In-vehicle karaoke howling elimination method, device and equipment, medium and vehicle

Abstract

The invention relates to an in-vehicle karaoke howling elimination method, device and equipment, a medium and a vehicle. The method comprises the following steps: acquiring a first audio signal acquired by an in-vehicle pickup, a second audio signal acquired by a karaoke microphone and a currently played accompaniment audio signal; if detecting that a howling feature exists in the first audio signal, comparing the first audio signal, the accompaniment audio signal and the second audio signal, and determining a howling sub-audio signal related to howling in the first audio signal; and eliminating an audio signal related to the howling sub-audio signal in the second audio signal to obtain a howling-eliminated human voice audio signal. According to the invention, whistling generated when the user karaoke in the vehicle can be eliminated, and the user experience is improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of audio signal processing, and in particular to a method, device, equipment, medium and vehicle for eliminating howling of karaoke songs in a car. Background Art

[0002] With the continuous development of society, cars have become one of the main choices for people to travel. As people's requirements for quality of life increase, the entertainment equipment configured in vehicles is becoming more and more abundant. At present, many vehicles are equipped with karaoke equipment, which can satisfy the hobbies of many car owners and passengers to sing in the car. However, due to the special environment in the car, singing in the car can easily cause the karaoke equipment to produce howling sounds, affecting the user experience. Summary of the invention

[0003] In order to solve the above technical problems, the present disclosure provides a method, device, equipment, medium and vehicle for eliminating howling when singing karaoke in a car.

[0004] In a first aspect, the present disclosure provides a method for eliminating howling during karaoke in a car, comprising:

[0005] Acquire a first audio signal collected by a car microphone, a second audio signal collected by a karaoke microphone, and a currently playing accompaniment audio signal;

[0006] If a howling feature is detected in the first audio signal, comparing the first audio signal, the accompaniment audio signal and the second audio signal to determine a howling sub-audio signal related to the howling in the first audio signal;

[0007] The audio signal related to the howling sub-audio signal is eliminated from the second audio signal to obtain a human voice audio signal with howling eliminated.

[0008] Optionally, the sensitivity of the microphone is higher than the sensitivity of the karaoke microphone, and the distance between the microphone and the in-car audio system is smaller than the distance between the karaoke microphone and the in-car audio system.

[0009] Optionally, the method for detecting the howling feature includes:

[0010] Performing denoising on the first audio signal to obtain a denoised first audio signal;

[0011] Extracting an autocorrelation function of the denoised first audio signal;

[0012] If the autocorrelation function has at least two similar peaks, it is determined that a howling feature exists in the first audio signal.

[0013] Optionally, the comparing the first audio signal, the accompaniment audio signal and the second audio signal to determine a howling sub-audio signal related to howling in the first audio signal includes:

[0014] Performing sound source separation on the denoised first audio signal to obtain at least two first sub-audio signals;

[0015] Comparing the at least two first sub audio signals with the accompaniment audio signal, and determining a target first sub audio signal including the accompaniment audio signal among the at least two first sub audio signals;

[0016] Separating and eliminating the accompaniment audio signal from the target first sub audio signal to obtain a second sub audio signal;

[0017] The second audio signal is compared with the second sub audio signal, and a sub audio signal similar to the sub audio signal of the second audio signal and having a larger amplitude is extracted from the second sub audio signal as the howling sub audio signal.

[0018] Optionally, the step of eliminating an audio signal related to the howling sub-audio signal in the second audio signal to obtain a human voice audio signal with howling eliminated includes:

[0019] Extracting audio features of the howling sub-audio signal;

[0020] Using an adaptive filtering algorithm to search for and eliminate audio signal components related to the audio feature in the second audio signal to obtain a filtered audio signal;

[0021] The filtered audio signals are recombined to obtain the human voice audio signal with howling eliminated.

[0022] Optionally, the method further includes:

[0023] Denoising and enhancing the human voice audio signal, and mixing the enhanced human voice audio signal with the accompaniment audio signal to be played to obtain a final output mixed signal;

[0024] The audio corresponding to the mixed signal is played through the in-car audio system.

[0025] In a second aspect, the present disclosure provides a device for eliminating howling during karaoke in a car, comprising:

[0026] An acquisition module is used to acquire a first audio signal collected by a car microphone, a second audio signal collected by a karaoke microphone, and an accompaniment audio signal currently being played;

[0027] a detection module, configured to, if a howling feature is detected in the first audio signal, compare the first audio signal, the accompaniment audio signal and the second audio signal to determine a howling sub-audio signal related to the howling in the first audio signal;

[0028] The processing module is used to eliminate the audio signal related to the howling sub-audio signal in the second audio signal to obtain a human voice audio signal with howling eliminated.

[0029] Optionally, the sensitivity of the microphone is higher than the sensitivity of the karaoke microphone, and the distance between the microphone and the in-car audio system is smaller than the distance between the karaoke microphone and the in-car audio system.

[0030] Optionally, when detecting the howling feature, the detection module is specifically used to denoise the first audio signal to obtain a denoised first audio signal; extract the autocorrelation function of the denoised first audio signal; if at least two similar peaks appear in the autocorrelation function, it is determined that the howling feature exists in the first audio signal.

[0031] Optionally, when the detection module compares the first audio signal, the accompaniment audio signal and the second audio signal to determine the howling sub-audio signal related to the howling in the first audio signal, the detection module is specifically used to perform sound source separation on the denoised first audio signal to obtain at least two first sub-audio signals; compare the at least two first sub-audio signals with the accompaniment audio signal to determine a target first sub-audio signal that contains the accompaniment audio signal among the at least two first sub-audio signals; separate and eliminate the accompaniment audio signal from the target first sub-audio signal to obtain a second sub-audio signal; and compare the second audio signal with the second sub-audio signal to extract a sub-audio signal that is similar to the sub-audio signal of the second audio signal and has a larger amplitude from the second sub-audio signal as the howling sub-audio signal.

[0032] Optionally, when the processing module eliminates the audio signal related to the howling sub-audio signal in the second audio signal to obtain the human voice audio signal with howling eliminated, it is specifically used to extract the audio features of the howling sub-audio signal; use an adaptive filtering algorithm to search for and eliminate the audio signal components related to the audio features in the second audio signal to obtain a filtered audio signal; and recombine the filtered audio signals to obtain the human voice audio signal with howling eliminated.

[0033] Optionally, the device also includes a playback module, which is used to denoise and enhance the human voice audio signal, and mix the enhanced human voice audio signal with the accompaniment audio signal to be played to obtain a final output mixed signal; and play the audio corresponding to the mixed signal through the in-car audio system.

[0034] In a third aspect, the present disclosure provides a computer device, comprising:

[0035] Memory;

[0036] Processor; and

[0037] Computer programs;

[0038] The computer program is stored in the memory and is configured to be executed by the processor to implement the method as described in any one of the first aspects.

[0039] In a fourth aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method as described in any one of the first aspects.

[0040] In a fifth aspect, the present disclosure provides a vehicle, comprising the in-vehicle karaoke howling elimination device as described in the second aspect and / or the computer device as described in the third aspect.

[0041] The present invention provides a method, device, equipment, medium and vehicle for eliminating howling in car karaoke. After the karaoke function is turned on, a first audio signal collected by an in-car pickup, a second audio signal collected by a karaoke microphone and a currently played accompaniment audio signal are obtained. When a howling feature is detected in the first audio signal, the howling sub-audio signal related to the howling in the first audio signal is quickly and accurately determined by comparing the first audio signal, the accompaniment audio signal and the second audio signal. Finally, the audio signal related to the howling sub-audio signal is eliminated in the second audio signal to obtain a singing human voice audio signal with howling eliminated in the second audio signal, thereby achieving the effect of eliminating the howling caused by in-car karaoke, so that the human voice audio signal and the accompaniment audio signal can be mixed and output later, thereby improving the user experience. 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 disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0043] In order to more clearly illustrate the embodiments of the present invention 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 a method for eliminating howling during karaoke in a car provided by an embodiment of the present disclosure;

[0045] Figure 2 A schematic diagram of an application scenario provided by an embodiment of the present disclosure;

[0046] Figure 3 A schematic diagram of the structure of a device for eliminating howling in car karaoke provided by an embodiment of the present disclosure;

[0047] Figure 4 It is a structural schematic diagram of an electronic device in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0048] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0049] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0050] Figure 1 This is a flow chart of a method for eliminating howling during in-car karaoke provided by an embodiment of the present disclosure. The method can be executed by an in-car karaoke howling elimination device, which can be implemented in software and / or hardware. The in-car karaoke howling elimination device can be configured in an electronic device, such as a server or a terminal, wherein the terminal includes a computer device with specific data processing capabilities such as a car machine, a car computer, etc. The method includes the following steps:

[0051] S101, obtaining a first audio signal collected by a car microphone, a second audio signal collected by a karaoke microphone, and a currently playing accompaniment audio signal.

[0052] For example, Figure 2 Schematic diagram of an application scenario provided by an embodiment of the present disclosure, the scenario includes a vehicle 200 and a user 240, the vehicle 200 is equipped with a car machine 210, a karaoke microphone 220, a speaker 230 and a pickup 250, such as Figure 2 The vehicle computer 210 shown can execute the method for eliminating howling during karaoke in the vehicle provided by the embodiment of the present disclosure. It can be understood that the method for eliminating howling during karaoke in the vehicle provided by the embodiment of the present disclosure can also be applied to other scenarios.

[0053] exist Figure 2In the scenario shown, when user 240 turns on the karaoke function through the car machine 210, the singing audio signal of user 240 collected by the karaoke microphone is processed by the sound effect algorithm and mixed with the accompaniment audio signal, and the mixed audio signal is transmitted to the power amplifier device for amplification and then played by the speaker 230, completing the entire audio path of the karaoke. Since the sound emitted by the speaker 230 may be received by the karaoke microphone 220, amplified again by the power amplifier device and then played by the speaker 230, the amplified sound is then received by the karaoke microphone 220 again, amplified by the power amplifier device and played by the speaker 230, and such a cycle may form a strong acoustic oscillation, thereby generating self-excited howling.

[0054] Nowadays, manufacturers are paying more and more attention to the sound effects in cars. Usually, multiple speakers are installed in different positions in the vehicle cabin. This increases the probability of howling when singing karaoke in the car.

[0055] In order to eliminate the self-excited howling that may be generated when singing karaoke in the car, when the karaoke function is turned on, the car machine 210 will simultaneously obtain the first audio signal collected by the microphone 250, the second audio signal collected by the karaoke microphone 220, and the accompaniment audio signal corresponding to the karaoke accompaniment currently being played, so as to detect whether howling is generated during the karaoke process and subsequently eliminate the howling. The accompaniment audio signal can be directly obtained through locally stored data or downloaded online. In addition, in order to improve the sensitivity of detecting howling when singing karaoke in the car, multiple high-sensitivity microphones can also be set at different positions in the cabin.

[0056] In the disclosed embodiment, the sensitivity of the microphone arranged in the car is higher than that of the karaoke microphone, and the distance between the microphone and the car audio is smaller than the distance between the karaoke microphone and the car audio.

[0057] At present, in order to prevent howling during karaoke, the sound receiving range (including the directionality of sound receiving) and sensitivity of karaoke microphones are limited. In order to quickly detect the howling characteristics at the early stage of self-excited howling and eliminate the howling, the embodiment of the present disclosure can be a high-sensitivity microphone, whose sensitivity is higher than that of the karaoke microphone. At the same time, in order to generate a phase difference between the audio emitted by the sound machine collected by the microphone and the audio emitted by the sound machine collected by the karaoke microphone, when setting the microphone, the distance between its distribution position and the sound machine is smaller than the distance between the karaoke microphone and the sound machine, so that the amplitude of the howling audio emitted by the sound machine collected by the microphone will be greater than the amplitude of the howling audio emitted by the sound machine collected by the karaoke microphone. In general, karaoke microphones are usually held by users and are located in several predictable fixed planes. Therefore, when placing microphones in the car, the distance between the plane where the multiple microphones are located and the plane where the car audio is located can be made much smaller than the distance between the plane where the karaoke microphones are located and the plane where the car audio is located. For example, the car audio is usually distributed on the upper end of the cabin wall, so multiple microphones can be evenly arranged on the cabin ceiling, so that the distance between the microphones and the audio is closer than the distance between the audio and the karaoke microphones. In addition, the microphones and the audio are distributed on different planes, which can also reduce mutual interference.

[0058] S102: If a howling feature is detected in the first audio signal, compare the first audio signal, the accompaniment audio signal and the second audio signal to determine a howling sub-audio signal related to the howling in the first audio signal.

[0059] The vehicle computer 210 determines whether to turn on the howling elimination function by detecting whether the first audio signal collected by the microphone 250 has a howling feature. If the vehicle computer 210 detects a howling feature in the first audio signal collected by the microphone 250, the howling elimination is started. Generally, there are many ways to detect whether there is a howling feature in an audio signal. The embodiment of the present disclosure exemplarily provides the following method to detect the howling feature.

[0060] In some embodiments, the method for detecting howling features includes: denoising the first audio signal to obtain a denoised first audio signal; extracting the autocorrelation function of the denoised first audio signal; if the autocorrelation function has at least two similar peaks, determining that the howling feature exists in the first audio signal.

[0061] When the vehicle computer 210 detects whether there is a howling feature in the first audio signal, it first denoises the first audio signal to reduce the noise signal that affects the analysis. For example, the first audio signal can be denoised by filtering. Then the autocorrelation function (Autocorrelation Function) of the denoised first audio signal is extracted. The autocorrelation function is a tool for analyzing signal repeatability and is mainly used in time series data analysis. For a signal, the autocorrelation function describes the similarity between the signal and itself in the time domain. In order to reduce the amount of calculation for extracting the autocorrelation function of the first audio signal, the FFT algorithm (Fast Fourier Transform) can be used to accelerate the calculation of the autocorrelation function. Because the FFT algorithm is a prior art, it will not be described here.

[0062] According to the above-described process of generating self-excited howling, it is not difficult to understand that when howling occurs in an audio segment, there are some stable, periodic sound wave vibrations, which will repeat on the time axis. Therefore, if a howling feature exists in an audio signal, the autocorrelation function of this audio signal will usually have several similar peaks. Therefore, when at least two similar peaks appear in the autocorrelation function of the first audio signal, it can be determined that the howling feature exists in the first audio signal.

[0063] The embodiment of the present disclosure can quickly detect whether there is a howling feature in the first audio signal by extracting the autocorrelation function of the first audio signal.

[0064] After detecting the presence of a howling feature in the first audio signal, the car machine 210 can determine the howling sub-audio signal related to the howling in the first audio signal by comparing the first audio signal, the accompaniment audio signal and the second audio signal. Specifically, because the microphone 250 has a high sensitivity and can collect most of the sounds in the car, the first audio signal collected by the microphone 250 includes the audio signals corresponding to the howling a, singing voice b and accompaniment c played by the speaker 230, and the human voice D emitted by the user 240 when singing, wherein the howling a, singing voice b and accompaniment c played by the speaker 230 belong to the sound emitted by the same sound source speaker 230. Since the sound receiving range (including the directionality of the sound receiving) and sensitivity of the karaoke microphone are usually restricted, the second audio signal collected by the karaoke microphone 220 includes the audio signals corresponding to the howling a emitted by the speaker 230 and the human voice D emitted by the user 240 when singing. The vehicle computer 210 can directly obtain the accompaniment audio signal corresponding to the accompaniment sound c, and then determine the howling sub-audio signal related to the howling a in the first audio signal by comparing the first audio signal, the accompaniment audio signal and the second audio signal.

[0065] In one embodiment, comparing a first audio signal, an accompaniment audio signal, and a second audio signal to determine a howling sub-audio signal related to howling in the first audio signal includes: performing sound source separation on the denoised first audio signal to obtain at least two first sub-audio signals; comparing the at least two first sub-audio signals with the accompaniment audio signal to determine a target first sub-audio signal that contains the accompaniment audio signal in the at least two first sub-audio signals; separating and eliminating the accompaniment audio signal from the target first sub-audio signal to obtain a second sub-audio signal; comparing the second audio signal with the second sub-audio signal, and extracting a sub-audio signal that is similar to the sub-audio signal of the second audio signal and has a larger amplitude from the second sub-audio signal as the howling sub-audio signal.

[0066] When the car computer 210 determines and extracts the howling sub-audio signal related to the howling a in the first audio signal, it first uses a sound source separation algorithm to separate the sub-audio signals corresponding to different sound sources in the first audio signal. For example, the Conv-TasNet algorithm can be used to separate the sound source of the first audio signal. The Conv-TasNet algorithm is a sound source separation algorithm based on a time-domain convolutional neural network. The audio components contained in the first audio signal have been introduced above, where the howling a, the singing voice b and the accompaniment sound c belong to the sound emitted by the same sound source, the sound 230, and the human voice D belongs to the sound emitted by another sound source, the user 240. Therefore, the car computer 210 can use the sound source separation algorithm to separate the first audio signal into two first sub-audio signals corresponding to different sound sources, wherein the sound source corresponding to one of the first sub-audio signals is the sound 230, and the sound source corresponding to the other first sub-audio signal is the user 240.

[0067] Because the audio played by the audio system 230 includes howling a, singing voice b and accompaniment sound c, the car computer 210 can determine that the first sub-audio signal including the accompaniment audio signal is the target first sub-audio signal by comparing the above two first sub-audios with the accompaniment audio signal. Theoretically, the target first sub-audio signal includes the audio signals corresponding to the howling a, singing voice b and accompaniment sound c respectively.

[0068] Then, the vehicle computer 210 separates and eliminates the accompaniment audio signal contained in the target first sub-audio signal based on the accompaniment audio signal, that is, eliminates the audio signal corresponding to the accompaniment sound c in the target first sub-audio signal to obtain a second sub-audio signal. Theoretically, the second sub-audio signal includes audio signals corresponding to the howling a and the singing voice b. For example, a real-time accompaniment elimination algorithm can be used to eliminate the accompaniment audio signal contained in the target first sub-audio signal. The real-time accompaniment elimination algorithm is based on the LMS (least-mean-square) recursive algorithm and adds the Fast Fourier Transform (FFT) acceleration technology to achieve real-time audio signal elimination.

[0069] The second sub-audio signal includes audio signals corresponding to howling a and singing voice b, respectively, and the second audio signal includes howling a and voice D emitted by user 240 when singing. Then, the vehicle computer 210 can compare the second sub-audio signal with the second audio signal, and find that there are similar sub-audio signals in both parties, that is, the sub-audio signal corresponding to howling a in the second sub-audio signal and the sub-audio signal corresponding to howling a in the second audio signal. Since the distance between the microphone 250 and the sound system 230 is smaller than the distance between the sound system 230 and the karaoke microphone 220, and the sensitivity of the microphone 250 is higher than that of the karaoke microphone 220, the audio signal corresponding to howling a collected by the microphone 250 is greater than the audio signal corresponding to howling a collected by the karaoke microphone 220, that is, the signal strength of the sub-audio signal corresponding to howling a in the second sub-audio signal is greater than the signal strength of the sub-audio signal corresponding to howling a in the second audio signal. Correspondingly, a sub-audio signal similar to the sub-audio signal of the second audio signal and with a larger amplitude is extracted from the second sub-audio signal, which is the sub-audio signal corresponding to howling a in the second sub-audio signal. For example, a template matching algorithm in signal processing may be used to extract the second sub audio signal and a sub audio signal with a larger amplitude that is similar to the second audio signal. The sub audio signal is the howling sub audio signal related to the howling in the first audio signal.

[0070] S103: Eliminate the audio signal related to the howling sub-audio signal from the second audio signal to obtain a human voice audio signal with howling eliminated.

[0071] In the embodiment of the present disclosure, the second audio signal includes audio signals corresponding to the howling a emitted by the sound system 230 and the human voice D emitted by the user 240 when singing, and the extracted howling sub-audio signal is the audio signal corresponding to the howling a in the first audio signal. The vehicle computer 210 eliminates the audio signal related to the howling sub-audio signal in the second audio signal based on the howling sub-audio signal, and obtains the human voice audio signal in the second audio signal where the howling is eliminated, that is, the audio signal corresponding to the human voice D emitted by the user 240 when singing in the second audio signal. Among them, the audio signal related to the howling sub-audio signal in the second audio signal refers to a signal similar to the howling sub-audio signal, that is, the audio signal corresponding to the howling a in the second audio signal. Since the audio signal corresponding to the howling a in the second audio signal and the howling sub-audio signal are obtained by recording the howling a by the karaoke microphone 220 and the pickup 250, respectively, the amplitudes of the two sides are different, but the audio features such as the spectrum and the tonality features are similar, so the vehicle computer 210 can obtain the audio signal corresponding to the remaining human voice D in the second audio signal by eliminating the audio signal related to the howling sub-audio signal in the second audio signal.

[0072] In one implementation, eliminating an audio signal related to a howling sub-audio signal in a second audio signal to obtain a human voice audio signal with howling eliminated includes: extracting audio features of the howling sub-audio signal; using an adaptive filtering algorithm to search for and eliminate audio signal components related to the audio features in the second audio signal to obtain a filtered audio signal; and recombining the filtered audio signals to obtain a human voice audio signal with howling eliminated.

[0073] Taking into account the different amplitudes of the audio signal corresponding to the howling a in the second audio signal and the howling sub-audio signal, the vehicle computer 210 can mainly extract the frequency characteristics of the howling sub-audio signal as the audio characteristics of the howling sub-audio signal, because under normal circumstances the frequency of the howling audio and the frequency of the human voice audio will also be quite different. Specifically, methods such as spectral analysis can be used to determine the frequency domain range and spectral shape of the howling sub-audio signal. For example, algorithms such as Fourier transform can be used to analyze the frequency distribution of the howling sub-audio signal to find its main frequency components in the frequency domain.

[0074] Then, an adaptive filtering algorithm is used to search and eliminate the audio signal components related to the audio features of the howling sub-audio signal in the second audio signal, and these audio signal components represent the audio components in the second audio signal that are similar to the audio features. Among them, the adaptive filtering algorithm is a signal processing method based on a feedback mechanism, which can dynamically adjust the parameters of the filter according to the correlation between the input signal and the reference signal to suppress or remove the signal components at a specific frequency in the input signal. After completing the adaptive filtering process, it is necessary to combine the filtered audio signal extracted by the adaptive filtering algorithm with the original audio signal, that is, to combine the filtered audio signal with the second audio signal, and recombining the filtered audio signal to obtain a pure human voice audio signal. The combination process generally includes resampling and reconstruction of the filtered signal to match it with the original audio signal. In this way, the howling audio signal in the second audio signal can be accurately and effectively eliminated, and a high-quality human voice audio signal emitted by the user's singing can be obtained.

[0075] The disclosed embodiment obtains a first audio signal collected by a pickup in the car, a second audio signal collected by a karaoke microphone, and a currently played accompaniment audio signal after the karaoke function is turned on. When a howling feature is detected in the first audio signal, the howling sub-audio signal related to the howling in the first audio signal is quickly and accurately determined by comparing the first audio signal, the accompaniment audio signal and the second audio signal. Finally, the audio signal related to the howling sub-audio signal is eliminated in the second audio signal to obtain a singing human voice audio signal with the howling eliminated in the second audio signal, thereby achieving the effect of eliminating the howling caused by karaoke in the car, so that the human voice audio signal and the accompaniment audio signal can be mixed and output later, thereby improving the user experience.

[0076] In some embodiments, the method further includes: denoising and enhancing the human voice audio signal, and mixing the enhanced human voice audio signal with the accompaniment audio signal to be played to obtain a final output mixed signal; and playing the audio corresponding to the mixed signal through the in-car audio system.

[0077] After obtaining the howling human voice audio signal, the car computer 210 will mix the human voice audio signal and the accompaniment audio signal as the final output. Before mixing and outputting the human voice audio signal and the accompaniment audio signal, the car computer 210 denoises and enhances the human voice audio signal to improve the quality and fidelity of the human voice audio. For example, the car computer 210 can use a speech enhancement algorithm based on an artificial neural network or a speech enhancement algorithm based on a wavelet transform to denoise and enhance the human voice audio signal. Then the car computer 210 mixes the denoised and enhanced human voice audio signal with the accompaniment audio signal to obtain a mixed signal as the final output, and sends the mixed signal to the audio 230, and plays the final output audio through the audio 230, thereby improving the user's experience of singing karaoke in the car.

[0078] Figure 3 The schematic diagram of the structure of the in-car karaoke howling elimination device provided by the embodiment of the present disclosure. The in-car karaoke howling elimination device can be a terminal as described in the above embodiment, or the in-car karaoke howling elimination device can be a component or assembly in the terminal. The in-car karaoke howling elimination device provided by the embodiment of the present disclosure can execute the processing flow provided by the in-car karaoke howling elimination method embodiment, such as Figure 3 As shown, the in-car karaoke howling elimination device 300 includes:

[0079] An acquisition module 301 is used to acquire a first audio signal collected by a car microphone, a second audio signal collected by a karaoke microphone, and an accompaniment audio signal currently being played;

[0080] The detection module 302 is configured to compare the first audio signal, the accompaniment audio signal and the second audio signal to determine a howling sub-audio signal related to the howling in the first audio signal if a howling feature is detected in the first audio signal;

[0081] The processing module 303 is used to eliminate the audio signal related to the howling sub-audio signal in the second audio signal to obtain a human voice audio signal with howling eliminated.

[0082] In some embodiments, the sensitivity of the microphone is higher than that of the karaoke microphone, and the distance between the microphone and the in-car audio system is smaller than the distance between the karaoke microphone and the in-car audio system.

[0083] In some embodiments, when detecting the howling feature, the detection module 302 is specifically used to denoise the first audio signal to obtain the denoised first audio signal; extract the autocorrelation function of the denoised first audio signal; if the autocorrelation function has at least two similar peaks, it is determined that the howling feature exists in the first audio signal.

[0084] In some embodiments, when the detection module 302 compares the first audio signal, the accompaniment audio signal and the second audio signal to determine the howling sub-audio signal related to the howling in the first audio signal, it is specifically used to separate the sound source of the denoised first audio signal to obtain at least two first sub-audio signals; compare the at least two first sub-audio signals with the accompaniment audio signal to determine a target first sub-audio signal that contains the accompaniment audio signal in the at least two first sub-audio signals; separate and eliminate the accompaniment audio signal from the target first sub-audio signal to obtain a second sub-audio signal; compare the second audio signal with the second sub-audio signal, and extract a sub-audio signal that is similar to the sub-audio signal of the second audio signal and has a larger amplitude from the second sub-audio signal as the howling sub-audio signal.

[0085] In some embodiments, when the processing module 303 eliminates the audio signal related to the howling sub-audio signal in the second audio signal to obtain the human voice audio signal with howling eliminated, it is specifically used to extract the audio features of the howling sub-audio signal; use an adaptive filtering algorithm to search and eliminate the audio signal components related to the audio features in the second audio signal to obtain a filtered audio signal; and recombine the filtered audio signals to obtain the human voice audio signal with howling eliminated.

[0086] In some embodiments, the device also includes a playback module 304, which is used to denoise and enhance the human voice audio signal, and mix the enhanced human voice audio signal with the accompaniment audio signal to be played to obtain a final output mixed signal; and play the audio corresponding to the mixed signal through the in-car audio system.

[0087] Figure 3 The in-car karaoke howling elimination device of the illustrated embodiment can be used to implement the technical solution of the above-mentioned method embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0088] Figure 4 Schematic diagram of the structure of an electronic device in the embodiment of the present disclosure. Figure 4 , which shows a structural schematic diagram of an electronic device 400 suitable for implementing the embodiments of the present disclosure. Figure 4 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0089] like Figure 4As shown, the electronic device 400 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage device 408 into a random access memory (RAM) 403 to implement the in-vehicle karaoke howling elimination method of the embodiment of the present disclosure. In RAM 403, various programs and data required for the operation of the electronic device 400 are also stored. The processing device 401, ROM 402, and RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0090] Typically, the following devices may be connected to the I / O interface 405: an input device 406 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 408 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 409. The communication device 409 may allow the electronic device 400 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 4 The electronic device 400 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0091] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart, thereby implementing the above in-car karaoke howling elimination method. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 409, or installed from the storage device 408, or installed from the ROM 402. When the computer program is executed by the processing device 401, the above functions defined in the method of the embodiment of the present disclosure are executed.

[0092] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, 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 the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0093] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0094] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0095] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device:

[0096] Acquire a first audio signal collected by a car microphone, a second audio signal collected by a karaoke microphone, and a currently playing accompaniment audio signal;

[0097] If a howling feature is detected in the first audio signal, the first audio signal, the accompaniment audio signal and the second audio signal are compared to determine a howling sub-audio signal related to the howling in the first audio signal;

[0098] The audio signal related to the howling sub-audio signal is eliminated from the second audio signal to obtain a human voice audio signal with howling eliminated.

[0099] Optionally, when the above one or more programs are executed by the electronic device, the electronic device may also execute other steps described in the above embodiments.

[0100] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including but not limited to 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 crew computer, partially on the crew computer, as a separate software package, partially on the crew 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 crew 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).

[0101] 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 disclosure. 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 implementations as replacements, 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.

[0102] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

[0103] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0104] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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 foregoing.

[0105] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0106] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0107] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims. In addition, the embodiments of the present disclosure also provide a computer-readable storage medium on which a computer program is stored, and the computer program is executed by a processor to implement the in-car karaoke howling elimination method described in the above embodiment.

[0108] The present disclosure also provides a vehicle, including: Figure 3 The in-car karaoke howling elimination device and / or Figure 4 Computer equipment shown.

[0109] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprises" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

Claims

1. A method for eliminating howling during karaoke in a car, characterized in that: include: Acquire a first audio signal collected by a car microphone, a second audio signal collected by a karaoke microphone, and a currently playing accompaniment audio signal; If a howling feature is detected in the first audio signal, comparing the first audio signal, the accompaniment audio signal, and the second audio signal to determine a howling sub-audio signal related to the howling in the first audio signal; The audio signal related to the howling sub-audio signal is eliminated from the second audio signal to obtain a human voice audio signal with howling eliminated.

2. The method according to claim 1, wherein The sensitivity of the microphone is higher than that of the karaoke microphone, and the distance between the microphone and the car audio is shorter than the distance between the karaoke microphone and the car audio.

3. The method according to claim 1, wherein The method for detecting the howling characteristics includes: performing denoising processing on the first audio signal to obtain a denoised first audio signal; Extracting an autocorrelation function of the denoised first audio signal; If at least two similar peaks appear in the autocorrelation function, it is determined that a howling feature exists in the first audio signal.

4. The method according to claim 3, wherein The comparing the first audio signal, the accompaniment audio signal, and the second audio signal to determine a howling sub-audio signal related to howling in the first audio signal includes: performing sound source separation on the denoised first audio signal to obtain at least two first sub-audio signals; comparing the at least two first sub audio signals with the accompaniment audio signal to determine a target first sub audio signal including the accompaniment audio signal among the at least two first sub audio signals; Separating and eliminating the accompaniment audio signal from the target first sub-audio signal to obtain a second sub-audio signal; The second audio signal is compared with the second sub-audio signal, and a sub-audio signal similar to the sub-audio signal of the second audio signal and having a larger amplitude is extracted from the second sub-audio signal as the howling sub-audio signal.

5. The method according to claim 1, wherein Eliminating the audio signal related to the howling sub-audio signal in the second audio signal to obtain a human voice audio signal with howling eliminated includes: extracting audio features of the howling sub-audio signal; Using an adaptive filtering algorithm to search for and eliminate audio signal components related to the audio feature in the second audio signal to obtain a filtered audio signal; The filtered audio signals are recombined to obtain the human voice audio signal with howling eliminated.

6. The method according to claim 1, wherein The method further comprises: Denoising and enhancing the human voice audio signal, and mixing the enhanced human voice audio signal with the accompaniment audio signal to be played to obtain a final output mixed signal; The audio corresponding to the mixed signal is played through the in-car audio system.

7. A device for eliminating howling during karaoke in a car, characterized in that: include: An acquisition module is used to acquire a first audio signal collected by an in-car microphone, a second audio signal collected by a karaoke microphone, and a currently playing accompaniment audio signal; a detection module configured to, if a howling feature is detected in the first audio signal, compare the first audio signal, the accompaniment audio signal, and the second audio signal to determine a howling sub-audio signal related to the howling in the first audio signal; The processing module is configured to eliminate the audio signal related to the howling sub-audio signal in the second audio signal to obtain a human voice audio signal with howling eliminated.

8. A computer device comprising: Memory; processor; as well as computer programs; The computer program is stored in the memory and configured to be executed by the processor to implement the method according to any one of claims 1 to 6.

9. 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 6 is implemented.

10. A vehicle, characterized in that: It includes the in-car karaoke howling elimination device as described in claim 7 and / or the computer equipment as described in claim 8.

Images