target vehicle voice data with the best voice recognition effect, and the target vehicle voice data can be used to accurately control the vehicle voice system, thereby solving the problem of poor noise filtering effect of the existing voice noise reduction scheme, improving the noise filtering effect, accurately identifying the voice in the vehicle environment, and improving the user experience.

[0100] Embodiment 5

[0101] Embodiment 5 of the present invention further provides a computer storage medium storing a computer program, wherein the computer program, when executed by a computer processor, is used to execute the vehicle-mounted voice noise reduction method described in any of the above embodiments of the present invention: obtaining vehicle-mounted audio data, and performing initial noise reduction processing on the vehicle-mounted audio data to obtain vehicle-mounted voice data to be noise reduced; obtaining external vehicle environment audio data, and performing noise reduction processing on the vehicle-mounted voice data to be noise reduced again based on the external vehicle environment audio data to obtain target vehicle-mounted voice data; and controlling the vehicle-mounted voice system based on the target vehicle-mounted voice data.

[0102] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, a device or a device or used in combination with it.

[0103] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0104] The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wire, optical cable, radio frequency (RF), etc., or any suitable combination of the foregoing.

[0105] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0106] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A vehicle-mounted voice noise reduction method, characterized in that: include: Acquiring vehicle audio data, and performing primary noise reduction processing on the vehicle audio data to obtain vehicle voice data to be subjected to noise reduction; Acquire the external vehicle environment audio data, and perform noise reduction processing on the vehicle voice data to be denoised again according to the external vehicle environment audio data to obtain the target vehicle voice data; Controlling the vehicle voice system according to the target vehicle voice data; According to the vehicle external environment audio data, the vehicle voice data to be denoised is subjected to denoising again to obtain target vehicle voice data, including: Get the audio resolution interval; Determine the target vehicle external environment audio data and the target vehicle voice data to be de-noised according to the current time and the audio resolution interval; Determine a difference calculation result between the target external vehicle environment audio data and the target vehicle-mounted voice data to be de-noised; Determining the target vehicle-mounted voice data according to the difference calculation result; Wherein, according to the current time and the audio resolution interval, determining the target vehicle external environment audio data and the target vehicle voice data to be de-noised includes: Determine a first audio resolution differential interval and a second audio resolution differential interval according to the audio resolution interval; Using the vehicle exterior environment audio data within the first audio resolution difference interval before the current moment as the target vehicle exterior environment audio data; The vehicle-mounted voice data to be denoised within the second audio resolution difference interval after the current moment is used as the target vehicle-mounted voice data to be denoised; or Determine a first audio resolution differential interval and a second audio resolution differential interval according to the audio resolution interval; Determine the exterior environment audio equalization data according to the exterior environment audio data within the first audio resolution difference interval before the current moment, and use the exterior environment audio equalization data as the target exterior environment audio data; The vehicle-mounted voice data to be denoised within a target multiple of the second audio resolution differential interval after the current moment is used as the target vehicle-mounted voice data to be denoised.

2. The method according to claim 1, characterized in that Obtaining audio data from the vehicle's exterior environment, including: When it is determined that the vehicle-mounted voice data to be denoised is a target waveform, determining a vehicle operating state; When it is determined that the vehicle operating state is the target vehicle operating state, turning on the external microphone; The external vehicle environment audio data is obtained through the external vehicle microphone.

3. The method according to claim 2, characterized in that The vehicle exterior environment audio data includes at least one of tire noise audio data, wind noise audio data and engine noise.

4. A vehicle-mounted voice noise reduction device, characterized in that: include: The vehicle voice data module to be subjected to noise reduction is used to obtain vehicle audio data and perform primary noise reduction processing on the vehicle audio data to obtain the vehicle voice data to be subjected to noise reduction; A target vehicle voice data acquisition module is used to acquire the external vehicle environment audio data, and perform noise reduction processing on the vehicle voice data to be denoised again according to the external vehicle environment audio data to obtain the target vehicle voice data; A vehicle voice system control module, used to control the vehicle voice system according to the target vehicle voice data; Wherein, the target vehicle voice data acquisition module is specifically used for: Get the audio resolution interval; Determine the target vehicle external environment audio data and the target vehicle voice data to be de-noised according to the current time and the audio resolution interval; Determine a difference calculation result between the target external vehicle environment audio data and the target vehicle-mounted voice data to be de-noised; Determining the target vehicle-mounted voice data according to the difference calculation result; Wherein, according to the current time and the audio resolution interval, determining the target vehicle external environment audio data and the target vehicle voice data to be de-noised includes: Determine a first audio resolution differential interval and a second audio resolution differential interval according to the audio resolution interval; Using the vehicle exterior environment audio data within the first audio resolution difference interval before the current moment as the target vehicle exterior environment audio data; The vehicle-mounted voice data to be denoised within the second audio resolution difference interval after the current moment is used as the target vehicle-mounted voice data to be denoised; or Determine a first audio resolution differential interval and a second audio resolution differential interval according to the audio resolution interval; Determine the exterior environment audio equalization data according to the exterior environment audio data within the first audio resolution difference interval before the current moment, and use the exterior environment audio equalization data as the target exterior environment audio data; The vehicle-mounted voice data to be denoised within a target multiple of the second audio resolution differential interval after the current moment is used as the target vehicle-mounted voice data to be denoised.

5. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the in-vehicle speech noise reduction method as described in any one of claims 1-3.

6. A computer storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the vehicle-mounted speech noise reduction method as described in any one of claims 1 to 3 is implemented.

Images