Method for reducing noise of in-vehicle voice

Abstract

This invention provides a method for noise reduction of in-vehicle voice signals, belonging to the field of noise processing technology. The method includes: performing spectral analysis on the collected in-vehicle environmental audio signal based on vehicle status signals, and outputting the spectral analysis results; the spectral analysis results include the filtering frequency bands that require filter activation; activating the filters of the filtering frequency bands according to the spectral analysis results to filter the in-vehicle environmental audio signal, obtaining a filtered signal; detecting and dividing the filtered signal into user voice segments and noise segments; and adjusting the amplitude of the filtered signal according to the user voice segments and noise segments to obtain a noise-reduced signal. This invention improves the noise reduction effect by specifically filtering and adjusting the collected audio signal, thereby improving the accuracy of subsequent speech recognition.

Description

Technical Field

[0001] This invention relates to the field of noise processing technology, and in particular to a method for noise reduction of in-vehicle voice. Background Technology

[0002] With the development of intelligent vehicle technology, in-vehicle voice interaction has become the core way for users to control vehicle functions. However, the complex noise environment inside the vehicle, such as engine vibration noise, air conditioning noise, tire noise, and wind noise, seriously affects the accuracy of voice recognition, leading to misrecognition of commands or response delays, and reducing the user experience. Summary of the Invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art, and proposes a noise reduction method for in-vehicle voice with targeted filtering and adjustment.

[0004] In a first aspect, embodiments of the present invention provide a method for noise reduction of in-vehicle voice, comprising: performing spectrum analysis on the collected in-vehicle environmental audio signal based on vehicle status signals, and outputting spectrum analysis results; the spectrum analysis results include the filtering frequency bands for which filters need to be activated; activating the filters of the filtering frequency bands based on the spectrum analysis results to filter the in-vehicle environmental audio signal, thereby obtaining a filtered signal; detecting the filtered signal to divide it into user voice segments and noise segments, and adjusting the amplitude of the filtered signal based on the user voice segments and noise segments to obtain a noise-reduced signal.

[0005] According to an embodiment of the present invention, spectral analysis is performed on the collected in-vehicle ambient audio signal based on the vehicle status signal, and the spectral analysis result is output. This includes: performing a fast Fourier transform on the in-vehicle ambient audio signal to obtain spectral information; associating noise correlation parameters in the vehicle status signal with corresponding preset frequency bands; the noise correlation parameters include at least one of engine speed, air conditioning fan speed, and vehicle speed parameters; in response to a noise correlation parameter being greater than a first preset threshold, marking the corresponding preset frequency band as a filtered frequency band; and in response to the spectral information having frequency bands with amplitudes greater than a second preset threshold in a preset number of consecutive frames, marking the frequency bands greater than the second preset threshold as filtered frequency bands.

[0006] According to an embodiment of the present invention, a filter of the filtering frequency band is activated to filter the in-vehicle ambient audio signal based on the spectrum analysis results to obtain a filtered signal. The method includes: selecting a filter to be activated based on the spectrum analysis results; the filter includes at least a low-pass filter and a high-pass filter; adjusting the step size of the filter according to the filtering frequency band to filter the in-vehicle ambient audio signal to obtain a filtered signal.

[0007] According to an embodiment of the present invention, after obtaining the filtered signal, the method further includes a step of echo cancellation of the filtered signal, specifically including: estimating the echo path based on the vehicle speaker audio signal and the filtered signal; and canceling the echo of the filtered signal using a filter based on the echo path.

[0008] According to an embodiment of the present invention, detecting the division of the filtered signal into user speech segments and noise segments includes: calculating the zero-crossing rate and spectral entropy of each frame of filtered signal; determining whether the current frame of filtered signal meets the speech conditions; the speech conditions are greater than a preset amplitude threshold, zero-crossing rate lower than a preset zero-crossing threshold, and spectral entropy lower than a preset entropy threshold; if yes, then the current frame of filtered signal is taken as a candidate speech segment; if no, then the current frame of filtered signal is taken as a noise segment; for each filtered signal in the candidate speech segment, determining whether there is an adjacent filtered signal; if yes, then the filtered signal is taken as a speech segment; if no, then the filtered signal is taken as a noise segment.

[0009] According to an embodiment of the present invention, adjusting the amplitude of the filtered signal to obtain a noise-reduced signal based on the user's voice segment and the noise segment includes: initiating a gain boost operation in response to the presence of a voice segment; and initiating a gain attenuation operation in response to the presence of a noise segment or the detection of a sudden high level.

[0010] According to an embodiment of the present invention, the method further includes: adjusting the parameters of the filter and speech segment detection for special environments, specifically including: reducing the fast Fourier transform frequency and enhancing the low-frequency filtering intensity in response to the temperature and humidity being higher than a first temperature threshold and a humidity threshold; and reducing the preset amplitude threshold for determining the speech segment in response to the temperature being lower than a second temperature threshold.

[0011] Secondly, the present invention provides a vehicle-mounted voice noise reduction system, which can be used to implement the above-mentioned vehicle-mounted voice noise reduction method, comprising: an analysis module, used to perform spectrum analysis on the collected in-vehicle environmental audio signal based on the vehicle status signal, and output spectrum analysis results; the spectrum analysis results include the filtering frequency bands that need to be activated by the filter; a filtering module, used to activate the filter of the filtering frequency band according to the spectrum analysis results to filter the in-vehicle environmental audio signal, and obtain a filtered signal; and an adjustment module, used to detect the filtering signal to divide it into user voice segments and noise segments, and adjust the amplitude of the filtering signal according to the user voice segments and noise segments to obtain a noise-reduced signal.

[0012] A third aspect of the present invention provides an electronic device comprising: one or more processors; and a memory for storing one or more programs, wherein, when the one or more programs are executed by the one or more processors, the one or more processors perform the above-described noise reduction method for in-vehicle voice.

[0013] A fourth aspect of the present invention also provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the above-described noise reduction method for in-vehicle voice.

[0014] The noise reduction method for in-vehicle voice provided by this invention performs spectrum analysis on the collected in-vehicle environmental audio signal based on the vehicle status signal and dynamically activates the filter. By integrating vehicle CAN bus data and real-time audio spectrum, it solves the technical problems of large delay and insufficient targeting of traditional noise reduction solutions for in-vehicle dynamic noise suppression, thereby improving the noise reduction effect and voice recognition accuracy. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating a method for noise reduction of in-vehicle voice according to an embodiment of the present invention.

[0016] Figure 2 This is a block diagram illustrating the filtering application of the method provided in the embodiments of the present invention;

[0017] Figure 3 This is a timing diagram of the echo cancellation method provided in the embodiments of the present invention;

[0018] Figure 4 This is a block diagram of the dynamic gain of the method provided in the embodiments of the present invention;

[0019] Figure 5 This is a schematic diagram of the microphone layout for the method provided in the embodiments of the present invention;

[0020] Figure 6 This is a structural block diagram of an in-vehicle voice noise reduction system provided in an embodiment of the present invention;

[0021] Figure 7 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0022] To enable those skilled in the art to better understand the technical solutions of the present invention, exemplary embodiments of the present invention are described below in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0023] Where there is no conflict, the various embodiments of the present invention and the features thereof may be combined with each other.

[0024] As used herein, the term “and / or” includes any and all combinations of one or more related enumerated entries.

[0025] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used herein, the singular forms “a” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that when the terms “comprising” and / or “made of” are used in this specification, the presence of the stated feature, integral, step, operation, element, and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof is not excluded. Terms such as “connected” or “linked” are not limited to physical or mechanical connections but can include electrical connections, whether direct or indirect.

[0026] Unless otherwise specified, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having the meaning consistent with their meaning in the context of the relevant art and the invention, and will not be interpreted as having an idealized or overly formal meaning unless expressly so defined herein.

[0027] In the technical solution of this invention, the collection, storage, use, processing, transmission, provision, and disclosure of user personal information all comply with relevant laws and regulations and do not violate public order and good morals. The use of user data in this technical solution follows relevant national laws and regulations (e.g., the "Information Security Technology - Personal Information Security Specification"). For example: appropriate measures are taken for personal information access control; restrictions are imposed on the display of personal information; the purpose of using personal information does not exceed the scope of direct or reasonable association; and explicit identity targeting is eliminated when using personal information to avoid precisely locating a specific individual.

[0028] In existing technologies, in-vehicle voice noise reduction mainly relies on single-microphone noise reduction, echo cancellation technology, and gain control strategies. Single-microphone noise reduction suppresses noise in specific frequency bands using a fixed filter, but it cannot adapt to dynamically changing noise environments and has limited anti-interference capabilities. Echo cancellation technology uses a traditional least mean square algorithm to process the echo between the speaker and microphone, but its convergence speed is slow, and its suppression effect is poor when user voice and speaker playback are present simultaneously; residual echoes can lead to a decrease in recognition accuracy. Gain control strategies use fixed gain adjustment or simple energy threshold triggering, which can easily misinterpret noise as speech and over-amplify it in low signal-to-noise ratio environments, or fail to recognize speech due to insufficient speech energy.

[0029] To address the problem of low speech recognition accuracy in complex in-vehicle noise environments, this invention provides a noise reduction method for in-vehicle speech that combines vehicle state perception, adaptive filtering, and dynamic gain adjustment. Figure 1This is a flowchart illustrating a method for denoising in-vehicle voice based on an embodiment of the present invention. The method includes: performing spectral analysis on a collected in-vehicle environmental audio signal based on a vehicle status signal, and outputting the spectral analysis result; the spectral analysis result includes the filtering frequency bands for which filters need to be activated; activating the filters of the filtering frequency bands based on the spectral analysis result to filter the in-vehicle environmental audio signal, obtaining a filtered signal; detecting and dividing the filtered signal into user voice segments and noise segments; and adjusting the amplitude of the filtered signal based on the user voice segments and noise segments to obtain a denoised signal.

[0030] In this embodiment, Figure 5 This is a schematic diagram of the microphone layout components and hardware parameters provided in the embodiments of the present invention, such as... Figure 5 As shown, a 6-channel MEMS (Micro-Electro-Mechanical System) microphone is used, distributed in the car ceiling (2 above the windshield and 2 on each side of the rear seat headrests) to form an all-round spatial sampling and suppress noise in non-target areas.

[0031] Through the embodiments of the present invention, the present invention utilizes vehicle bus data such as engine speed, air conditioning fan speed, and vehicle speed to predict noise characteristics, thereby improving the targeting of noise reduction algorithms for specific vehicle noises; by distinguishing between noise segments and speech segments, it specifically enhances speech clarity, realizing speech signal enhancement and dynamic gain control suitable for intelligent cockpit environments, thereby improving the recognition accuracy and user experience of in-vehicle voice assistants.

[0032] Based on the above embodiments, the collected in-vehicle environmental audio signal is subjected to spectrum analysis according to the vehicle status signal, and the spectrum analysis result is output, including: performing a fast Fourier transform on the in-vehicle environmental audio signal to obtain spectrum information; associating the noise correlation parameter in the vehicle status signal with the corresponding preset frequency band; the noise correlation parameter includes at least one of the engine speed, air conditioning fan speed, and vehicle speed parameters; in response to the noise correlation parameter being greater than a first preset threshold, the corresponding preset frequency band is marked as a filter frequency band; in response to the spectrum information having a frequency band with an amplitude greater than a second preset threshold in a preset number of consecutive frames, the frequency band with an amplitude greater than the second preset threshold is marked as a filter frequency band.

[0033] In this embodiment, the real-time spectrum analysis unit acquires the real-time status of the vehicle through a bus interface and performs spectrum analysis based on a processor and a fast Fourier transform accelerator.

[0034] Through embodiments of the present invention, noise source parameters such as engine and air conditioning are obtained via bus, and filter parameters are dynamically adjusted to solve the problem of insufficient suppression of specific vehicle noise by traditional solutions.

[0035] Figure 2 This is a block diagram illustrating the filtering application of the method provided in the embodiments of the present invention, such as... Figure 2 As shown, the process involves activating a filter in the selected frequency band based on the spectrum analysis results to filter the in-vehicle ambient audio signal, thereby obtaining a filtered signal. This includes: selecting the activated filter based on the spectrum analysis results; the filter includes at least a low-pass filter and a high-pass filter; and adjusting the step size of the filter according to the frequency band to filter the in-vehicle ambient audio signal, thereby obtaining a filtered signal.

[0036] In this embodiment, the adaptive filter bank includes a low-pass filter and a high-pass filter, employing a modified variable-step NLMS (Normalized Least Mean Square) algorithm, where the step size ranges from 0.005 to 0.1, and the filter order is 256 s. The preprocessing module suppresses power frequency interference using a 50Hz notch filter, and the pre-amplification gain is set to 20dB. The spectrum analysis unit fuses the vehicle state with the spectrum characteristics.

[0037] Through the embodiments of the present invention, a dual-path filter is designed to address the differences in low-frequency and high-frequency noise characteristics. When the energy of a certain frequency band exceeds a preset value for a continuous preset frame, the corresponding filter is triggered and the step size of the filter is adjusted.

[0038] Figure 3 The timing diagram for echo cancellation provided in the embodiment of the present invention shows that after obtaining the filtered signal, the method further includes a step of echo cancellation on the filtered signal, specifically including: estimating the echo path based on the vehicle speaker audio signal and the filtered signal; and canceling the echo of the filtered signal using a filter based on the echo path.

[0039] In this embodiment, the echo path estimation unit estimates the echo delay range based on a multi-channel cross-correlation algorithm and stores the parameters of the 10 most recent paths for fast matching. The linear adaptive filter employs the frequency domain block LMS algorithm (frequency domain block least mean square algorithm).

[0040] Through the embodiments of the present invention, by estimating the echo path and filtering to cancel it out, combined with linear adaptive filtering and nonlinear processing, echoes are effectively suppressed, solving the problem of decreased recognition rate caused by residual echoes in dual-talk scenarios.

[0041] Based on the above embodiments, the detection of filtered signals to divide user speech segments and noise segments includes: calculating the zero-crossing rate and spectral entropy of each frame of filtered signal; determining whether the current frame of filtered signal meets the speech conditions; the speech conditions are greater than a preset amplitude threshold, zero-crossing rate lower than a preset zero-crossing threshold, and spectral entropy lower than a preset entropy threshold; if yes, the current frame of filtered signal is taken as a candidate speech segment; if no, the current frame of filtered signal is taken as a noise segment; for each filtered signal in the candidate speech segment, determining whether there is an adjacent filtered signal; if yes, the filtered signal is taken as a speech segment; if no, the filtered signal is taken as a noise segment.

[0042] Through the embodiments of the present invention, speech activity detection and decision-making based on multiple features such as zero-crossing rate and spectral entropy are achieved. Due to the adoption of a dual-threshold mechanism, noise is prevented from being misjudged as speech.

[0043] Figure 4 The following is a block diagram of the dynamic gain of the method provided in the embodiments of the present invention, such as... Figure 4 As shown, the amplitude of the filtered signal is adjusted to obtain the noise-reduced signal based on the user's voice segment and the noise segment, including: in response to the voice segment, a gain boost operation is initiated; in response to the noise segment or a sudden high level is detected, a gain attenuation operation is initiated.

[0044] It should be noted that the signal is divided into frames according to the preset frame length, and the inter-frame distortion is reduced by the overlapping and addition method.

[0045] In this embodiment, linear gain is used during the voice segment and compression gain is used during the noise segment to avoid excessive amplification of noise. Similarly, the gain is reduced when sudden noise is detected to prevent speaker overload.

[0046] Through embodiments of the present invention, the accuracy of speech segment recognition is improved by adopting different gain measures for speech segments and noise segments.

[0047] Based on the above embodiments, the method further includes: adjusting the parameters of the filter and speech segment detection for special environments, specifically including: reducing the fast Fourier transform frequency and enhancing the low-frequency filtering intensity in response to the temperature and humidity being higher than the first temperature threshold and humidity threshold; and reducing the preset amplitude threshold for determining the speech segment in response to the temperature being lower than the second temperature threshold.

[0048] In this embodiment, the technical adjustments for high-temperature and high-humidity environments involve microphone selection, filter materials, and algorithm optimization. Specifically, a waterproof and moisture-proof MEMS microphone is used, and the diaphragm material is changed to polytetrafluoroethylene (PTFE). Moisture-resistant materials are used for the filters, and the solder joints are coated with conformal coating to prevent poor contact caused by high-temperature oxidation. Furthermore, in high-temperature environments, the FFT (Fast Fourier Transform) operation frequency is reduced to decrease processor heat generation, while simultaneously increasing the low-frequency filtering intensity to compensate for the decrease in microphone sensitivity caused by high temperatures.

[0049] In this embodiment, adaptation to low-temperature, low-signal-to-noise ratio (SNR) environments (such as cold regions and high-speed scenarios) involves microphone array layout, algorithm enhancement, and threshold adjustment for speech segment recognition. Specifically, two microphones pointing towards the driver's seat are added, and heating diaphragms are added to the microphone interfaces to enhance target speech acquisition; a combination of spectral subtraction and wavelet threshold denoising algorithms is used to improve the enhancement effect of low SNR speech; and the threshold for speech segment recognition is lowered to avoid the reduction in speech energy caused by low temperature being misjudged as noise.

[0050] Through embodiments of the present invention, special environmental parameters are adjusted to compensate for changes in voice characteristics in low-temperature environments, preventing performance degradation under extreme conditions.

[0051] Figure 6 A structural block diagram of an in-vehicle voice noise reduction system provided in an embodiment of the present invention is shown below. Figure 6 As shown, this invention provides a vehicle-mounted voice noise reduction system, which can be used to implement the aforementioned vehicle-mounted voice noise reduction method. The system includes: an analysis module, used to perform spectral analysis on the collected in-vehicle environmental audio signal based on vehicle status signals, and output spectral analysis results; the spectral analysis results include the filtering frequency bands for which filters need to be activated; a filtering module, used to activate the filters of the filtering frequency bands based on the spectral analysis results to filter the in-vehicle environmental audio signal, obtaining a filtered signal; and an adjustment module, used to detect the user voice segment and noise segment in the filtered signal, and adjust the amplitude of the filtered signal based on the user voice segment and noise segment to obtain a noise-reduced signal.

[0052] Based on the same inventive concept, embodiments of the present invention also provide an electronic device. Figure 7 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Figure 7As shown, an embodiment of the present invention provides an electronic device including: one or more processors 101, a memory 102, and one or more I / O interfaces 103. The memory 102 stores one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement any of the in-vehicle voice noise reduction methods described in the above embodiments; the one or more I / O interfaces 103 are connected between the processor and the memory, configured to enable information interaction between the processor and the memory.

[0053] The processor 101 is a device with data processing capabilities, including but not limited to a central processing unit (CPU); the memory 102 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and flash memory (FLASH); the I / O interface (read / write interface) 103 is connected between the processor 101 and the memory 102, and can realize information interaction between the processor 101 and the memory 102, including but not limited to a data bus (Bus).

[0054] In some embodiments, the processor 101, memory 102, and I / O interface 103 are interconnected via bus 104, and thus connected to other components of the computing device.

[0055] In some embodiments, the one or more processors 101 include a field-programmable gate array.

[0056] This invention also provides a computer-readable medium. The computer-readable medium stores a computer program, which, when executed by a processor, implements the steps of any of the in-vehicle voice noise reduction methods described in the above embodiments. The computer-readable storage medium can be volatile or non-volatile.

[0057] This invention also provides a computer program product, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code. When the computer-readable code is run in the processor of an electronic device, the processor in the electronic device executes the above-described vehicle voice noise reduction method.

[0058] Those skilled in the art will understand that all or some of the steps, systems, and apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software can be distributed on a computer-readable storage medium, which may include computer storage media (or non-transitory media) and communication media (or transient media).

[0059] As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable program instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technologies, portable compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, it is known to those skilled in the art that communication media typically contain computer-readable program instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0060] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0061] The computer program instructions used to perform the operations of this invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via 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). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing state information from the computer-readable program instructions. This electronic circuitry can execute the computer-readable program instructions to implement various aspects of the invention.

[0062] The computer program product described herein can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0063] Various aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0064] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0065] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0066] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0067] Example embodiments have been disclosed herein, and while specific terminology has been used, it is for illustrative purposes only and should be construed as such, and is not intended to be limiting. In some instances, it will be apparent to those skilled in the art that features, characteristics, and / or elements described in conjunction with particular embodiments may be used alone, or in combination with features, characteristics, and / or elements described in conjunction with other embodiments, unless otherwise expressly indicated. Therefore, those skilled in the art will understand that various changes in form and detail may be made without departing from the scope of the invention as set forth in the appended claims.

Claims

1. A method for noise reduction of in-vehicle voice input, characterized in that, include: The collected in-vehicle ambient audio signal is subjected to spectrum analysis based on the vehicle status signal, and the spectrum analysis results are output; the spectrum analysis results include the filter frequency bands that need to be activated by the filter; Based on the spectrum analysis results, the filter of the filtering frequency band is activated to filter the audio signal in the vehicle environment, and the filtered signal is obtained. The filtered signal is divided into user speech segments and noise segments. Based on the user speech segments and noise segments, the amplitude of the filtered signal is adjusted to obtain a noise-reduced signal.

2. The method according to claim 1, wherein, The step of performing spectral analysis on the collected in-vehicle ambient audio signal based on the vehicle status signal and outputting the spectral analysis results includes: Perform a Fast Fourier Transform on the in-vehicle ambient audio signal to obtain the spectral information; The noise correlation parameters in the vehicle status signal are associated with the corresponding preset frequency band; the noise correlation parameters include at least one of the following parameters: engine speed, air conditioning fan speed, and vehicle speed. If the noise correlation parameter is greater than a first preset threshold, the corresponding preset frequency band is marked as a filter frequency band. If the spectrum information contains frequency bands whose amplitude is greater than a second preset threshold in a preset number of consecutive frames, then the frequency bands with amplitude greater than the second preset threshold are marked as filter frequency bands.

3. The method according to claim 1, wherein, The filter, which activates the filter band based on the spectrum analysis results, filters the in-vehicle ambient audio signal to obtain a filtered signal, including: Based on the spectrum analysis results, select the filter to be activated; the filter includes at least a low-pass filter and a high-pass filter. The step size of the filter is adjusted according to the filter frequency band to filter the in-vehicle ambient audio signal and obtain a filtered signal.

4. The method according to claim 1, wherein, After obtaining the filtered signal, the method further includes an echo cancellation step for the filtered signal, specifically including: The echo path is estimated based on the audio signal from the vehicle speaker and the filtered signal. Based on the echo path, the filtered signal is echo-cancelled using a filter.

5. The method according to claim 1, wherein, The detection of the filtered signal to divide it into user speech segments and noise segments includes: Calculate the zero-crossing rate and spectral entropy of the filtered signal for each frame; Determine whether the current frame filtered signal meets the speech conditions; the speech conditions are greater than a preset amplitude threshold, zero-crossing rate lower than a preset zero-crossing threshold, and spectral entropy lower than a preset entropy threshold. If so, the current frame filtered signal will be used as the candidate speech segment; If not, the current frame's filtered signal will be treated as a noise segment; For each filtered signal in the candidate speech segment, determine whether there are adjacent filtered signals; If so, then the filtered signal is taken as the speech segment; If not, then the filtered signal is treated as a noise segment.

6. The method according to claim 1, wherein, The step of adjusting the amplitude of the filtered signal to obtain a noise-reduced signal based on the user's voice segment and the noise segment includes: In response to a speech segment, initiate a gain boost operation; In response to a noise segment or the detection of a sudden high level, a gain attenuation operation is initiated.

7. The method according to claim 1, wherein, The method further includes: For specific environments, adjust the parameters of the filter and speech segment detection, including: In response to temperature and humidity exceeding the first temperature threshold and humidity threshold, the fast Fourier transform frequency is reduced to enhance the low-frequency filtering strength. In response to a temperature below a second temperature threshold, the preset amplitude threshold for determining the speech segment is reduced.

8. A vehicle-mounted voice noise reduction system, characterized in that, Capable of implementing the method as described in any one of claims 1 to 7, comprising: The analysis module is used to perform spectrum analysis on the collected in-vehicle ambient audio signal based on the vehicle status signal and output the spectrum analysis results; the spectrum analysis results include the filter frequency bands that need to be activated by the filter; The filtering module is used to activate the filter of the filtering frequency band based on the spectrum analysis results to filter the audio signal in the vehicle environment and obtain the filtered signal. The adjustment module is used to detect the user's voice segment and noise segment by dividing the filtered signal, and adjust the amplitude of the filtered signal according to the user's voice segment and noise segment to obtain a noise-reduced signal.

9. An electronic device, characterized in that, include: One or more processors; Memory, used to store 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 method as described in any one of claims 1 to 7.

10. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images