Vehicle-mounted echo cancellation method and device, equipment and storage medium
By combining adaptive filters and neural networks, multi-channel multi-reference echoes in the in-vehicle environment are processed, achieving efficient echo cancellation and improving voice call quality.
Patent Information
- Application Number
- CN202411175080.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-26
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-08-26
AI Technical Summary
Existing in-vehicle echo cancellation methods cannot effectively eliminate all echoes, resulting in a decrease in the quality of remote voice calls.
An adaptive filter and neural network approach is adopted. By acquiring the speech signal and reference signal, frame windowing, Fourier transform and adaptive filtering are performed. Then, the neural network is used to generate a mask vector for echo removal. Finally, the echo-removed speech signal is obtained through inverse Fourier transform and signal frame reconstruction.
It effectively eliminates multi-channel, multi-reference echoes in the vehicle environment, improves voice call quality, and solves the problems of slow convergence, easy divergence, and large computational load.
Smart Images

Figure CN119028307A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of echo cancellation, and in particular to a vehicle-mounted echo cancellation method, device, equipment and storage medium. Background Art
[0002] There are many types of echoes in car scenarios, including music, navigation, voice broadcast, etc. There are many echo paths and many changes, which require good tracking performance. At the same time, real cars generally have multi-channel signals in multiple sound zones, which require echo cancellation processing of multiple signals at the same time.
[0003] The current echo cancellation method cannot eliminate all echoes, and the far end can still receive residual echoes that have not been completely eliminated, thereby reducing the call quality of the voice call.
[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention
[0005] The main purpose of the present application is to provide a vehicle-mounted echo cancellation method, device, equipment and storage medium, aiming to solve the technical problem that the vehicle-mounted microphone receives a large voice echo signal.
[0006] To achieve the above object, the present application proposes a vehicle-mounted echo cancellation method, the vehicle-mounted echo cancellation method comprising:
[0007] Acquire a speech signal and a reference signal;
[0008] Processing the speech signal and the reference signal through an adaptive filter to obtain a residual signal;
[0009] The speech signal, the reference signal and the residual signal are processed by a neural network to obtain a speech signal without echo.
[0010] In one embodiment, after the step of acquiring the speech signal and the reference signal, the method further includes:
[0011] Performing frame-by-frame windowing processing on the speech signal and the reference signal respectively to obtain a frame-by-frame windowed speech signal and a reference signal;
[0012] Performing Fourier transformation on the frame-windowed speech signal and the reference signal to obtain a time-frequency domain speech signal and a time-frequency domain reference signal;
[0013] The step of processing the speech signal and the reference signal by an adaptive filter to obtain a residual signal comprises:
[0014] Processing the time-frequency domain speech signal and the time-frequency domain reference signal through an adaptive filter to obtain a time-frequency domain residual signal;
[0015] The step of processing the speech signal, the reference signal and the time-frequency domain residual signal by a neural network to obtain a speech signal without echoes comprises:
[0016] The time-frequency domain speech signal, the time-frequency domain reference signal and the time-frequency domain residual signal are processed by a neural network to obtain a speech signal with echo removed.
[0017] In one embodiment, the step of processing the time-frequency domain speech signal, the time-frequency domain reference signal and the time-frequency domain residual signal by a neural network to obtain a speech signal without echoes includes:
[0018] Processing the time-frequency domain speech signal, the time-frequency domain reference signal and the time-frequency domain residual signal through a neural network to obtain a mask vector;
[0019] By processing the mask vector and the time-frequency domain speech signal, an echo-free speech signal is obtained.
[0020] In one embodiment, the step of processing the time-frequency domain speech signal, the time-frequency domain reference signal and the time-frequency domain residual signal by a neural network to obtain a mask vector includes:
[0021] splicing the time-frequency domain speech signal, the time-frequency domain reference signal and the residual signal into a vector through a normalization layer of the neural network;
[0022] The vector is processed by the core layer of the neural network to obtain a mask vector.
[0023] In one embodiment, the step of splicing the time-frequency domain speech signal, the time-frequency domain reference signal and the residual signal into a vector through the normalization layer of the neural network includes:
[0024] The time-frequency domain speech signal, the time-frequency domain reference signal and the residual signal are normalized by the normalization layer of the neural network to obtain a normalized time-frequency domain speech signal, a time-frequency domain reference signal and a residual signal;
[0025] The normalized time-frequency domain speech signal, the time-frequency domain reference signal and the residual signal are concatenated into a vector along the frequency axis.
[0026] In one embodiment, the step of obtaining the de-echoed speech signal by processing the mask vector and the time-frequency domain speech signal comprises:
[0027] Processing the mask vector and the time-frequency domain speech signal to obtain a time-frequency domain signal after echo removal;
[0028] Performing inverse Fourier transform on the time-frequency domain signal after the echo is removed to obtain a time-domain speech signal after the echo is removed;
[0029] The time-domain speech signal after the echo is removed is subjected to signal frame reorganization to obtain a speech signal after the echo is removed.
[0030] In one embodiment, the step of acquiring a reference signal includes:
[0031] Get the reference audio played by each car speaker;
[0032] The reference audio is evenly mixed according to a preset ratio to obtain the reference signal.
[0033] In addition, to achieve the above-mentioned purpose, the present application also proposes a vehicle-mounted echo cancellation device, the device comprising:
[0034] A signal acquisition module, used to acquire a speech signal and a reference signal;
[0035] A first processing module, configured to process the speech signal and the reference signal through an adaptive filter to obtain a residual signal;
[0036] The second processing module is used to process the speech signal, the reference signal and the residual signal through a neural network to obtain a speech signal without echo.
[0037] In addition, to achieve the above objectives, the present application also proposes a vehicle-mounted echo cancellation device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the vehicle-mounted echo cancellation method described above.
[0038] In addition, to achieve the above objectives, the present application also proposes a storage medium, which is a computer-readable storage medium, and stores a computer program on the storage medium. When the computer program is executed by a processor, the steps of the vehicle-mounted echo cancellation method described above are implemented.
[0039] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the vehicle-mounted echo cancellation method described above are implemented.
[0040] One or more technical solutions proposed in this application have at least the following technical effects:
[0041] Acquire speech signal and reference signal; process the speech signal and reference signal through adaptive filter to obtain residual signal; process the speech signal, reference signal and residual signal through neural network to obtain echo-free speech signal, and perform echo cancellation processing in two levels based on the combination of adaptive filtering and neural network to efficiently process multi-channel and multi-reference signals. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] 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.
[0043] 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.
[0044] Figure 1 A flow chart of the first embodiment of the vehicle-mounted echo cancellation method of the present application;
[0045] Figure 2 A diagram of an in-vehicle echo audio link provided in Embodiment 1 of the in-vehicle echo cancellation method of the present application;
[0046] Figure 3 A structural block diagram of the first embodiment of the vehicle-mounted echo cancellation method of the present application;
[0047] Figure 4 A schematic diagram of a flow chart provided for the second embodiment of the vehicle-mounted echo cancellation method of the present application;
[0048] Figure 5 A flowchart of the third embodiment of the vehicle-mounted echo cancellation method of the present application is provided;
[0049] Figure 6 This is a schematic diagram of the module structure of the vehicle-mounted echo cancellation device according to an embodiment of the present application;
[0050] Figure 7 Schematic diagram of the device structure of the hardware operating environment involved in the vehicle-mounted echo cancellation method in the embodiment of the present application.
[0051] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0052] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.
[0053] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.
[0054] The present application proposes an echo cancellation algorithm based on the combination of adaptive filtering and neural network, which can process multi-channel and multi-reference signals and effectively solve the problems of slow convergence, easy divergence and large amount of calculation.
[0055] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a vehicle-mounted echo cancellation device, etc. The following takes the vehicle-mounted echo cancellation device as an example to illustrate this embodiment and the following embodiments.
[0056] Based on this, the embodiment of the present application provides a vehicle-mounted echo cancellation method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the vehicle-mounted echo cancellation method of the present application.
[0057] In this embodiment, the vehicle-mounted echo cancellation method includes steps S10 to S30:
[0058] Step S10, acquiring a speech signal and a reference signal;
[0059] It should be noted that the voice signal is a sound signal received by a microphone or other vehicle-mounted voice receiving device. The received voice signal includes noise such as echo. The reference signal refers to the reference audio signal played by speakers at different positions in the car (such as front, back, left and right).
[0060] like Figure 2 As shown, Figure 2 This is a diagram of the vehicle-mounted echo audio link. The microphone and the speaker are distributed. The received echo signal of microphone i (i=1, 2, 3...) can be modeled as:
[0061]
[0062] n is the number of speakers in the car, x j is the reference signal played by the loudspeaker, ji For x j The propagation path of the signal from speaker j to microphone i. * represents the convolution operation. Assume that the near-end speech of microphone i is s i , then the signal collected by microphone i is: d i =s i +y i Since the echo has a great impact on the back-end speech recognition effect, we need to perform echo cancellation on the signal collected by the microphone to separate the speech signal si ,Therefore, this strategy of vehicle echo cancellation method is proposed.
[0063] Furthermore, the step of obtaining a reference signal includes:
[0064] Get the reference audio played by each car speaker;
[0065] The reference audio is evenly mixed according to a preset ratio to obtain a reference signal.
[0066] In the specific implementation, the reference signal played back by the speaker at each position in the car is used to divide the multiple reference audios equally in proportion and mix them into a smaller number of reference audios (the actual car is generally 1 or 2 channels, and in a few cases 4 channels).
[0067] It should be noted that the reference signals of multiple speakers are adjusted and distributed according to a preset ratio to ensure that the volume and timbre of each position in the car are balanced.
[0068] Mixing into a smaller number of reference audio This process involves combining the signals from multiple speakers into fewer channels. For example, if there are 8 speakers in the car, their sound signals can be combined into 2 main channels (usually the signals for the left and right front speakers), or in some cases, 4 channels (left front, right front, left rear, right rear).
[0069] Step S20, processing the speech signal and the reference signal through an adaptive filter to obtain a residual signal;
[0070] It should be noted that the residual signal refers to the original speech signal minus the signal processed by the adaptive filter. This difference represents the noise or echo that the filter cannot completely eliminate.
[0071] The adaptive filter automatically adjusts its parameters according to the reference signal to optimize the reduction or elimination of unwanted sound components, such as echo or noise. The adaptive filter continuously monitors the residual signal and adjusts the filter parameters according to its characteristics through the minimum mean square error (LMS) algorithm or other adaptive algorithms to further reduce the noise or echo components in the residual signal.
[0072] It should be understood that the first echo cancellation process using a linear adaptive filter obtains a speech time-frequency domain signal E, which has a higher signal-to-noise ratio than speech and has a certain guiding role in neural network training.
[0073] In a specific implementation, the mixed reference signal and the signal collected by the microphone are input into an adaptive filter module to obtain a residual signal after linear filtering.
[0074] Step S30, processing the speech signal, the reference signal and the residual signal through a neural network to obtain a speech signal without echo.
[0075] In a specific implementation, the original microphone signal, the mixed reference signal, and the residual signal after linear filtering are input together to the post-stage neural network to obtain the near-end speech signal that has finally undergone echo cancellation processing.
[0076] like Figure 3 As shown, Figure 3 : As a structural block diagram, the speech signal D with echo and the reference signal x are first subjected to frame FFT processing to obtain the speech time-frequency domain signal D with echo and the reference time-frequency domain signal X, and then input into the adaptive filter to obtain the speech time-frequency domain signal E enhanced by the linear filter. The speech time-frequency domain signal D with echo, the reference time-frequency domain signal X and the speech time-frequency domain signal E enhanced by the linear filter are input into the LayerNorm layer for normalization processing to obtain their own normalized signals, and then input into the core layer of the neural network to obtain the time-frequency mask value. The time-frequency mask value and the speech time-frequency domain signal D with echo are processed to obtain the enhanced near-end speech signal s.
[0077] It should be noted that an adaptive filter is a filter that can automatically adjust its parameters according to the characteristics of the input signal to improve the quality of the signal.
[0078] Speech time-frequency with echo: It is the original speech signal, including noise such as echo.
[0079] Linear filter enhanced domain signal D: The signal is enhanced by a linear filter to obtain an improved time-frequency domain signal.
[0080] Speech time-frequency domain signal E: The speech signal processed by the linear filter is located in the time-frequency domain.
[0081] Reference time-frequency domain signal X: the time-frequency domain signal used as a reference.
[0082] LayerNorm layer: is a normalization layer used to adjust the output of the layer in the neural network so that it has a distribution with a mean of 0 and a standard deviation of 1, which helps to improve the stability and performance of the network.
[0083] Core layer (RNN+fully connected+sigmoid): The core layer consists of a recurrent neural network (RNN), a fully connected layer, and a sigmoid activation function for further signal processing.
[0084] Time-frequency mask value: A mask applied in the time-frequency domain to mask out or emphasize certain parts of the signal.
[0085] multiply: represents the multiplication operation, which is used to apply a mask to a signal.
[0086] ifft&overlapadd: refers to the Inverse Fast Fourier Transform (IFFT) and overlap-add technique, which is used to convert the time-frequency domain signal back to the time domain signal.
[0087] This embodiment provides a vehicle-mounted echo cancellation method, which obtains a voice signal and a reference signal; processes the voice signal and the reference signal through an adaptive filter to obtain a residual signal; processes the voice signal, the reference signal and the residual signal through a neural network to obtain a voice signal without echoes, and performs echo cancellation processing in two levels based on a combination of adaptive filtering and a neural network, so as to efficiently process multi-channel and multi-reference signals.
[0088] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 4 After step S10, the vehicle-mounted echo cancellation method further includes steps S101 to S102:
[0089] Step S101, performing frame-by-frame windowing processing on the speech signal and the reference signal respectively to obtain the frame-by-frame windowed speech signal and the reference signal;
[0090] It should be noted that framing is to divide a continuous signal into shorter segments, which are called frames. The purpose of framing is to convert a continuous signal into a format suitable for discrete Fourier transform (DFT) processing.
[0091] Windowing is to multiply each frame by a window function, such as a Hanning window, a Hamming window, or a rectangular window. The role of the window function is to reduce the discontinuity at the frame boundary, thereby reducing the spectrum leakage effect.
[0092] Step S102, performing Fourier transform on the framed and windowed speech signal and the reference signal to obtain a time-frequency domain speech signal and a time-frequency domain reference signal;
[0093] Then, each frame processed by the window function is subjected to a fast Fourier transform. Among them, FFT is an efficient algorithm that can quickly calculate the spectrum of the signal, that is, the amplitude and phase of the signal at different frequencies.
[0094] In a specific implementation, the speech signal d with echo and the reference signal x are framed and windowed, and Fourier transform is performed to obtain time-frequency domain signals D and X respectively.
[0095] Furthermore, the step of processing the speech signal and the reference signal by an adaptive filter to obtain a residual signal includes:
[0096] The time-frequency domain speech signal and the time-frequency domain reference signal are processed by an adaptive filter to obtain a time-frequency domain residual signal;
[0097] The step of processing the speech signal, the reference signal and the time-frequency domain residual signal by a neural network to obtain the speech signal without echo includes:
[0098] The time-frequency domain speech signal, the time-frequency domain reference signal and the time-frequency domain residual signal are processed by a neural network to obtain a speech signal without echo.
[0099] This embodiment provides a vehicle-mounted echo cancellation method, which first performs frame processing on the voice signal and the reference signal, and then processes them through an echo cancellation algorithm combining adaptive filtering and a neural network. It can process multi-channel and multi-reference signals and effectively solve the problems of slow convergence, easy divergence and large amount of calculation.
[0100] Based on the first and second embodiments of the present application, in the third embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction, and will not be described in detail later. Figure 5 , step S30, including steps S301-S302:
[0101] Step S301, processing the time-frequency domain speech signal, the time-frequency domain reference signal and the time-frequency domain residual signal through a neural network to obtain a mask vector;
[0102] It should be noted that the mask vector can be a Boolean array or a binary array, and the elements of the array can be 0 or 1, indicating whether the corresponding data point is selected or masked.
[0103] In the specific implementation, the time-frequency domain speech signal, the time-frequency domain reference signal and the time-frequency domain residual signal are processed through the normalization layer and the core layer of the neural network to obtain a mask vector with the same latitude as the time-frequency domain speech signal.
[0104] Furthermore, the step S301 includes:
[0105] The time-frequency domain speech signal, the time-frequency domain reference signal and the residual signal are concatenated into a vector through the normalization layer of the neural network;
[0106] The vector is processed through the core layer of the neural network to obtain the mask vector.
[0107] In the specific implementation, the LayerNorm layer is used for normalization, and then the three normalized time-frequency vectors are concatenated into a vector along the frequency axis. This concatenated vector is then input into the core layer of the network, including n layers of RNN (GRU, LSTM), a layer of full connection, and finally a mask vector mask with the same latitude as D is obtained through the nonlinear activation sigmoid.
[0108] Furthermore, the step of splicing the time-frequency domain speech signal, the time-frequency domain reference signal and the residual signal into a vector through a normalization layer of a neural network includes:
[0109] The time-frequency domain speech signal, the time-frequency domain reference signal and the residual signal are normalized by a normalization layer of a neural network to obtain a normalized time-frequency domain speech signal, a time-frequency domain reference signal and a residual signal;
[0110] The normalized time-frequency domain speech signal, the time-frequency domain reference signal and the residual signal are concatenated into a vector along the frequency axis.
[0111] It should be noted that the role of the normalization layer is to adjust the distribution of the signal so that it has a stable mean and standard deviation; after normalization, the characteristic distribution of each signal is more standardized, which is helpful for subsequent neural network processing.
[0112] The normalized time-frequency domain speech signal, the time-frequency domain reference signal and the residual signal are concatenated along the frequency axis, and the values of the three signals are arranged in sequence in the frequency dimension to form a longer vector.
[0113] In the specific implementation, normalization is performed through the LayerNorm layer, and then the three normalized time-frequency vectors are concatenated into one vector along the frequency axis.
[0114] Step S302: Process the mask vector and the time-frequency domain speech signal to obtain an echo-free speech signal.
[0115] Furthermore, the step S302 includes:
[0116] The mask vector and the time-frequency domain speech signal are processed to obtain a time-frequency domain signal after the echo is removed;
[0117] Performing inverse Fourier transform on the time-frequency domain signal after the echo is removed to obtain the time-domain speech signal after the echo is removed;
[0118] The time-domain speech signal after the echo is removed is reassembled into signal frames to obtain the speech signal after the echo is removed.
[0119] In a specific implementation, the time-frequency domain speech signal is multiplied by the mask vector mask, and an inverse Fourier transform and overlap add are performed to obtain an enhanced near-end speech signal with echo removed.
[0120] It should be noted that the time-frequency domain signal after the echo is removed is subjected to an inverse Fourier transform (IFFT) to convert the signal from the frequency domain back to the time domain, thereby obtaining the time-domain speech signal after the echo is removed.
[0121] After the inverse Fourier transform, a series of short-time signal frames are obtained. Signal frame reconstruction refers to recombining these short-time signal frames into a continuous time domain signal. The Overlap-Add method is used to ensure signal continuity and reduce boundary effects.
[0122] This embodiment provides a vehicle-mounted echo cancellation method, in which the original microphone signal, the mixed reference signal, and the residual signal after linear filtering are input together to a post-stage neural network to obtain a near-end speech signal that has finally undergone echo cancellation processing. At this time, multiple microphone signals can be assembled into one batch and transmitted to the network to achieve the purpose of saving computing overhead, so that the network can achieve good results without a very complex RNN layer, with good effects and low computing power requirements.
[0123] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the vehicle-mounted echo cancellation method of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.
[0124] This application also provides a vehicle-mounted echo cancellation device, please refer to Figure 6 , the vehicle-mounted echo cancellation device comprises:
[0125] A signal acquisition module 10, used to acquire a speech signal and a reference signal;
[0126] A first processing module 20, configured to process the speech signal and the reference signal through an adaptive filter to obtain a residual signal;
[0127] The second processing module 30 is used to process the speech signal, the reference signal and the residual signal through a neural network to obtain a speech signal with echo removed.
[0128] The vehicle-mounted echo cancellation device provided by the present application adopts the vehicle-mounted echo cancellation method in the above embodiment, which can solve the technical problem that the vehicle-mounted microphone receives a large voice echo signal. Compared with the prior art, the beneficial effects of the vehicle-mounted echo cancellation device provided by the present application are the same as the beneficial effects of the vehicle-mounted echo cancellation method provided by the above embodiment, and other technical features in the vehicle-mounted echo cancellation device are the same as the features disclosed in the above embodiment method, which will not be repeated here.
[0129] The present application provides a vehicle-mounted echo cancellation device, which includes: 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 vehicle-mounted echo cancellation method in the above-mentioned embodiment 1.
[0130] Reference below Figure 7 , which shows a schematic diagram of the structure of a vehicle-mounted echo cancellation device suitable for implementing an embodiment of the present application. The vehicle-mounted echo cancellation device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 7 The vehicle-mounted echo cancellation device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0131] like Figure 7As shown, the vehicle-mounted echo cancellation device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. Various programs and data required for the operation of the vehicle-mounted echo cancellation device are also stored in the RAM 1004. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 may allow the vehicle-mounted echo cancellation device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a vehicle-mounted echo cancellation device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.
[0132] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.
[0133] The vehicle-mounted echo cancellation device provided by the present application adopts the vehicle-mounted echo cancellation method in the above embodiment, which can solve the technical problem that the vehicle-mounted microphone receives a large voice echo signal. Compared with the prior art, the beneficial effects of the vehicle-mounted echo cancellation device provided by the present application are the same as the beneficial effects of the vehicle-mounted echo cancellation method provided by the above embodiment, and other technical features in the vehicle-mounted echo cancellation device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.
[0134] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.
[0135] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0136] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the vehicle-mounted echo cancellation method in the above-mentioned embodiment.
[0137] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.
[0138] The computer-readable storage medium may be included in the vehicle-mounted echo cancellation device; or may exist independently without being assembled into the vehicle-mounted echo cancellation device.
[0139] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the vehicle-mounted echo cancellation device, the vehicle-mounted echo cancellation device: obtains a speech signal and a reference signal; processes the speech signal and the reference signal through an adaptive filter to obtain a residual signal; and processes the speech signal, the reference signal and the residual signal through a neural network to obtain a speech signal without echoes.
[0140] Computer program code for performing the operations of the present application may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0141] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0142] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.
[0143] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned vehicle-mounted echo cancellation method, and can solve the technical problem that the vehicle-mounted microphone receives a large voice echo signal. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the vehicle-mounted echo cancellation method provided by the above-mentioned embodiment, and will not be repeated here.
[0144] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned vehicle-mounted echo cancellation method when executed by a processor.
[0145] The computer program product provided by the present application can solve the technical problem that the vehicle-mounted microphone receives a large voice echo signal. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the vehicle-mounted echo cancellation method provided by the above embodiment, which will not be repeated here.
[0146] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.
Claims
1. A vehicle-mounted echo cancellation method, characterized in that: The vehicle-mounted echo cancellation method comprises: Acquire a speech signal and a reference signal; Processing the speech signal and the reference signal through an adaptive filter to obtain a residual signal; The speech signal, the reference signal and the residual signal are processed by a neural network to obtain a speech signal without echo.
2. The vehicle-mounted echo cancellation method as claimed in claim 1, characterized in that: After the step of acquiring the speech signal and the reference signal, the method further includes: Performing frame-by-frame windowing processing on the speech signal and the reference signal respectively to obtain a frame-by-frame windowed speech signal and a reference signal; Performing Fourier transformation on the frame-windowed speech signal and the reference signal to obtain a time-frequency domain speech signal and a time-frequency domain reference signal; The step of processing the speech signal and the reference signal by an adaptive filter to obtain a residual signal comprises: Processing the time-frequency domain speech signal and the time-frequency domain reference signal through an adaptive filter to obtain a time-frequency domain residual signal; The step of processing the speech signal, the reference signal and the time-frequency domain residual signal by a neural network to obtain a speech signal without echoes comprises: The time-frequency domain speech signal, the time-frequency domain reference signal and the time-frequency domain residual signal are processed by a neural network to obtain a speech signal with echo removed.
3. The vehicle-mounted echo cancellation method as claimed in claim 2, characterized in that: The step of processing the time-frequency domain speech signal, the time-frequency domain reference signal and the time-frequency domain residual signal by a neural network to obtain a speech signal without echoes comprises: Processing the time-frequency domain speech signal, the time-frequency domain reference signal and the time-frequency domain residual signal through a neural network to obtain a mask vector; By processing the mask vector and the time-frequency domain speech signal, an echo-free speech signal is obtained.
4. The vehicle-mounted echo cancellation method as claimed in claim 3, characterized in that: The step of processing the time-frequency domain speech signal, the time-frequency domain reference signal and the time-frequency domain residual signal by a neural network to obtain a mask vector comprises: splicing the time-frequency domain speech signal, the time-frequency domain reference signal and the residual signal into a vector through a normalization layer of the neural network; The vector is processed by the core layer of the neural network to obtain a mask vector.
5. The vehicle-mounted echo cancellation method as claimed in claim 4, characterized in that: The step of splicing the time-frequency domain speech signal, the time-frequency domain reference signal and the residual signal into a vector through the normalization layer of the neural network comprises: The time-frequency domain speech signal, the time-frequency domain reference signal and the residual signal are normalized by the normalization layer of the neural network to obtain a normalized time-frequency domain speech signal, a time-frequency domain reference signal and a residual signal; The normalized time-frequency domain speech signal, the time-frequency domain reference signal and the residual signal are concatenated into a vector along the frequency axis.
6. The vehicle-mounted echo cancellation method as claimed in claim 3, characterized in that: The step of obtaining the de-echoed speech signal by processing the mask vector and the time-frequency domain speech signal comprises: Processing the mask vector and the time-frequency domain speech signal to obtain a time-frequency domain signal after echo removal; Performing inverse Fourier transform on the time-frequency domain signal after the echo is removed to obtain a time-domain speech signal after the echo is removed; The time-domain speech signal after the echo is removed is subjected to signal frame reorganization to obtain a speech signal after the echo is removed.
7. The vehicle-mounted echo cancellation method as claimed in claim 1, characterized in that: The step of obtaining a reference signal comprises: Get the reference audio played by each car speaker; The reference audio is evenly mixed according to a preset ratio to obtain the reference signal.
8. A vehicle-mounted echo cancellation device, characterized in that: The device comprises: A signal acquisition module, used to acquire a speech signal and a reference signal; A first processing module, configured to process the speech signal and the reference signal through an adaptive filter to obtain a residual signal; The second processing module is used to process the speech signal, the reference signal and the residual signal through a neural network to obtain a speech signal without echo.
9. A vehicle-mounted echo cancellation device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the vehicle-mounted echo cancellation method according to any one of claims 1 to 7.
10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the vehicle-mounted echo cancellation method according to any one of claims 1 to 7 are implemented.
Citation Information
Patent Citations
Acoustic echo cancellation method and system based on adaptive filter and neural network
CN113436636A
Echo elimination method and device, electronic equipment and computer readable medium
CN115083431A
Echo cancellation method and device, audio equipment and storage medium
CN117727317A
Cited By
In-vehicle call method and device, storage medium and electronic terminal
CN120748424A
