Sound signal processing method and device, medium and equipment

Abstract

The invention provides a sound signal processing method and device, a medium and equipment, and the method comprises the steps: obtaining an original voice signal collected in a passenger compartment of a vehicle, the original voice signal being a user voice signal with a noise signal; obtaining a target noise type of the noise signal, and determining a target filtering frequency band corresponding to the target noise type based on a preset first corresponding relation; obtaining the target intensity of the noise signal, and determining a target intensity threshold value corresponding to the target intensity based on a preset second corresponding relation; and filtering a noise signal in the original voice signal based on the target filtering frequency band, and suppressing the noise signal in the original voice signal based on the target intensity threshold to obtain a user voice signal. According to the invention, noise signals in original voice signals can be reduced, the influence of the noise signals on voice recognition is reduced, and the accuracy of voice recognition is improved.

Description

Technical Field

[0001] The present application relates to the field of human-computer interaction technology, and in particular to a sound signal processing method, device, medium and equipment. Background Art

[0002] In the process of human-computer interaction, voice control is a common voice control method. Users can issue voice signals, and after receiving the voice signals, the machine recognizes the voice signals and performs corresponding functions according to the instructions in the voice signals. However, when the environment where the machine is located is noisy, the original sound signals received by the machine contain a lot of noise, which can easily cause the machine to be unable to recognize the voice signals in the original sound signals. Summary of the invention

[0003] In view of this, the present application provides a sound signal processing method, device, medium and equipment, the main purpose of which is to reduce the impact of noise signals on speech recognition and improve the accuracy of speech recognition during the speech recognition process.

[0004] To achieve the above objectives, the present application discloses, in a first aspect, a sound signal processing method, comprising:

[0005] Acquire an original voice signal collected in a passenger compartment of a vehicle, wherein the original voice signal is a user voice signal with a noise signal;

[0006] Acquire a target noise type of the noise signal, and determine a target filtering frequency band corresponding to the target noise type based on a preset first corresponding relationship;

[0007] Acquire the target strength of the noise signal, and determine a target strength threshold corresponding to the target strength based on a preset second corresponding relationship;

[0008] The noise signal in the original voice signal is filtered based on the target filtering frequency band, and the noise signal in the original voice signal is suppressed based on the target strength threshold to obtain the user voice signal.

[0009] Optionally, the acquiring the target noise type of the noise signal and determining the target filtering frequency band corresponding to the target noise type based on a preset first corresponding relationship includes:

[0010] Converting the original speech signal into original spectrum data;

[0011] Using a noise recognition model, identifying a noise type of at least one noise signal in the original spectrum data;

[0012] A target filtering frequency band corresponding to the target noise type frequency is determined based on a preset first corresponding relationship, and the target noise type is at least one of the noise types.

[0013] Optionally, the acquiring the target strength of the noise signal and determining a target strength threshold corresponding to the target strength based on a preset second corresponding relationship includes:

[0014] Acquire a target intensity change value of the noise signal, where the target intensity change value is used to indicate a change in the target intensity;

[0015] The target intensity threshold corresponding to the target intensity is adjusted based on a preset second corresponding relationship to obtain a dynamic intensity threshold, where the dynamic intensity threshold represents a change in the target intensity threshold, and the dynamic intensity threshold corresponds to the target intensity change value.

[0016] Optionally, the acquiring of the original voice signal collected in the passenger compartment of the vehicle includes:

[0017] Using an onboard microphone array in a passenger compartment of the vehicle to collect a first sound signal in the cabin, the first sound signal being an original voice signal including a media sound played by an onboard speaker;

[0018] Acquiring sound data for playing through the vehicle-mounted speaker;

[0019] The echo cancellation algorithm is used to refer to the sound data to eliminate the media sound in the first sound signal to obtain the original sound signal.

[0020] Optionally, when the user voice signal is used to wake up the in-vehicle voice assistant, filtering the noise signal in the original voice signal based on the target filtering frequency band, and suppressing the noise signal in the original voice signal based on the target intensity threshold, to obtain the user voice signal, includes:

[0021] Obtaining a target filter frequency band change value and a target intensity change value of the noise signal during the vehicle voice assistant wake-up period, wherein the target filter frequency band change value is used to indicate a change in the target filter frequency band, and the target intensity change value is used to indicate a change in the target intensity;

[0022] The noise signal in the original voice signal is filtered based on the target filtering frequency band change value, and the noise signal in the original voice signal is suppressed based on the target intensity change value to obtain the user voice signal.

[0023] Optionally, when the user voice signal is used to wake up an in-vehicle voice assistant, the method further includes:

[0024] Adjust the wake-up sensitivity of the in-vehicle voice assistant according to the target strength of the noise signal.

[0025] Optionally, after filtering the noise signal in the original voice signal based on the target filtering frequency band and suppressing the noise signal in the original voice signal based on the target strength threshold to obtain the user voice signal, the method further includes:

[0026] Determine the human voice frequency interval to which the user voice signal belongs;

[0027] The user voice signal in the human voice frequency interval is enhanced to obtain the enhanced user voice signal.

[0028] The second aspect of the present application discloses a sound signal processing device, comprising:

[0029] An acquisition module, used to acquire an original voice signal collected in a passenger compartment of a vehicle, wherein the original voice signal is a user voice signal with a noise signal;

[0030] A first determination module, configured to obtain a target noise type of the noise signal, and determine a target filtering frequency band corresponding to the target noise type based on a preset first corresponding relationship;

[0031] A second determination module is used to obtain the target strength of the noise signal and determine a target strength threshold corresponding to the target strength based on a preset second corresponding relationship;

[0032] A processing module is used to filter the noise signal in the original voice signal based on the target filtering frequency band, and suppress the noise signal in the original voice signal based on the target intensity threshold to obtain the user voice signal.

[0033] In a third aspect of the present application, an electronic device is provided, including:

[0034] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any one of the methods disclosed in the first aspect.

[0035] In a fourth aspect of the present application, an embodiment provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method of the first aspect is implemented.

[0036] In a fifth aspect embodiment of the present application, a vehicle is provided, in which the device as described in the second aspect or the electronic device as described in the third aspect is mounted.

[0037] In summary, according to the technical solution disclosed in the present application, the original voice signal contains a noise signal, which easily causes the machine to be unable to recognize the voice signal in the original sound signal. The present application provides a sound signal processing method, firstly obtaining the original voice signal collected in the passenger compartment of the vehicle, the original voice signal is a user voice signal with a noise signal; then obtaining the target noise type of the noise signal, and determining the target filter frequency band corresponding to the target noise type based on a preset first corresponding relationship; then obtaining the target intensity of the noise signal, and determining the target intensity threshold corresponding to the target intensity based on a preset second corresponding relationship; finally filtering the noise signal in the original voice signal based on the target filter frequency band, and suppressing the noise signal in the original voice signal based on the target intensity threshold, to obtain the user voice signal. In the technical solution of the present application, the original voice signal is collected in the passenger compartment of the vehicle. When the original voice signal contains a noise signal, in order to separate the user voice signal from the original voice signal. The present application can determine the target noise type and target intensity of the noise signal. The target filter frequency band corresponding to the target noise type is determined by the preset first corresponding relationship, and the target intensity threshold corresponding to the target intensity value is determined by the preset second corresponding relationship. The noise signal of the target filtering frequency in the original speech signal is filtered. At the same time, the noise signal in the original speech signal is suppressed with the target intensity threshold, thereby reducing the noise signal in the original speech signal, reducing the impact of the noise signal on speech recognition, and improving the accuracy of speech recognition.

[0038] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0041] Figure 1A flow chart of a sound signal processing method provided by an embodiment of the present application is shown;

[0042] Figure 2 A structural diagram of a sound signal processing device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0043] In order to better understand the technical solutions provided by the embodiments of this specification, the technical solutions of the embodiments of this specification are described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of this specification and the specific features in the embodiments are detailed descriptions of the technical solutions of the embodiments of this specification, rather than limitations on the technical solutions of this specification. In the absence of conflict, the embodiments of this specification and the technical features in the embodiments can be combined with each other.

[0044] In this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment 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, method, article or equipment. In the absence of more restrictions, the elements limited by the statement "comprise one..." do not exclude the existence of other identical elements in the process, method, article or equipment including the elements. The term "more than two" includes two or more than two situations.

[0045] In the process of human-computer interaction recognition, users can issue control instructions in the form of voice signals. The machine can receive the voice signals, identify the control instructions from the voice signals, and perform corresponding functions according to the control instructions. For example, when waking up the machine, the user can say the corresponding wake-up word, and the said wake-up word is received by the machine in the form of a voice signal. The machine extracts the wake-up word from the voice signal and compares the wake-up word with the preset wake-up word. If the comparison is successful, the machine can be awakened. However, if the noise signal in the voice signal received by the machine is relatively strong, it is difficult for the machine to extract the wake-up word from the voice signal, and the probability of the machine waking up is reduced, which seriously affects the user experience.

[0046] To solve the above problems, this embodiment provides a sound signal processing method, which can be executed in the control system of the vehicle computer. Figure 1 As shown, including:

[0047] Step 101 , obtaining an original voice signal collected in a passenger compartment of a vehicle, where the original voice signal is a user voice signal with a noise signal.

[0048] The passenger compartment of a vehicle refers to the space inside the vehicle, that is, the area where the passengers and the driver are located. In the process of collecting the original voice signal, the sound signal in the passenger compartment can be collected through a microphone or other audio equipment in the passenger compartment. In the collected original voice signal, in addition to the user voice signal that needs to be further recognized, it also includes a noise signal, which will interfere with the recognition of the user voice signal. In general, the signals in the original voice signal except the user voice signal can be used as noise signals. Among them, the noise signal in the original voice signal can be environmental noise: for example, the sound of wind when the vehicle is driving, the friction sound of the tires and the ground, the noise of other vehicles, etc. Mechanical noise: for example, the roar of the engine, the running sound of the air conditioning system, etc. Electronic equipment noise: for example, the noise emitted by electronic equipment such as the car audio system and mobile phones.

[0049] In some embodiments, the specific process of collecting the original voice signal may be:

[0050] A first sound signal in the cabin is collected by using an on-board microphone array in the passenger compartment of the vehicle, where the first sound signal is an original voice signal including media sound played by the on-board speaker; sound data for playing through the on-board speaker is obtained; and an echo cancellation algorithm is used to eliminate the media sound in the first sound signal with reference to the sound data to obtain the original sound signal.

[0051] An array of multiple microphones installed inside the vehicle is used to capture the sounds inside the cabin. The first sound signal collected by the vehicle microphone array includes all the sounds inside the cabin. While riding, passengers may listen to media sounds, such as navigation sounds, music, etc., through the vehicle speakers. In this process, the first sound signal includes the media sounds played by the vehicle speakers. The media sounds played in the vehicle are generated based on sound data. Sound data is the specific content played by the vehicle speakers, such as music files, audio files of navigation prompts, etc. The vehicle speakers play the media sounds by reading the music data. These sound data are extracted or recorded from the system for subsequent processing.

[0052] The echo cancellation algorithm is a signal processing technology used to remove echoes and interference signals. In this embodiment, it is used to eliminate the media sound played by the vehicle-mounted speaker in the first sound signal. The sound data obtained from the system is used as a reference signal. The media sound portion of the first sound signal is removed by the echo cancellation algorithm, and the final signal contains only the user's voice, removing the media sound played by the vehicle-mounted speaker. Exemplarily, when the vehicle-mounted system plays navigation instructions and background music, the driver issues a voice wake-up command. The system filters out the navigation sound and music signals through a preset echo cancellation algorithm to ensure that the driver's voice commands can be accurately recognized.

[0053] The system using the technical solution of this embodiment can eliminate the media sound from the first sound signal obtained by the microphone when the passengers listen to the media sound through the vehicle's speakers, reduce the recognition of the user's voice signal by the media sound, and can more accurately recognize and process the user's voice, thereby improving the quality of voice recognition.

[0054] In some embodiments, during the training process of the echo cancellation algorithm, the training data used to train the algorithm may include different media volumes, so that the echo cancellation algorithm generated by the training can eliminate media sounds of different volumes. In addition, the training data used to train the algorithm can also include different vehicle noises, such as engine noise, and a mixture of engine noise and air conditioning noise. The vehicle noise can correspond to different driving speeds of the vehicle, so that the echo cancellation algorithm generated by the training can eliminate the noise generated by the vehicle at different driving speeds. Exemplarily, the echo cancellation algorithm can be adjusted in real time according to changes in vehicle speed and volume to ensure that the acoustic echo can be effectively resisted even when driving at high speeds.

[0055] Step 102: Acquire a target noise type of the noise signal, and determine a target filtering frequency band corresponding to the target noise type based on a preset first corresponding relationship.

[0056] Different noise types may have different frequency characteristics and manifestations. The target noise type may be, for example: wind noise: the sound of wind when the vehicle is driving. Mechanical noise: the operating sound of equipment such as engines and air conditioners. Environmental noise: the sound of other vehicles on the road, the sound of pedestrians talking, etc. After receiving the original voice signal, the noise type can be determined, and the determined noise type is the target noise type of the noise signal. After determining the target noise type of the noise signal, the distribution frequency band of the noise signal can be determined as the target filtering frequency band of the noise signal. The preset first corresponding relationship is a preset mapping table or rule, which defines the relationship between different types of noise and their corresponding filtering frequency bands. By determining the target filtering frequency band, the distribution position of the noise signal in the original voice signal can be determined in detail. For example, if the target noise type is wind noise, the preset first corresponding relationship can indicate that the wind noise is mainly concentrated in the low frequency band (for example, below 200Hz), then the target filtering frequency band is the frequency band below 200Hz. If the target noise type is mechanical noise, the preset first correspondence may indicate that the mechanical noise is mainly concentrated in a mid-frequency band (eg, 500 Hz to 2000 Hz), and the target filtering frequency band is a frequency band from 500 Hz to 2000 Hz.

[0057] In some embodiments, the process of determining the target filtering frequency band may be:

[0058] Convert an original speech signal into original spectrum data; use a noise recognition model to identify at least one noise type of a noise signal in the original spectrum data; determine a target filtering frequency band corresponding to a target noise type frequency based on a preset first corresponding relationship, wherein the target noise type is at least one of the noise types.

[0059] Spectral data refers to the intensity information of each frequency component obtained by performing spectral analysis on the original speech signal and converting it from the time domain to the frequency domain. Common spectral analysis methods include Fourier transform. The original speech signal is converted into spectral data using a spectral analysis method (such as Fourier transform). In this way, the distribution of the signal at different frequencies can be more intuitively seen. Through the noise recognition model, the distribution of the signal at different frequencies is identified, and at least one type of noise signal is identified from the original spectral data. For example, the model may identify wind noise, mechanical noise, environmental noise, etc. Exemplarily, the identification of noise types can also be further combined with actual driving scenarios. For example, when the vehicle is detected to be driving at high speed, the detected noise is mainly high-frequency wind noise and medium- and low-frequency road noise. After the frequency band characteristics of these noises are detected in the spectral data, the target noise types are automatically identified as "high-speed driving wind noise" and "road noise". When it is detected that the vehicle is driving on an urban road, the noise mainly comes from engine noise and external environmental noise, such as the sound of other vehicles around the vehicle.

[0060] Step 103: Acquire the target strength of the noise signal, and determine a target strength threshold corresponding to the target strength based on a preset second corresponding relationship.

[0061] The target intensity represents the intensity value of the noise signal, and the intensity value of the noise can be measured by a sound pressure meter. The preset second correspondence is a predefined mapping relationship between the target intensity of a noise signal and the target intensity threshold. This correspondence is usually a function or a table, which can be set according to different application scenarios. The target intensity threshold is used to determine whether the intensity of the noise signal has reached the standard that requires certain measures to be taken. Exemplarily, the target intensity threshold can be a level value, that is, the target intensity threshold can represent the intensity level of the noise signal. For example, the target intensity threshold can be divided into levels 1 to 7. The greater the target intensity of the noise signal, the higher the target intensity threshold corresponding to the target intensity. According to the preset second correspondence, find the target intensity threshold corresponding to the current noise signal target intensity. For example, if the target intensity of the noise signal is 100dB, the preset second correspondence may stipulate that the threshold corresponding to 100dB is 2.

[0062] By determining the target strength threshold corresponding to the target strength of the noise signal, the system can better accurately divide the noise signal according to the noise strength, and execute different measures according to the noise signals with different target strength thresholds.

[0063] In some embodiments, obtaining the target strength of the noise signal and determining the target strength threshold corresponding to the target strength based on a preset second corresponding relationship specifically include:

[0064] Obtain a target intensity change value of the noise signal, the target intensity change value is used to indicate the change of the target intensity; adjust the target intensity threshold corresponding to the target intensity based on a preset second corresponding relationship, and obtain a dynamic intensity threshold, the dynamic intensity threshold indicates the change of the target intensity threshold, and the dynamic intensity threshold corresponds to the target intensity change value.

[0065] Since the target intensity represents the intensity or energy level of the noise signal, the target intensity change value is used to represent the change of the intensity of the noise signal over time. For example, the intensity of the noise signal may increase or decrease within a certain period of time. The target intensity change value can be a numerical value, indicating the degree of change of the noise intensity. There is a preset second corresponding relationship between the target intensity of the noise signal and the target intensity threshold. On this basis, the preset second corresponding relationship can be used to determine the dynamic intensity threshold corresponding to the target intensity change value, and the dynamic intensity threshold represents the change of the target intensity threshold over time. The dynamic intensity threshold will be adjusted in real time according to the change of the intensity of the noise signal. According to the adjusted target intensity threshold, the dynamic intensity threshold that changes with time is obtained, so that the change of the noise signal intensity can be determined in time, and noise signals of different intensities can be flexibly responded to. In this way, the system can more effectively adapt to changes in the noise environment and improve the robustness and accuracy of speech signal processing.

[0066] Step 104: filter the noise signal in the original voice signal based on the target filtering frequency band, and suppress the noise signal in the original voice signal based on the target intensity threshold to obtain the user voice signal.

[0067] The target filtering frequency band is the frequency range where the noise signal is located. After determining the target filtering frequency band where the noise signal is located, the original voice signal of the target filtering frequency band can be directly filtered to speed up the filtering speed of the noise signal. For example, if the noise signal is mainly concentrated in the frequency band of 1000Hz to 2000Hz, a filter can be used to filter the signal in this frequency band. Exemplarily, when filtering the noise signal, a suitable filtering strategy can be selected according to the target noise type of the noise, such as filtering specific frequency bands for different noise types (wind noise, engine noise, road noise, etc.).

[0068] High-frequency filtering: Mainly for wind noise, the system weakens or filters sounds that exceed a specific frequency.

[0069] Low-frequency filtering: For engine noise or tire friction, the system reduces low-frequency noise and retains mid- and high-frequency voice signals.

[0070] In addition to noise filtering, technical means can also be used to reduce or eliminate noise signals that exceed the target intensity threshold. If the target intensity of the noise signal exceeds the target intensity threshold, measures are taken to suppress or eliminate these noise signals. Common suppression methods include:

[0071] 1. Dynamic range compression: Reduce the dynamic range of the noise signal to reduce its intensity.

[0072] 2. Noise Threshold: When the intensity of the noise signal exceeds the threshold, it will be completely or partially cut off.

[0073] 3. Adaptive filtering: Use adaptive filters to dynamically adjust the filtering parameters according to the changes in the noise signal to more effectively suppress noise.

[0074] After filtering and suppression processing, a clear user voice signal is extracted from the original voice signal for subsequent processing or playback.

[0075] In some embodiments, the process of processing the noise signal in the original speech signal includes:

[0076] The target filter frequency band change value and target intensity change value of the noise signal are obtained during the wake-up period of the in-vehicle voice assistant. The target filter frequency band change value is used to indicate the change of the target filter frequency band, and the target intensity change value is used to indicate the change of the target intensity. The noise signal in the original voice signal is filtered based on the target filter frequency band change value, and the noise signal in the original voice signal is suppressed based on the target intensity change value to obtain the user voice signal.

[0077] This embodiment proposes a specific application scenario. The user voice signal generated by the sound signal processing method of this embodiment can be used to wake up the in-vehicle voice assistant. The time period when the in-vehicle voice assistant is activated or awakened represents the in-vehicle voice assistant awakening time period. It is usually a period of time after the in-vehicle voice assistant recognizes the user's wake-up word.

[0078] After the in-vehicle voice assistant is awakened, the in-vehicle voice assistant can wait for further instructions from the occupant. During this process, the target noise type and target intensity of the noise signal in the received original voice signal may change. For example, the main frequency band of the noise signal may change from the low frequency band to the high frequency band. For example, the intensity of the noise signal may increase first and then decrease. The target filter frequency band change value indicates the change of the frequency band. The target intensity change value indicates the change of the target intensity.

[0079] According to the change of the target filtering frequency band, the present embodiment can dynamically adjust the parameters of the filter so that it can effectively remove the changing noise frequency band. For example, if the main frequency band of the noise signal changes from the low frequency band to the high frequency band, the filter will be adjusted accordingly so that the noise frequency filtered by the filter changes from the low frequency band to the high frequency band.

[0080] The intensity of noise suppression is dynamically adjusted according to the changes in the target intensity. For example, if the intensity of the noise signal increases first and then decreases, the noise suppression algorithm will adjust accordingly, first increasing the suppression intensity and then gradually decreasing it. After dynamic filtering and suppression processing, the user voice signal can be extracted from the original voice signal in a certain period of time, and the noise has been effectively removed or reduced.

[0081] In this embodiment, the original voice signal is collected in the passenger compartment of the vehicle. When the original voice signal contains a noise signal, in order to separate the user voice signal from the original voice signal. The present application can determine the target noise type and target intensity of the noise signal. The target filter frequency band corresponding to the target noise type is determined by a preset first corresponding relationship, and the target intensity threshold corresponding to the target intensity value is determined by a preset second corresponding relationship. The noise signal of the target filter frequency in the original voice signal is filtered, and at the same time, the noise signal in the original voice signal is suppressed by the target intensity threshold, thereby reducing the noise signal in the original voice signal, reducing the influence of the noise signal on voice recognition, and improving the accuracy of voice recognition.

[0082] In some embodiments, the sound signal processing method further includes: adjusting the wake-up sensitivity of the in-vehicle voice assistant according to the target intensity of the noise signal.

[0083] Wake-up sensitivity refers to the sensitivity of the in-vehicle voice assistant to the wake-up word. High wake-up sensitivity means that the system is easier to wake up, while low sensitivity means that the system is more difficult to wake up. In order to adapt the sensitivity to the noise intensity, if the intensity of the noise signal is high, the system will increase the wake-up sensitivity. This can reduce the risk of missed wake-ups. If the intensity of the noise signal is low, the system will increase the sensitivity, thereby reducing missed wake-ups and improving the user experience. Exemplary, high noise environment: For example, when driving on a highway, the noise inside and outside the vehicle is large. At this time, the system will increase the wake-up sensitivity so that the voice assistant can more sensitively obtain the user's voice signal. Low noise environment: For example, in a parking lot or in a stationary car, the noise is small. At this time, the system will reduce the wake-up sensitivity and reduce the risk of false wake-ups. On the basis of being able to wake up the in-vehicle voice assistant in different noise environments, it not only reduces misoperation but also improves the user experience.

[0084] In some embodiments, it is also possible to: determine the human voice frequency interval to which the user voice signal belongs; and perform signal enhancement on the user voice signal in the human voice frequency interval to obtain an enhanced user voice signal.

[0085] Human voice frequency range: The frequency range of human voice is usually between 80Hz and 14,000Hz, but most useful voice information is concentrated between 300Hz and 3,400Hz. This range is called the human voice frequency range. By analyzing the spectrum of the user's voice signal, the human voice frequency range where the user's voice signal is mainly concentrated is determined.

[0086] After determining the human voice frequency interval to which the user voice signal belongs, the signal within this interval is enhanced.

[0087] The signal enhancement method includes: gain adjustment: increasing the signal strength within the frequency band. After the signal enhancement process, a clearer and higher-quality user voice signal is obtained. In the process of signal enhancement, in order to adapt to the change in the signal strength of the noise signal, the present embodiment can also adjust the gain of the user voice signal according to the change in the ambient noise. When the noise intensity is large, the gain of the voice signal is increased to improve the signal-to-noise ratio; when the noise intensity is small, the gain is appropriately reduced to avoid distortion caused by excessive volume.

[0088] In this way, the system can effectively improve the quality of user voice signals, improve the accuracy of voice recognition and the user experience.

[0089] In some embodiments, the sound signal processing method may further:

[0090] Obtain user feedback on false or missed wake-ups, such as false wake-ups and missed wake-ups. Adjust the filtering strategy and noise signal suppression strategy, as well as the sensitivity, based on these feedbacks. Use machine learning methods to train models based on long-term noise data to optimize filtering strategies and wake-up recognition models in different noise environments.

[0091] After the system collects enough user feedback and noise signals under different target noise types, it gradually optimizes its noise filtering and sensitivity adjustment strategies so that the system can better adapt to personal driving habits and environmental changes over time.

[0092] This embodiment provides a structure diagram of a sound signal processing device, such as Figure 2 As shown, including:

[0093] An acquisition module 21 is used to acquire an original voice signal collected in the passenger compartment of the vehicle, wherein the original voice signal is a user voice signal with a noise signal;

[0094] A first determination module 22, configured to obtain a target noise type of the noise signal, and determine a target filtering frequency band corresponding to the target noise type based on a preset first corresponding relationship;

[0095] A second determination module 23 is used to obtain the target strength of the noise signal and determine a target strength threshold corresponding to the target strength based on a preset second corresponding relationship;

[0096] The processing module 24 is used to filter the noise signal in the original voice signal based on the target filtering frequency band, and suppress the noise signal in the original voice signal based on the target intensity threshold to obtain the user voice signal.

[0097] In some embodiments, the first determining module 22 is configured to:

[0098] Converting the original speech signal into original spectrum data;

[0099] Using a noise recognition model, identifying a noise type of at least one noise signal in the original spectrum data;

[0100] A target filtering frequency band corresponding to the target noise type frequency is determined based on a preset first corresponding relationship, and the target noise type is at least one of the noise types.

[0101] In some embodiments, the second determining module 23 is configured to:

[0102] Acquire a target intensity change value of the noise signal, where the target intensity change value is used to indicate a change in the target intensity;

[0103] The target intensity threshold corresponding to the target intensity is adjusted based on a preset second corresponding relationship to obtain a dynamic intensity threshold, where the dynamic intensity threshold represents a change in the target intensity threshold, and the dynamic intensity threshold corresponds to the target intensity change value.

[0104] In some embodiments, the acquisition module 21 is used to:

[0105] Using an onboard microphone array in a passenger compartment of the vehicle to collect a first sound signal in the cabin, the first sound signal being an original voice signal including a media sound played by an onboard speaker;

[0106] Acquiring sound data for playing through the vehicle-mounted speaker;

[0107] The echo cancellation algorithm is used to refer to the sound data to eliminate the media sound in the first sound signal to obtain the original sound signal.

[0108] In some embodiments, the processing module 24 is configured to:

[0109] Obtaining a target filter frequency band change value and a target intensity change value of the noise signal during the vehicle voice assistant wake-up period, wherein the target filter frequency band change value is used to indicate a change in the target filter frequency band, and the target intensity change value is used to indicate a change in the target intensity;

[0110] The noise signal in the original voice signal is filtered based on the target filtering frequency band change value, and the noise signal in the original voice signal is suppressed based on the target intensity change value to obtain the user voice signal.

[0111] In some embodiments, the sound signal processing device further includes: an adjustment module 25, which is used to:

[0112] Adjust the wake-up sensitivity of the in-vehicle voice assistant according to the target strength of the noise signal.

[0113] In some embodiments, the sound signal processing device further includes: an enhancement module 26, which is used to:

[0114] Determine the human voice frequency interval to which the user voice signal belongs;

[0115] The user voice signal in the human voice frequency interval is enhanced to obtain the enhanced user voice signal.

[0116] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0117] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-readable program code.

[0118] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0119] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0120] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0121] An embodiment of the present application further provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device executes the process of the sound signal processing method.

[0122] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integration. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)), etc.

[0123] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0124] In the several embodiments provided in the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0125] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0126] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0127] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0128] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

[0129] Although preferred embodiments of the present specification have been described, additional changes and modifications may be made to these embodiments by those skilled in the art once the basic inventive concepts are known. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present specification. Obviously, those skilled in the art may make various changes and modifications to the present specification without departing from the spirit and scope of the present specification. Thus, if these modifications and variations of the present specification fall within the scope of the claims of the present specification and their equivalents, the present specification is also intended to include these modifications and variations.

Claims

1. A sound signal processing method, characterized in that: include: Acquire an original voice signal collected in a passenger compartment of a vehicle, wherein the original voice signal is a user voice signal with a noise signal; Acquire a target noise type of the noise signal, and determine a target filtering frequency band corresponding to the target noise type based on a preset first corresponding relationship; Acquire the target strength of the noise signal, and determine a target strength threshold corresponding to the target strength based on a preset second corresponding relationship; The noise signal in the original voice signal is filtered based on the target filtering frequency band, and the noise signal in the original voice signal is suppressed based on the target strength threshold to obtain the user voice signal.

2. The method according to claim 1, characterized in that The step of acquiring a target noise type of the noise signal and determining a target filtering frequency band corresponding to the target noise type based on a preset first corresponding relationship includes: Converting the original speech signal into original spectrum data; Using a noise recognition model, identifying a noise type of at least one noise signal in the original spectrum data; A target filtering frequency band corresponding to the target noise type frequency is determined based on a preset first corresponding relationship, and the target noise type is at least one of the noise types.

3. The method according to claim 1, characterized in that The acquiring the target strength of the noise signal and determining the target strength threshold corresponding to the target strength based on a preset second corresponding relationship includes: Acquire a target intensity change value of the noise signal, where the target intensity change value is used to indicate a change in the target intensity; The target intensity threshold corresponding to the target intensity is adjusted based on a preset second corresponding relationship to obtain a dynamic intensity threshold, where the dynamic intensity threshold represents a change in the target intensity threshold, and the dynamic intensity threshold corresponds to the target intensity change value.

4. The method according to claim 1, characterized in that: The obtaining of the original voice signal collected in the passenger compartment of the vehicle includes: Using an onboard microphone array in a passenger compartment of the vehicle to collect a first sound signal in the cabin, the first sound signal being an original voice signal including a media sound played by an onboard speaker; Acquiring sound data for playing through the vehicle-mounted speaker; The echo cancellation algorithm is used to refer to the sound data to eliminate the media sound in the first sound signal to obtain the original sound signal.

5. The method according to claim 1, characterized in that When the user voice signal is used to wake up the in-vehicle voice assistant, filtering the noise signal in the original voice signal based on the target filtering frequency band, and suppressing the noise signal in the original voice signal based on the target intensity threshold to obtain the user voice signal, includes: Obtaining a target filter frequency band change value and a target intensity change value of the noise signal during the vehicle voice assistant wake-up period, wherein the target filter frequency band change value is used to indicate a change in the target filter frequency band, and the target intensity change value is used to indicate a change in the target intensity; The noise signal in the original voice signal is filtered based on the target filtering frequency band change value, and the noise signal in the original voice signal is suppressed based on the target intensity change value to obtain the user voice signal.

6. The method according to claim 5, characterized in that When the user voice signal is used to wake up the in-vehicle voice assistant, the method further includes: Adjust the wake-up sensitivity of the in-vehicle voice assistant according to the target strength of the noise signal.

7. The method according to claim 1, characterized in that After filtering the noise signal in the original voice signal based on the target filtering frequency band and suppressing the noise signal in the original voice signal based on the target strength threshold to obtain the user voice signal, the method further includes: Determine the human voice frequency interval to which the user voice signal belongs; The user voice signal in the human voice frequency interval is enhanced to obtain the enhanced user voice signal.

8. A sound signal processing device, characterized in that: include: An acquisition module, used to acquire an original voice signal collected in a passenger compartment of a vehicle, wherein the original voice signal is a user voice signal with a noise signal; A first determination module, configured to obtain a target noise type of the noise signal, and determine a target filtering frequency band corresponding to the target noise type based on a preset first corresponding relationship; A second determination module is used to obtain the target strength of the noise signal and determine a target strength threshold corresponding to the target strength based on a preset second corresponding relationship; A processing module is used to filter the noise signal in the original voice signal based on the target filtering frequency band, and suppress the noise signal in the original voice signal based on the target intensity threshold to obtain the user voice signal.

9. An electronic device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1 to 7.

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

Images