Microphone detection method and device, vehicle and storage medium

Abstract

The embodiment of the invention discloses a microphone detection method and device, a vehicle and a storage medium, the method is applied to the vehicle, the vehicle comprises a microphone, and the method comprises the following steps: obtaining a current audio signal collected by the microphone; according to the current audio signal and a reference audio signal, it is determined that the microphone is shielded by the target type of shielding object, and the reference audio signal is an audio signal obtained when the microphone is not shielded. According to the embodiment of the invention, the condition that the microphone is accidentally shielded in the use process can be rapidly and effectively detected, so that the detection of the abnormal state of the microphone is more comprehensive, and manual detection is not needed; and by determining the type of the shielding object, the user can quickly position the position of the shielded microphone according to the type of the shielding object, so that the shielding object can be removed in time.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of vehicle technology, and are related to but not limited to a microphone detection method, device, vehicle, and storage medium. Background Art

[0002] Microphones, as essential devices for audio pickup, are widely used in vehicles. Installing microphones in vehicles enables in-vehicle voice recognition systems to perform functions such as speech recognition. However, if the microphone is in an abnormal state during vehicle use, this can seriously affect the voice recognition effect. Therefore, it is necessary to monitor the status of vehicle microphones.

[0003] At present, the relevant technology mainly adopts manual periodic detection to detect vehicle microphones, and only detects hardware failures of the microphone (such as short circuit / open circuit, etc.). It can be seen that this detection method cannot fully detect the abnormal status of the microphone, and the cost of manual detection is relatively high. Summary of the Invention

[0004] In view of this, an embodiment of the present application provides a microphone detection method, device, vehicle and storage medium, which can quickly and effectively detect situations where the microphone is accidentally blocked during use without the need for manual detection.

[0005] An embodiment of the present application provides a microphone detection method, which is applied to a vehicle, wherein the vehicle includes a microphone. The method includes:

[0006] Acquire the current audio signal collected by the microphone;

[0007] It is determined that the microphone is blocked by a target type of blocking object according to the current audio signal and a reference audio signal, where the reference audio signal is an audio signal obtained when the microphone is not blocked.

[0008] In the above embodiment, since the installation location of the vehicle microphone is relatively hidden and the user is usually not aware of the installation location of the microphone, this solution can detect in real time whether the microphone is blocked and determine whether it is blocked by the target type of obstruction by comparing the current audio signal collected by the microphone with the reference audio signal collected when it is not blocked. This detection method can quickly and effectively detect situations where the microphone is accidentally blocked during use, making the detection of abnormal microphone status more comprehensive and eliminating the need for manual detection; and, by determining the type of obstruction, the user can quickly locate the position of the obstructed microphone by the type of obstruction, so that the obstruction can be cleared in time.

[0009] In some embodiments, determining, based on the current audio signal and the reference audio signal, that the microphone is blocked by a target type of blocking object includes:

[0010] It is determined that the microphone is blocked by the target type of blocking object according to a current frequency response curve corresponding to the current audio signal and a reference frequency response curve corresponding to the reference audio signal.

[0011] In the above embodiment, since different types of obstructions have different effects on the frequency response curve of the microphone, and changes in the frequency response curve can reflect very subtle changes in the audio signal, therefore, based on the current frequency response curve and the reference frequency response curve, slight occlusion changes can be detected, that is, the type of obstruction blocking the microphone can be accurately identified, thereby improving the accuracy of detecting obstructions.

[0012] In some embodiments, determining that the microphone is blocked by the target type of obstruction according to the current frequency response curve corresponding to the current audio signal and the reference frequency response curve corresponding to the reference audio signal includes:

[0013] comparing a current frequency response curve corresponding to the current audio signal with a reference frequency response curve corresponding to the reference audio signal, determining a signal attenuation frequency band in the current frequency response curve, wherein an amplitude attenuation value of the signal attenuation frequency band is greater than or equal to an amplitude attenuation threshold;

[0014] According to the signal attenuation frequency band and / or the amplitude attenuation value of the signal attenuation frequency band, it is determined that the microphone is blocked by the target type of obstruction, wherein different signal attenuation frequency bands and / or different amplitude attenuation values correspond to different types of obstructions.

[0015] In the above embodiment, since different types of obstructions have different effects on the amplitude of the frequency response curve of the microphone, the frequency band in which the amplitude attenuation value of the current frequency response curve is greater than or equal to the amplitude attenuation threshold compared with the reference frequency response curve is used as the signal attenuation frequency band, that is, whether the microphone is blocked can be quickly determined by the change in the amplitude of the curve; and, based on the signal attenuation frequency band and / or the amplitude attenuation value of the signal attenuation frequency band, not only can the type of obstruction blocking the microphone be flexibly determined, but the accuracy of identifying the type of obstruction is also improved.

[0016] In some embodiments, the method further comprises:

[0017] Correcting the signal attenuation frequency band according to the reference frequency response curve to obtain a corrected signal attenuation frequency band;

[0018] A revised current frequency response curve is obtained according to the revised signal attenuation frequency band.

[0019] In the above embodiment, after detecting that the microphone is blocked by the target type of obstruction, the signal attenuation frequency band in the current frequency response curve can also be corrected according to the reference frequency response curve, so as to obtain the corrected current frequency response curve according to the corrected model attenuation frequency band. Therefore, by correcting the current frequency response curve, the sound pickup effect of the microphone is effectively guaranteed, and the accuracy of voice recognition by the in-vehicle voice recognition system is ensured.

[0020] In some embodiments, the correcting the signal attenuation frequency band according to the reference frequency response curve to obtain the corrected signal attenuation frequency band includes:

[0021] Determining the number of segments according to the amplitude attenuation value of the signal attenuation frequency band, wherein the number of segments is positively correlated with the amplitude attenuation value of the signal attenuation frequency band;

[0022] Segmenting the signal attenuation frequency band according to the number of segments to obtain at least one segmented signal attenuation frequency point;

[0023] Determining a reference attenuation value corresponding to each of the signal attenuation frequency points according to the reference frequency response curve;

[0024] The signal attenuation frequency band is corrected according to the reference attenuation value corresponding to each signal attenuation frequency point to obtain the corrected signal attenuation frequency band.

[0025] In the above embodiment, the number of segments during correction is determined based on the amplitude attenuation value of the signal attenuation frequency band. The larger the amplitude attenuation value, the more segments there are. The more segments there are, the better the correction effect is, and the closer it is to the reference frequency response curve when the microphone is not blocked. This method can automatically adapt the number of segments according to the size of the amplitude attenuation value, effectively balancing the correction effect and the amount of correction calculation.

[0026] In some embodiments, the vehicle further comprises a speaker, and the method further comprises:

[0027] obtaining current environmental parameters of the vehicle, the current environmental parameters including the distance between the microphone and the speaker, and / or the noise level within the vehicle, wherein the current audio signal is obtained by the microphone collecting a sound signal played by the speaker;

[0028] The determining, based on the current audio signal and the reference audio signal, that the microphone is blocked by a target type of blocking object includes:

[0029] When at least one parameter of the current environmental parameters is greater than a corresponding threshold, compensating the current audio signal according to the current environmental parameters to obtain the compensated current audio signal;

[0030] It is determined that the microphone is blocked by the target type of blocking object according to the compensated current audio signal and the reference audio signal.

[0031] In the above embodiment, in order to avoid the detection result of the microphone being blocked by the target type of obstruction being caused by environmental factors such as distance and noise, therefore, before determining whether the microphone is blocked by the target type of obstruction based on the current audio signal and the reference audio signal, it is also possible to determine whether to compensate the current audio signal based on the distance between the microphone and the speaker, and / or the noise level in the vehicle. After determining that compensation is required, it is determined whether the microphone is blocked by the target type of obstruction based on the compensated current audio signal and the reference audio signal. This method effectively improves the detection accuracy when detecting that the microphone is blocked, and also improves the accuracy of determining the type of obstruction.

[0032] In some embodiments, when at least one parameter of the current environmental parameters is greater than a corresponding threshold, compensating the current audio signal according to the current environmental parameters to obtain the compensated current audio signal includes:

[0033] Obtaining a baseline attenuation value of the current audio signal corresponding to each parameter of the at least one parameter;

[0034] The current audio signal is compensated according to the reference attenuation value of the current audio signal corresponding to each parameter to obtain the compensated current audio signal.

[0035] In the above embodiment, different environmental parameters cause different degrees of signal attenuation on the current audio signal. By compensating the current audio signal through the benchmark attenuation value corresponding to each environmental parameter, the fineness of the compensated current audio signal can be improved in multiple dimensions, which is beneficial to the accuracy of subsequent detection when the microphone is blocked.

[0036] In some embodiments, the method further comprises:

[0037] Acquire abnormal data of detecting that the microphone is blocked, the abnormal data including at least one of the following: the number of times the microphone is blocked, and the blocking duration of the microphone;

[0038] An abnormality response operation for the microphone is performed according to the abnormality data.

[0039] In the above embodiment, abnormal data such as the number of times the microphone is blocked and the blocking duration reflect the abnormal situation of the microphone when it is blocked. Different abnormal response operations are performed based on these abnormal data, thereby improving the flexibility of the abnormal response operations performed.

[0040] In some embodiments, when the number of occlusions reaches a first number, the abnormal response operation is to record the number of occlusions and / or the type of the occlusion object each time the microphone is occluded; and / or,

[0041] If the number of obstructions reaches a second number consecutively within a preset time period, the abnormal response operation is to output a prompt message, wherein the prompt message is used to prompt the user to clear the obstruction blocking the microphone, and the second number of obstructions is greater than the first number of obstructions; and / or

[0042] When the blocking duration reaches a preset duration, the abnormal response operation is to reduce the audio signal strength of the microphone when it is woken up by voice.

[0043] In the above embodiment, different abnormal response operations are performed according to the number of occlusions. A higher number of occlusions indicates that the microphone has been blocked multiple times within a preset time period. In order to block the adverse effects on the microphone, a prompt to clear the obstruction is triggered. This method not only improves the flexibility of the abnormal response operation, but also can prompt the user to clean up in time when the number of occlusions is high, thereby reducing the impact of the obstruction on the microphone; and, when the occlusion time reaches the preset time, it indicates that the obstruction has not been cleared for a long time. In order to ensure the sensitivity of the microphone voice wake-up, an operation is performed to reduce the audio signal strength of the microphone being awakened by voice, thereby effectively ensuring that the microphone can be woken up normally.

[0044] In some embodiments, different types of obstructions correspond to different prompting modes of the prompt information, and the prompting mode is determined according to the degree of signal attenuation of the current audio signal compared to the reference audio signal.

[0045] In the above embodiment, since the degree of signal attenuation reflects to a certain extent that the microphone is blocked by different types of obstructions, different prompt methods are determined according to the degree of signal attenuation of the current audio signal compared with the reference audio signal, which means that different prompt methods can be determined based on the type of obstruction, effectively improving the flexibility of the prompt method when outputting prompt information.

[0046] An embodiment of the present application provides a microphone detection device, which is applied to a vehicle. The vehicle includes a microphone. The device includes:

[0047] An acquisition module, configured to acquire the current audio signal collected by the microphone;

[0048] A determination module is configured to determine whether the microphone is blocked by a target type of blocking object based on the current audio signal and a reference audio signal, wherein the reference audio signal is an audio signal obtained when the microphone is not blocked.

[0049] A vehicle provided in an embodiment of the present application includes a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the program, the method described in the embodiment of the present application is implemented.

[0050] The computer-readable storage medium provided in the embodiment of the present application stores a computer program thereon, and when the computer program is executed by a processor, the method described in the embodiment of the present application is implemented.

[0051] The computer program product provided in the embodiments of the present application includes a computer program, which implements the method described in the embodiments of the present application when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and, together with the specification, are used to illustrate the technical solutions of the present application.

[0053] Figure 1 is a schematic diagram of the structural layout of the vehicle audio system disclosed in an embodiment of the present application;

[0054] Figure 2 is a schematic diagram of the system architecture of the vehicle audio system disclosed in an embodiment of the present application;

[0055] Figure 3 This is a flowchart of a microphone detection method disclosed in an embodiment of the present application;

[0056] Figure 4 is a flow chart of another microphone detection method disclosed in an embodiment of the present application;

[0057] Figure 5A is a schematic diagram of a reference frequency response curve disclosed in an embodiment of the present application;

[0058] Figure 5B is a schematic diagram of the current frequency response curve disclosed in the embodiment of the present application;

[0059] Figure 6 is a flow chart of another microphone detection method disclosed in an embodiment of the present application;

[0060] Figure 7 is a flow chart of another microphone detection method disclosed in an embodiment of the present application;

[0061] Figure 81 is a flow chart of another microphone detection method disclosed in an embodiment of the present application;

[0062] Figure 9 is a structural diagram of a microphone detection device disclosed in an embodiment of the present application;

[0063] Figure 10 It is a structural schematic diagram of a vehicle disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0064] To make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the specific technical solutions of the present application will be further described in detail below in conjunction with the drawings in the embodiments of the present application. The following embodiments are used to illustrate the present application but are not intended to limit the scope of the present application.

[0065] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0066] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0067] It should be pointed out that the terms "first\second\third" involved in the embodiments of the present application are used to distinguish similar or different objects, and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0068] Microphones, as important devices for picking up audio, have been widely used in vehicles. By installing microphones in vehicles, in-vehicle voice recognition systems can implement functions such as voice recognition. However, if the microphone is in an abnormal state during vehicle use, it will seriously affect the voice recognition effect. Therefore, it is necessary to detect the status of the vehicle microphone. Currently, the relevant technology mainly uses manual regular detection to detect vehicle microphones, and only detects hardware faults of the microphone (such as short circuit / open circuit, etc.). It can be seen that this detection method cannot fully detect abnormal conditions of the microphone, and the cost of manual detection is high.

[0069] In view of this, embodiments of the present application provide a microphone detection method, device, vehicle, and storage medium. The method is applied to a vehicle, the vehicle including a microphone, and the method includes: obtaining a current audio signal collected by the microphone; determining whether the microphone is blocked by a target type of obstruction based on the current audio signal and a reference audio signal, wherein the reference audio signal is an audio signal obtained by the microphone when it is not blocked. Embodiments of the present application can quickly and effectively detect situations where the microphone is accidentally blocked during use, making the detection of abnormal microphone conditions more comprehensive and eliminating the need for manual detection; and, by determining the type of obstruction, the user can quickly locate the position of the obstructed microphone based on the type of obstruction, thereby promptly clearing the obstruction.

[0070] In order to make the purpose and technical solution of this application clearer and more intuitive, the following describes a microphone detection method disclosed in this application in conjunction with the accompanying drawings. It should be noted that this method can be applied to vehicles.

[0071] In the embodiment of the present application, the vehicle includes a microphone, and the microphone deployed in the vehicle may be one or more. Figure 1 , Figure 1 Schematic diagram of the structural layout of the vehicle audio system disclosed in the embodiment of the present application. Figure 1 The figure includes a microphone 10, and the number of microphones 10 includes a plurality of ( Figure 1 Four microphones are shown), and each microphone 10 can collect audio signals in the vehicle.

[0072] In the embodiment of the present application, the vehicle further includes a speaker, and the speaker deployed in the vehicle may be one or more. Figure 1 The speaker 20 is shown as including a plurality of speakers 20 ( Figure 1 Four speakers are shown), each speaker 20 can play a sound signal so that each microphone 10 in the vehicle can collect an audio signal.

[0073] Optionally, the microphones and speakers deployed on the vehicle can be in a combined form, that is, one microphone corresponds to one speaker, forming a combination of multiple groups of microphones and speakers, such as Figure 1 The combination of 4 sets of microphones and speakers is shown.

[0074] Optionally, the microphones and speakers deployed on the vehicle can also be in a non-combined form, that is, M microphones correspond to N speakers, and M and N are different, and M and N are integers greater than or equal to 1. For example, there is 1 microphone and 4 speakers deployed in the vehicle.

[0075] To further understand the functions of microphones and speakers in vehicle impact systems, Figure 2Detailed introduction to each module of the vehicle audio system and its corresponding functions. Figure 2 , Figure 2 is a schematic diagram of the system architecture of the vehicle audio system disclosed in the embodiment of this application, Figure 2 The vehicle audio system shown in FIG2 includes a main processor 201 , an audio processor 202 , a multi-channel amplifier 203 , a speaker 204 , a microphone 205 , a microphone processor 206 , and a display device 207 .

[0076] The main processor 201 is used to store the sweep frequency file and convert the sweep frequency file into a sweep frequency signal and send it to the audio processor 202. It should be noted that the sweep frequency file is used to indicate a sweep frequency sound source with a frequency that continuously changes within a specified frequency band, or it can be other preset sound sources with frequency changes. The sweep frequency file can be used to test the microphone 205.

[0077] The audio processor 202 is configured to send the sweep frequency signal to the multi-channel power amplifier 203 , and send the sweep frequency audio source corresponding to the sweep frequency file to the microphone processor 206 .

[0078] The multi-channel power amplifier 203 is used to receive the swept frequency signal sent from the audio processor 202 , amplify the swept frequency signal and send it to the speaker 204 .

[0079] The loudspeaker 204 is used to receive the swept frequency signal after being amplified by the multi-channel power amplifier 203 and convert the electrical signal corresponding to the swept frequency signal after being amplified by the power amplifier into a sound signal, thereby playing the sound signal.

[0080] The microphone 205 is used to collect the sound signal played by the speaker 204 and send the sound signal to the microphone processor 206.

[0081] The microphone processor 206 is used to perform echo cancellation processing on the sound signal collected by the microphone 205 according to the swept frequency sound source sent by the audio processor 202 to obtain an audio signal; it is also used to convert the audio signal into a frequency response curve and send the frequency response curve to the main processor 201.

[0082] The main processor 201 is further configured to analyze the frequency response curve sent by the microphone processor 206 to determine whether the microphone 205 is in an abnormal state, record the abnormal state of the microphone 205 , and send the abnormal state of the microphone 205 to the display device 207 .

[0083] The display device 207 is used to receive and display the abnormal status of the microphone 205 sent by the main processor 201 to prompt the user to clean the location of the microphone 205.

[0084] The following describes in detail a microphone detection method disclosed in this application, taking a vehicle as an example. Figure 3 , Figure 3 This is a flow chart of a microphone detection method disclosed in an embodiment of the present application. Figure 3 The method shown may include the following steps:

[0085] Step 301: The vehicle obtains a current audio signal collected by a microphone.

[0086] In an embodiment of the present application, a main processor in a vehicle may process a frequency sweep file to generate a frequency sweep signal. The frequency sweep signal may be a linear frequency sweep signal or a nonlinear frequency sweep signal, which is not limited in this application. A linear frequency sweep signal is used to indicate that the frequency increases linearly over time, i.e., the rate of change of the frequency is constant. Conversely, it is understood that a nonlinear frequency sweep signal is used to indicate that the frequency increases nonlinearly over time, i.e., the rate of change of the frequency is not constant.

[0087] For example, the generated sweep frequency signal can be a linear sweep frequency signal in the range of 20Hz-20kHz, the duration of the linear sweep frequency signal is 2s (that is, the frequency change is 19980Hz in 2 seconds), and the sound intensity is 75dB@1m, where @1m means that the sound intensity is measured at a distance of 1 meter from the sound source, that is, 75dB@1m means that the sound intensity measured at a distance of 1 meter from the sound source is 75 decibels.

[0088] In the embodiment of the present application, the speaker in the vehicle can play the sound signal corresponding to the swept frequency signal after being amplified by the power amplifier, so that the microphone in the vehicle can collect the corresponding audio signal. In other words, the current audio signal is obtained by collecting the sound signal played by the speaker from the microphone.

[0089] In some embodiments, the vehicle can control the speaker to play the sound signal at a preset playback frequency. It is understood that the preset playback frequency for the speaker to play the sound signal can be pre-set so that the microphone can collect the sound signal played by the speaker at the preset playback frequency to obtain the current audio signal. For example, the preset playback frequency can be set to play once every hour.

[0090] In some embodiments, the microphone deployed in the vehicle also includes an ambient microphone, which can be used to detect noise within the vehicle and, when the noise level is below a noise threshold, control the speaker to play a sound signal. It will be appreciated that to improve the detection of microphone anomalies, the speaker can be controlled to play a sound signal when the noise level within the vehicle is below the noise threshold to detect the microphone status. For example, the noise threshold can be set to 50dB, and the speaker will only be controlled to play a sound signal when the noise level is below 50dB.

[0091] In some embodiments, when a sound signal is detected to be controlled to play a speaker, the vehicle audio system may be controlled to pause the output of vehicle entertainment audio, etc., to avoid interfering with the detection result of the microphone.

[0092] It can be understood that the microphone in the above step 301 can be any microphone deployed in the vehicle.

[0093] In step 302 , the vehicle determines whether the microphone is blocked by a target type of blocking object based on the current audio signal and a reference audio signal, where the reference audio signal is an audio signal obtained when the microphone is not blocked.

[0094] In an embodiment of the present application, the vehicle can also control the speaker to play the corresponding sound signal when the detected microphone is in an unblocked state, so that the detected microphone collects the corresponding audio signal and uses the audio signal as the reference audio signal.

[0095] Optionally, the reference audio signal can be stored in the main processor of the vehicle, so that the main processor can subsequently compare the current audio signal with the reference audio signal to detect whether the microphone is blocked.

[0096] Optionally, after obtaining the current audio signal captured by the microphone, the vehicle can obtain a reference audio signal by reading the vehicle identification number (VIN). It should be noted that the VIN typically corresponds to a reference audio signal preset when the vehicle leaves the factory. By reading the VIN, the reference audio signal can be quickly obtained.

[0097] In an embodiment of the present application, the vehicle may match the current audio signal with a reference audio signal, and determine that the microphone is blocked if the current audio signal does not match the reference audio signal.

[0098] In some embodiments, the vehicle determines, based on a current audio signal and a reference audio signal, that the microphone is obscured by a target type of obstruction, including determining the microphone is obscured by the target type of obstruction based on an error value between audio signal characteristics of the current audio signal and the reference audio signal. The audio signal characteristics include at least one of a spectrum and a time domain, and the error values for the audio signal characteristics vary for different types of obstructions. In other words, the type of obstruction can be determined based on differences in the spectrum and / or time domain.

[0099] It should be noted that the spectrum is used to reflect the frequency attenuation of the current audio signal and the reference audio signal, while the time domain is used to reflect the amplitude, waveform, etc. of the current audio signal and the reference audio signal.

[0100] In some embodiments, after obtaining the current audio signal captured by the microphone, the current audio signal may be preprocessed to obtain a preprocessed current audio signal. Optionally, the preprocessing includes at least one of bandpass filtering and windowing. In other words, determining whether the microphone is obscured by a target type of obstruction based on the current audio signal and the reference audio signal includes: determining whether the microphone is obscured by a target type of obstruction based on the preprocessed current audio signal and the reference audio signal.

[0101] It should be noted that the implementation method of determining whether the microphone is blocked by the target type of obstruction based on the preprocessed current audio signal and the reference audio signal can be referred to the implementation method of determining whether the microphone is blocked by the target type of obstruction based on the current audio signal and the reference audio signal in the aforementioned embodiment, which will not be repeated here.

[0102] Bandpass filtering is used to filter out signals within a preset frequency range from the current audio signal. For example, low-frequency noise (such as engine roar and tire rolling noise) may be present in a vehicle. These noises are typically below 20 Hz (an example of a preset frequency range). Bandpass filtering can remove these low-frequency noises.

[0103] Windowing is used to indicate that the current audio signal is truncated in the time domain. It should be noted that the window function in the windowing process can include any one of a rectangular window, a Hanning window, a Hamming window, and a Blackman window, and this application does not limit this. The spectrum of the current audio signal usually leaks due to the finite length of the signal. Windowing can reduce spectrum leakage, making the spectrum smoother, thereby improving the accuracy of spectrum analysis. In other words, it can improve the accuracy of subsequent microphone detection results.

[0104] It can be seen that when implementing the embodiments of the present application, since the installation location of the vehicle microphone is relatively hidden and the user is usually not aware of the installation location of the microphone, this solution can detect in real time whether the microphone is blocked and determine whether it is blocked by the target type of obstruction by comparing the current audio signal collected by the microphone with the reference audio signal collected when it is not blocked. This detection method can quickly and effectively detect situations where the microphone is accidentally blocked during use, making the detection of abnormal microphone status more comprehensive and eliminating the need for manual detection; and, by determining the type of obstruction, the user can quickly locate the position of the obstructed microphone by the type of obstruction, so that the obstruction can be cleared in time.

[0105] Based on the description of the preceding embodiments, we have a basic understanding of how to detect microphone obstruction by a target type of obstruction. The following, combined with other diagrams, details how to determine whether a microphone is obstructed by a target type of obstruction based on the current audio signal and the reference audio signal. In other words, the implementation of step 302 described above can be seen in step 402 described below.

[0106] See Figure 4 , Figure 4 FIG. 1 is a flow chart of another microphone detection method disclosed in an embodiment of the present application. Figure 4 The method shown may include the following steps:

[0107] Step 401: The vehicle obtains a current audio signal collected by a microphone.

[0108] Regarding the implementation of step 401, reference may be made to the content of the aforementioned step 301, which will not be repeated here.

[0109] In step 402 , the vehicle determines whether the microphone is blocked by a target type of blocking object based on a current frequency response curve corresponding to the current audio signal and a reference frequency response curve corresponding to the reference audio signal.

[0110] It should be noted that in the embodiments of this application, a frequency response curve is an important tool for representing the response characteristics of a microphone to sound signals of different frequencies. A frequency response curve typically graphically displays the gain (or attenuation) of a microphone at various frequencies and is a key indicator for evaluating microphone performance. For example, it can be used to determine whether the microphone is obstructed and the type of obstruction.

[0111] In some embodiments, a microphone in a vehicle can collect the sound signal played by the speaker to obtain a corresponding current audio signal. After collecting the current audio signal, the current audio signal can also be subjected to frequency domain feature analysis to obtain a current frequency response curve corresponding to the current audio signal.

[0112] Optionally, the frequency domain feature analysis may analyze the frequency domain features of the current audio signal through fast Fourier transform, extract the amplitude spectrum of the current audio signal, and thereby obtain a current frequency response curve corresponding to the current audio signal.

[0113] In some implementations, the vehicle may perform frequency domain characteristic analysis on the reference audio signal to obtain a reference frequency response curve corresponding to the reference audio signal.

[0114] In some embodiments, a vehicle can also obtain a reference frequency response curve corresponding to a reference audio signal by reading the vehicle identification code. It should be noted that the vehicle identification code typically corresponds to a reference frequency response curve corresponding to a reference audio signal preset when the vehicle leaves the factory. By reading the vehicle identification code, the reference frequency response curve can be quickly obtained.

[0115] According to the description of the above embodiment, the reference audio signal is the audio signal obtained when the microphone is not blocked. It can be understood that the reference frequency response curve is the frequency response curve of the microphone when it is not blocked. For example, see Figure 5A , Figure 5A is a schematic diagram of the reference frequency response curve disclosed in the embodiment of this application, such as Figure 5A As shown, the curve represents the reference frequency response curve when the microphone is not blocked. The horizontal axis of the frequency response curve represents the frequency of the reference audio signal, and the unit is Hertz (Hz). The vertical axis represents the loudness of the reference audio signal when the microphone is not blocked, and the unit is decibel (dB).

[0116] According to the description of the above embodiment, the current audio signal is the audio signal acquired by the microphone in real time. It can be understood that the current frequency response curve is the frequency response curve when the microphone acquires the audio signal in real time. For example, see Figure 5B , Figure 5B is a schematic diagram of the current frequency response curve disclosed in the embodiment of this application, such as Figure 5B As shown, the curve represents the current frequency response curve when the microphone is blocked by the target type of obstruction. The horizontal axis of the frequency response curve represents the frequency of the current audio signal in Hertz (Hz), and the vertical axis represents the loudness of the current audio signal when the microphone is not blocked in decibels (dB).

[0117] In some embodiments, the vehicle can compare the current frequency response curve with the reference frequency response curve to obtain a difference curve, where the difference curve is used to indicate a curve in which signal attenuation exists in the current frequency response curve compared to the reference frequency response curve; based on the signal attenuation frequency band corresponding to the difference curve and / or the amplitude attenuation value corresponding to the signal attenuation frequency band, it is determined that the microphone is blocked by an obstruction of the target type.

[0118] It can be understood that if the current frequency response curve coincides with the reference frequency response curve, or if the amplitude attenuation value corresponding to the signal attenuation frequency band in the difference curve between the current frequency response curve and the reference frequency response curve is less than the amplitude attenuation threshold, it is determined that the microphone is not blocked.

[0119] It can be seen that the implementation of the embodiments of the present application can quickly and effectively detect situations where the microphone is accidentally blocked during use, making the detection of abnormal microphone conditions more comprehensive and eliminating the need for manual detection. In addition, by determining the type of obstruction, the user can quickly locate the position of the obstructed microphone based on the type of obstruction, thereby promptly removing the obstruction. Because different types of obstructions have different effects on the frequency response curve of the microphone, and changes in the frequency response curve can reflect very subtle changes in the audio signal, based on the current frequency response curve and the reference frequency response curve, subtle changes in obstruction can be detected, that is, the type of obstruction blocking the microphone can be accurately identified, thereby improving the accuracy of detecting obstructions.

[0120] Based on the description of the aforementioned embodiments, we have generally understood how to determine whether a microphone is obstructed by a target type of obstruction based on the current frequency response curve and the reference frequency response curve. The following, combined with other illustrations, further details how to determine whether a microphone is obstructed by a target type of obstruction based on the current frequency response curve and the reference frequency response curve, and how to modify the current audio signal captured by the microphone after determining that the microphone is obstructed.

[0121] See Figure 6 , Figure 6 This is a flow chart of another flow control method disclosed in the embodiment of this application. Figure 6 The method shown may include the following steps:

[0122] Step 601: The vehicle obtains a current audio signal collected by a microphone.

[0123] Regarding the implementation of step 601, reference may be made to the content of the aforementioned step 301, which will not be repeated here.

[0124] In step 602 , the vehicle compares a current frequency response curve corresponding to the current audio signal with a reference frequency response curve corresponding to the reference audio signal to determine a signal attenuation frequency band in the current frequency response curve.

[0125] In the embodiment of the present application, the amplitude attenuation value of the signal attenuation frequency band is greater than or equal to the amplitude attenuation threshold. It is understood that if the amplitude attenuation value of the signal attenuation frequency band is greater than or equal to the amplitude attenuation threshold, it indicates that the current audio signal is attenuated, which indicates that the microphone may be blocked by an obstruction.

[0126] As an example, the amplitude corresponding to the signal attenuation frequency band in the current frequency response curve can be expressed by Lmeasured(f), and the amplitude in the reference frequency response curve corresponding to the signal attenuation frequency band can be expressed by Lreference(f). Then, the amplitude attenuation value ΔL of the signal attenuation frequency band = Lreference(f)-Lmeasured(f).

[0127] In some embodiments, the vehicle may compare the current frequency response curve with a reference frequency response curve to obtain a difference curve, where the difference curve is used to indicate a curve in the current frequency response curve where signal attenuation exists compared to the reference frequency response curve; when the amplitude attenuation value corresponding to the difference curve is greater than or equal to an amplitude attenuation threshold, the signal attenuation frequency band in the current frequency response curve is determined.

[0128] It should be noted that in addition to determining whether there is a difference curve of signal attenuation between the current frequency response curve and the reference frequency response curve, it is also necessary to further determine the magnitude of the amplitude attenuation value corresponding to the difference curve. This can prevent the microphone from being affected by noise in the environment during the process of collecting audio signals, thereby causing misjudgment of whether the microphone is blocked by an obstruction.

[0129] In some embodiments, different signal attenuation frequency bands correspond to different amplitude attenuation thresholds, and a mapping relationship between signal attenuation frequency bands and amplitude attenuation thresholds can be pre-set for different types of obstructions.

[0130] It should be noted that the amplitude attenuation threshold can be customized by those skilled in the art and is not limited in this application. For example, if the amplitude attenuation threshold for the signal attenuation frequency band 2-4kHz is set to 10dB, if the amplitude attenuation value for the signal attenuation frequency band 2-4kHz is 20dB, it indicates that the microphone is blocked by obstruction 1; if the amplitude attenuation threshold for the signal attenuation frequency band 4-8kHz is set to 15dB, if the amplitude attenuation value for the signal attenuation frequency band 4-8kHz is 15dB, it indicates that the microphone is blocked by obstruction 2.

[0131] In step 603 , the vehicle determines whether the microphone is blocked by a target type of blocking object based on the signal attenuation frequency band and / or the amplitude attenuation value of the signal attenuation frequency band.

[0132] In the embodiment of the present application, different signal attenuation frequency bands and / or different amplitude attenuation values correspond to different types of obstructions. It is understood that each type of obstruction corresponds to a different signal attenuation frequency band and / or amplitude attenuation value.

[0133] Optionally, the amplitude of the attenuation start frequency point and the amplitude of the attenuation end frequency point of the signal attenuation frequency band in the frequency response curve may be used as the amplitude attenuation value of the signal attenuation frequency band.

[0134] It should be noted that those skilled in the art can pre-set a mapping relationship between each type of obstruction and the signal attenuation frequency band and / or the amplitude attenuation value corresponding to the signal attenuation frequency band, and this application does not limit this. In other words, the type of obstruction can be determined based on at least one of the signal attenuation frequency band and the amplitude attenuation value corresponding to the signal attenuation frequency band.

[0135] In some embodiments, different types of obstructions affect the frequency at which the current audio signal collected by the microphone attenuates. For example, a rough obstruction (e.g., clothing) affects the current audio signal collected by the microphone at a higher frequency range, such as 2-8 kHz, while a smooth obstruction (e.g., glass) affects the current audio signal collected by the microphone at a lower frequency range, such as 0-2 kHz. Therefore, the type of obstruction can be determined based on the frequency range corresponding to the signal attenuation frequency range.

[0136] As an example, Figure 5A and Figure 5B As shown, Figure 5B The current frequency response curve corresponding to the current audio signal in the mid-difference curve begins to attenuate from 3000 Hz, and the signal attenuation frequency band is 3000-20000 Hz. Assuming that the type of obstruction corresponding to 3000-20000 Hz is clothing, it is determined that the obstruction is clothing.

[0137] In some embodiments, different types of obstructions have different effects on the amplitude attenuation of the current audio signal collected by the microphone. For example, for obstructions with a relatively high surface density (e.g., T-shirts, plush seat covers), the amplitude attenuation of the current audio signal collected by the microphone is also higher (i.e., the higher the signal attenuation), such as 3000dB to -20dB. For obstructions with a relatively low surface density (e.g., sweaters), the amplitude attenuation of the current audio signal collected by the microphone is also lower (i.e., the lower the signal attenuation), such as the loudness attenuating from 3000dB to 1000dB. Therefore, the type of obstruction can be determined based on the amplitude attenuation value of the signal attenuation frequency band.

[0138] As an example, Figure 5A and Figure 5B As shown, Figure 5B The current frequency response curve corresponding to the current audio signal in the middle difference curve starts to attenuate from 3000 Hz. The amplitude attenuation value corresponding to the signal attenuation frequency band of 3000-20000 Hz is 3000 dB to -20 dB. Assuming that the type of obstruction corresponding to 3000 dB to -20 dB is a T-shirt, it is determined that the obstruction is a T-shirt.

[0139] In some implementations, different types of obstructions may have different frequencies and amplitude attenuation values that affect the signal attenuation of the current audio signal collected by the microphone.

[0140] As an example, Figure 5A and Figure 5B As shown, Figure 5BThe current frequency response curve corresponding to the current audio signal in the mid-difference curve starts to attenuate from 3000Hz, and the signal attenuation frequency band is 3000-20000Hz. Assuming that the type of obstruction corresponding to 3000-20000Hz is clothing, the obstruction can be further determined by combining the amplitude attenuation value corresponding to the signal attenuation frequency band, such as Figure 5B The amplitude attenuation value corresponding to the medium signal attenuation frequency band is 3000dB to -20dB, so it is determined that the obstruction is a T-shirt.

[0141] In step 604 , the vehicle corrects the signal attenuation frequency band according to the reference frequency response curve to obtain a corrected signal attenuation frequency band.

[0142] In an embodiment of the present application, after detecting that the microphone is blocked by a target type of obstruction, the signal attenuation band in the current frequency response curve can also be corrected according to the reference frequency response curve, thereby obtaining a corrected current frequency response curve, effectively ensuring the microphone's sound pickup effect.

[0143] In some embodiments, the signal attenuation frequency band is corrected based on a reference frequency response curve to obtain a corrected signal attenuation frequency band, including: determining the number of segments based on the amplitude attenuation value of the signal attenuation frequency band, wherein the number of segments is positively correlated with the amplitude attenuation value of the signal attenuation frequency band; segmenting the signal attenuation frequency band based on the number of segments to obtain at least one segmented signal attenuation frequency point; determining a reference attenuation value corresponding to each signal attenuation frequency point based on the reference frequency response curve; and correcting the signal attenuation frequency band based on the reference attenuation value corresponding to each signal attenuation frequency point to obtain a corrected signal attenuation frequency band. In this embodiment, the number of segments is used to indicate that the signal attenuation frequency band is divided into at least two frequency bands. Dividing the signal attenuation frequency band into at least two frequency bands facilitates point-by-point compensation for the amplitude corresponding to each segmented frequency point, thereby improving the efficiency of correction and compensation.

[0144] In this embodiment, the number of segments is positively correlated with the amplitude attenuation value within the signal attenuation frequency band. It can be understood that a larger amplitude attenuation value results in a greater number of segments, which in turn leads to better correction results, more closely approximating the baseline frequency response curve when the microphone is not obstructed. Conversely, a smaller amplitude attenuation value results in a smaller number of segments. Since the degree of signal attenuation is lower, reducing the number of segments can reduce the amount of correction calculations.

[0145] With this implementation, the number of segments during correction is determined based on the amplitude attenuation value of the signal attenuation frequency band. This approach can automatically adapt the number of segments based on the amplitude attenuation value, effectively balancing the correction effect and the amount of correction calculation.

[0146] In some embodiments, the signal attenuation frequency band is corrected based on a reference frequency response curve to obtain a corrected signal attenuation frequency band, including: determining the number of segments based on the target type of obstruction; segmenting the signal attenuation frequency band based on the number of segments to obtain at least one segmented signal attenuation frequency point; determining a reference attenuation value corresponding to each signal attenuation frequency point based on the reference frequency response curve; and correcting the signal attenuation frequency band based on the reference attenuation value corresponding to each signal attenuation frequency point to obtain a corrected signal attenuation frequency band. In this embodiment, the number of segments is determined based on the obstruction type, thereby balancing computing power and correction effect. In other words, for different types of obstructions, a selective correction method for fineness can be determined. For example, if the obstruction is caused by a smooth object, the attenuation amplitude is smaller, and the number of segments can be reduced.

[0147] Step 605 : The vehicle obtains a corrected current frequency response curve according to the corrected signal attenuation frequency band.

[0148] In the embodiment of the present application, after the signal attenuation frequency band in the current frequency response curve is corrected according to the reference frequency response curve, a corrected current frequency response curve is obtained. For example, see Figure 5A and Figure 5B ,Will Figure 5B The corrected current frequency response curve can be found in Figure 5A In other words, the purpose of the correction is to eliminate the influence of the obstruction on the audio signal as much as possible, so as to ensure the pickup effect of the microphone.

[0149] Step 606 : The vehicle obtains a corrected current audio signal according to the corrected current frequency response curve.

[0150] In the embodiment of the present application, the modified current frequency response curve can be converted into a modified current audio signal through inverse Fourier transform, that is, the frequency domain signal is converted back into a time domain signal.

[0151] It can be seen that the implementation of the embodiments of the present application can quickly and effectively detect situations where the microphone is accidentally blocked during use, making the detection of abnormal microphone conditions more comprehensive and eliminating the need for manual detection; and, by determining the type of obstruction, the user can quickly locate the position of the obstructed microphone based on the type of obstruction, thereby promptly removing the obstruction. Since different types of obstructions have different effects on the amplitude of the microphone's frequency response curve, the frequency band in which the amplitude attenuation value of the current frequency response curve is greater than or equal to the amplitude attenuation threshold compared to the reference frequency response curve is used as the signal attenuation band, that is, the change in the curve amplitude can be used to quickly determine whether the microphone is blocked; and, based on the signal attenuation band and / or the amplitude attenuation value of the signal attenuation band, not only can the type of obstruction blocking the microphone be flexibly determined, but the accuracy of identifying the obstruction type is also improved. After detecting that the microphone is blocked by the target type of obstruction, the signal attenuation band in the current frequency response curve can also be corrected according to the reference frequency response curve, so as to obtain the corrected current frequency response curve according to the corrected model attenuation band. Therefore, by correcting the current frequency response curve, the microphone's sound pickup effect is effectively guaranteed, ensuring the accuracy of voice recognition by the in-vehicle voice recognition system.

[0152] Based on the description of the aforementioned embodiment, we have basically understood the implementation method of determining whether the microphone is blocked by the target type of obstruction based on the current frequency response curve and the reference frequency response curve. In order to avoid the attenuation of the current audio signal collected by the microphone due to the distance between the speaker and the microphone, which affects the detection effect, it is also possible to compensate and correct the current audio signal after the microphone collects the current audio signal, and detect whether the microphone is blocked by the target type of obstruction based on the compensated and corrected current audio signal. The following will further introduce the implementation method of compensating and correcting the current audio signal before detecting whether the microphone is blocked by the target type of obstruction in combination with other illustrations.

[0153] See Figure 7 , Figure 7 This is a flow chart of another flow control method disclosed in the embodiment of this application. Figure 7 The method shown may include the following steps:

[0154] Step 701: The vehicle obtains a current audio signal collected by a microphone.

[0155] Regarding the implementation of step 701, reference may be made to the content of the aforementioned step 301, which will not be repeated here.

[0156] Step 702: The vehicle obtains current environmental parameters of the vehicle.

[0157] In an embodiment of the present application, in order to avoid the detection result of the microphone being blocked by the target type of obstruction due to environmental factors such as distance and noise, before determining whether the microphone is blocked by the target type of obstruction based on the current audio signal and the reference audio signal, the current environmental parameters of the vehicle can also be obtained to compensate the current audio signal through the current environmental parameters of the vehicle.

[0158] Optionally, the current environment parameter includes the distance between the microphone and the speaker. It is understandable that if the distance between the microphone and the speaker is far, the signal will be attenuated during the transmission process. Figure 1 The vehicle shown has multiple microphones and speakers. Assuming microphone 10 and speaker 20 are a group, microphone 10 can generally be used to detect the sound signal played by speaker 20. However, if speaker 20 fails, other speakers besides speaker 20 can also be used to detect microphone 10. Therefore, embodiments of the present application can obtain distance information between the microphone and the speaker before detecting that the microphone is blocked by a target type of obstruction based on the current audio signal and the reference audio signal.

[0159] Optionally, the current environmental parameters include the noise level in the vehicle. It can also be understood that when there is noise in the vehicle, there will be some attenuation of the signal during transmission. Therefore, the embodiment of the present application can obtain the current noise between the microphone and the speaker before detecting that the microphone is blocked by the target type of obstruction based on the current audio signal and the reference audio signal, and determine the noise level corresponding to the current noise based on a mapping relationship, and the mapping relationship includes the relationship between the preset noise and the preset noise level. It should be noted that those skilled in the art can set the mapping relationship as needed, and this application does not limit this.

[0160] It should be noted that the current environmental parameters of the vehicle obtained may include at least one of the above, and this application is not limited to this.

[0161] Step 703 : When at least one parameter of the current environmental parameters is greater than a corresponding threshold value, the vehicle compensates the current audio signal according to the current environmental parameters to obtain a compensated current audio signal.

[0162] According to the above steps, the current environmental parameters include the distance between the microphone and the speaker, and / or the noise level in the vehicle. In other words, the methods for triggering the compensation of the current audio signal based on the current environmental parameters may include the following:

[0163] Method 1: When the distance between the microphone and speaker of the vehicle is greater than a distance threshold, the current audio signal is compensated based on the distance between the microphone and speaker to obtain a compensated current audio signal. It is understood that when the distance is greater than the distance threshold, the compensation of the current audio signal is triggered. The distance threshold can be any value and is not limited in this application.

[0164] Method 2: When the noise level within the vehicle exceeds a noise level threshold, the current audio signal is compensated based on the noise level within the vehicle to obtain a compensated current audio signal. It will be understood that when the noise level exceeds the noise level threshold, the compensation of the current audio signal is triggered. The noise level can be set at any level and is not limited in this application.

[0165] Method 3: When the distance between the microphone and the speaker of the vehicle is greater than a distance threshold, and the noise level within the vehicle is greater than a noise level threshold, the current audio signal is compensated based on the distance between the microphone and the speaker and the noise level within the vehicle to obtain a compensated current audio signal. It will be understood that the compensation of the current audio signal is only triggered when both the distance and the noise level are greater than the corresponding thresholds.

[0166] It should be noted that the method of triggering the compensation of the current audio signal based on the current environmental parameters can adopt any one of the above three methods, and this application is not limited to this.

[0167] In some embodiments, when at least one of the current environmental parameters of a vehicle is greater than a corresponding threshold, the vehicle compensates the current audio signal based on the current environmental parameters to obtain a compensated current audio signal. This includes: the vehicle obtaining a baseline attenuation value for the current audio signal corresponding to each of the at least one parameter; and compensating the current audio signal based on the baseline attenuation value for the current audio signal corresponding to each parameter to obtain the compensated current audio signal. With this embodiment, different environmental parameters cause different degrees of signal attenuation on the current audio signal. Compensating the current audio signal using the baseline attenuation value corresponding to each environmental parameter can improve the sophistication of the compensated current audio signal in multiple dimensions, facilitating the accuracy of subsequent detection when the microphone is blocked.

[0168] According to the aforementioned embodiment, the current audio signal can be compensated based on at least one of the aforementioned current environmental parameters. Therefore, the vehicle can compensate the current audio signal based on the baseline attenuation value of the current audio signal corresponding to each of the at least one parameter in the following manners:

[0169] Method 1: The vehicle compensates the current audio signal based on a baseline attenuation value of the current audio signal corresponding to the distance between the microphone and the speaker. The baseline attenuation value can be determined based on a mapping relationship between a preset distance and a preset baseline attenuation value of the current audio signal.

[0170] Method 2: The vehicle compensates the current audio signal based on a baseline attenuation value of the current audio signal corresponding to the noise level in the vehicle. The baseline attenuation value can be determined based on a mapping relationship between a preset noise level and a preset baseline attenuation value of the current audio signal.

[0171] Method 3: The vehicle compensates the current audio signal according to a first reference attenuation value of the current audio signal corresponding to the distance between the microphone and the speaker, and a second reference attenuation value of the current audio signal corresponding to the noise level in the vehicle.

[0172] It should be noted that, according to the baseline attenuation value of the current audio signal corresponding to each parameter in the at least one parameter, the current audio signal can be compensated in any of the three aforementioned ways, and this application does not limit this.

[0173] It should be noted that those skilled in the art can customize the above mapping relationship as needed, and this application does not limit this.

[0174] In step 704 , the vehicle determines, based on the compensated current audio signal and the reference audio signal, whether the microphone is blocked by an obstruction of the target type.

[0175] In some embodiments, the vehicle determines that the microphone is blocked by the target type of obstruction based on the compensated current audio signal and the reference audio signal, including: determining that the microphone is blocked by the target type of obstruction based on the compensated current frequency response curve corresponding to the compensated current audio signal and the reference frequency response curve corresponding to the reference audio signal.

[0176] It should be noted that the implementation method of determining whether the microphone is blocked by the target type of obstruction based on the compensated current audio signal and the reference audio signal can be referred to the implementation method of determining whether the microphone is blocked by the target type of obstruction based on the current audio signal and the reference audio signal in the aforementioned embodiment, which will not be repeated here.

[0177] It can be seen that the implementation of the embodiments of the present application can quickly and effectively detect situations where the microphone is accidentally blocked during use, making the detection of abnormal microphone conditions more comprehensive and eliminating the need for manual detection. In addition, by determining the type of obstruction, the user can quickly locate the position of the obstructed microphone based on the type of obstruction, thereby promptly removing the obstruction. Whether to compensate the current audio signal can be determined based on the distance between the microphone and the speaker, and / or the noise level in the vehicle. After determining that compensation is required, the microphone can be determined to be blocked by the target type of obstruction based on the compensated current audio signal and the reference audio signal. This method effectively improves the detection accuracy when detecting microphone obstruction and also improves the accuracy of determining the type of obstruction.

[0178] In some embodiments, after detecting that the microphone is blocked by a target type of blocking object, a graded response may be performed based on the blocking situation. The following will describe in detail the implementation of the graded response based on the blocking situation in conjunction with other figures.

[0179] See Figure 8 , Figure 8 FIG. 1 is a flow chart of another flow control method disclosed in an embodiment of the present application. Figure 8 The method shown may include the following steps:

[0180] Step 801: The vehicle obtains a current audio signal collected by a microphone.

[0181] In step 802 , the vehicle determines whether the microphone is blocked by a target type of blocker based on the current audio signal and a reference audio signal, where the reference audio signal is an audio signal obtained when the microphone is not blocked.

[0182] Regarding the implementation of steps 801 to 802, reference may be made to the contents of steps 301 to 302 above, which will not be repeated here.

[0183] In step 803 , the vehicle obtains abnormal data indicating that the microphone is blocked.

[0184] In the embodiment of the present application, the abnormal data is used to reflect the abnormal situation that the microphone is blocked.

[0185] Optionally, the abnormal data includes the number of times the microphone is blocked.

[0186] Optionally, the abnormal data includes an occlusion duration of the microphone being blocked.

[0187] It should be noted that the abnormal data of the microphone being blocked may be at least one of the above-mentioned blocking times and blocking duration.

[0188] Step 804 : The vehicle performs an abnormal response operation for the microphone based on the abnormal data.

[0189] In an embodiment of the present application, the vehicle can generate an abnormal response operation based on the abnormal data of the microphone being blocked, and perform the abnormal response operation for the microphone. It can be understood that the number of times the microphone is blocked, the duration of the blockage, etc. reflect the different blocking conditions of the microphone. For example, when the microphone is severely blocked, it is necessary to prompt the user to clear the obstruction on the microphone. In other words, different response operations can be performed based on the abnormal data to the blocking condition of the microphone. The following implementation methods for the abnormal response operation of the microphone may include the following:

[0190] In Method 1, when the number of occlusions reaches the first count, the abnormal response operation is to record the number of occlusions and / or the type of obstruction each time the microphone was obstructed. For example, if the first count is 1 and the number of times the microphone was obstructed is only once, since the number of occlusions is relatively low, at least one of the number of occlusions and the type of obstruction each time the microphone was obstructed can be recorded first. The user can then view the occlusion information recorded in the log.

[0191] In method 2, if the number of consecutive obstructions reaches a second count within a preset duration, the abnormal response operation is to output a prompt message, which prompts the user to clear the obstruction. The second count is greater than the first count. For example, if the second count is 3, the preset duration is 1 hour, and the number of consecutive detections of microphone obstruction reaches 3 within 1 hour, it indicates that the microphone is frequently obstructed, and a prompt message is required to prompt the user to clear the obstruction.

[0192] Optionally, the current frequency response curve corresponding to the current audio signal is compared with the reference frequency response curve corresponding to the reference audio signal. If there is no signal attenuation frequency band in the current frequency response curve, or the current frequency response curve and the reference frequency response curve are consistent or similar, it indicates that the obstruction has been cleared.

[0193] In the above-mentioned methods 1 and 2, different abnormal response operations are performed according to the number of occlusions. The higher the number of occlusions, the more times the microphone has been blocked within the preset time. In order to block the adverse effects on the microphone, a prompt to clear the obstruction is triggered. This method not only improves the flexibility of the abnormal response operation, but also can prompt the user to clean up in time when the number of occlusions is high, thereby reducing the impact of the obstruction on the microphone.

[0194] It should be noted that the first number and the second number can be any preset values, and this application does not limit this.

[0195] In method 3, if the occlusion duration reaches a preset value, the abnormal response action is to reduce the audio signal strength of the microphone wake-up sound. Optionally, the vehicle can also send the reduced audio signal strength of the microphone wake-up sound to the cloud to prompt the vehicle manufacturer to optimize the microphone layout design.

[0196] For example, assuming the preset duration is 20 hours, and assuming that the microphone is detected to be blocked for 20 hours, it reflects to a certain extent that the user is inconvenient or forgets to clear the obstruction, causing the microphone to be blocked for a long time. At this time, the audio signal strength of the microphone being awakened by voice is automatically reduced.

[0197] In the above method 3, when the occlusion duration reaches the preset duration, it means that the obstruction has not been cleared for a long time. In order to ensure the sensitivity of the microphone voice wake-up, the operation of reducing the audio signal strength of the microphone being awakened by voice is performed, effectively ensuring that the microphone can be awakened normally.

[0198] It should be noted that the abnormal response operation can be any one or more of the above-mentioned methods.

[0199] In some embodiments, the prompt method for outputting the prompt information in the aforementioned method 2 can be determined based on the type of obstruction. Specifically, the prompt method for outputting the prompt information corresponding to the target type of obstruction can be determined based on a mapping between preset obstruction types and preset prompt methods. In other words, different types of obstructions correspond to different prompt methods, and the prompt method is determined based on the degree of signal attenuation of the current audio signal compared to the reference audio signal.

[0200] As an example, clothing-type obstructions can alert the user by outputting a prompt message "The microphone is blocked by clothing, please clean the clothing" on the vehicle's display module; if the user's body accidentally blocks the microphone, the vehicle's lighting module's warning light or the audio module's buzzer can be used to alert the user that the microphone is blocked.

[0201] As another example, the same prompting method can be used to indicate that the microphone is blocked with different prompting effects. For example, if clothing is blocking the microphone, the buzzer can be controlled to prompt for 5 seconds, and if the user's body is blocking the microphone, the buzzer can be controlled to prompt for 2 seconds.

[0202] With this implementation, since the degree of signal attenuation reflects to a certain extent whether the microphone is blocked by different types of obstructions, different prompt methods are determined based on the degree of signal attenuation of the current audio signal compared to the reference audio signal, indicating that different prompt methods can be determined based on the type of obstruction, effectively improving the flexibility of the prompt method when outputting prompt information.

[0203] As can be seen, the implementation of the embodiments of the present application can quickly and effectively detect situations where the microphone is accidentally blocked during use, making the detection of abnormal microphone conditions more comprehensive and eliminating the need for manual inspection. Furthermore, by determining the type of obstruction, the user can quickly locate the position of the obstructed microphone based on the type of obstruction, thereby promptly removing the obstruction. Abnormal data such as the number of times the microphone is blocked and the duration of the obstruction reflect abnormal conditions when the microphone is blocked. Using this abnormal data, different abnormal response operations can be executed, increasing the flexibility of the abnormal response operations performed.

[0204] It should be understood that, although the various steps in the above-mentioned flowcharts are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless clearly stated herein, the execution of these steps is not strictly restricted in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the above-mentioned flowcharts may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps. In addition, the above-mentioned multiple embodiments can be implemented independently or in combination with each other, and are not limited thereto.

[0205] Based on the aforementioned embodiments, embodiments of the present application provide a microphone detection device, which is applied to the vehicle described in the aforementioned embodiments, wherein the vehicle includes a microphone. The device includes various modules and units included in each module, and can be implemented using a processor; of course, it can also be implemented using specific logic circuits. During implementation, the processor can be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP), or a field programmable gate array (FPGA).

[0206] See Figure 9 , Figure 9 is a schematic structural diagram of a microphone detection device disclosed in an embodiment of the present application, such as Figure 9 The device shown includes an acquisition module 901 and a determination module 902 .

[0207] The acquisition module 901 is used to acquire the current audio signal collected by the microphone.

[0208] The determination module 902 is configured to determine whether the microphone is blocked by a target type of blocker based on the current audio signal and a reference audio signal, where the reference audio signal is an audio signal obtained when the microphone is not blocked.

[0209] In some embodiments, the determination module 902 is specifically configured to:

[0210] It is determined that the microphone is blocked by a target type of blocking object according to a current frequency response curve corresponding to the current audio signal and a reference frequency response curve corresponding to the reference audio signal.

[0211] In some embodiments, the determining module 902 is further configured to:

[0212] Comparing a current frequency response curve corresponding to the current audio signal with a reference frequency response curve corresponding to the reference audio signal, determining a signal attenuation frequency band in the current frequency response curve, wherein an amplitude attenuation value of the signal attenuation frequency band is greater than or equal to an amplitude attenuation threshold;

[0213] It is determined that the microphone is blocked by a target type of obstruction according to the signal attenuation frequency band and / or the amplitude attenuation value of the signal attenuation frequency band, wherein different signal attenuation frequency bands and / or different amplitude attenuation values correspond to different types of obstructions.

[0214] In some embodiments, the apparatus further comprises a correction module;

[0215] The correction module is used to correct the signal attenuation frequency band according to the reference frequency response curve to obtain a corrected signal attenuation frequency band; and to obtain a corrected current frequency response curve according to the corrected signal attenuation frequency band.

[0216] In some embodiments, the correction module is specifically configured to:

[0217] The number of segments is determined according to the amplitude attenuation value of the signal attenuation frequency band, and the number of segments is positively correlated with the amplitude attenuation value of the signal attenuation frequency band;

[0218] Segmenting the signal attenuation frequency band according to the number of segments to obtain at least one signal attenuation frequency point after segmentation;

[0219] According to the reference frequency response curve, determine the reference attenuation value corresponding to each signal attenuation frequency point;

[0220] The signal attenuation frequency band is corrected according to the reference attenuation value corresponding to each signal attenuation frequency point to obtain a corrected signal attenuation frequency band.

[0221] In some embodiments, the vehicle further comprises a speaker;

[0222] The acquisition module 901 is also used to obtain the current environmental parameters of the vehicle, which include the distance between the microphone and the speaker, and / or the noise level in the vehicle. The current audio signal is obtained by the microphone collecting the sound signal played by the speaker.

[0223] The determination module 902 is further specifically configured to:

[0224] When at least one parameter of the current environmental parameters is greater than a corresponding threshold, compensating the current audio signal according to the current environmental parameters to obtain a compensated current audio signal;

[0225] It is determined that the microphone is blocked by a target type of blocking object according to the compensated current audio signal and the reference audio signal.

[0226] In some embodiments, the determining module 902 is further configured to:

[0227] Obtaining a baseline attenuation value of a current audio signal corresponding to each parameter of at least one parameter;

[0228] The current audio signal is compensated according to the reference attenuation value of the current audio signal corresponding to each parameter to obtain a compensated current audio signal.

[0229] In some embodiments, the acquisition module 901 is further configured to acquire abnormal data when the microphone is detected to be blocked, where the abnormal data includes at least one of the following: the number of times the microphone is blocked, and the duration of the blocking.

[0230] The device also includes a processing module;

[0231] The processing module is used to execute an abnormal response operation for the microphone according to the abnormal data.

[0232] In some embodiments, when the number of occlusions reaches a first number, the abnormal response operation is to record the number of occlusions and / or the type of occlusion object each time the microphone is occluded; and / or,

[0233] If the number of obstructions reaches a second number consecutively within a preset time period, the abnormal response operation is to output a prompt message, which is used to prompt the user to clear the obstruction blocking the microphone, and the second number is greater than the first number; and / or

[0234] When the occlusion duration reaches a preset duration, the abnormal response operation is to reduce the audio signal strength of the microphone when it is woken up by voice.

[0235] In some embodiments, different types of obstructions correspond to different prompting methods for prompt information, and the prompting method is determined according to the degree of signal attenuation of the current audio signal compared to the reference audio signal.

[0236] It should be noted that the division of modules in the microphone detection device shown in the embodiment of the present application is schematic and is merely a logical function division. There may be other division methods in actual implementation.

[0237] The embodiment of the present application provides a vehicle, please refer to Figure 10 , Figure 10This is a schematic diagram of the structure of a vehicle disclosed in the embodiment of this application. Figure 10 As shown, the vehicle includes:

[0238] A memory 1001 storing executable program code;

[0239] a processor 1002 coupled to the memory 1001;

[0240] The processor 1002 calls the executable program code stored in the memory 1001 to execute any one of the microphone detection methods in the above method embodiments.

[0241] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, part or all of the steps in any one of the microphone detection methods provided in the above embodiments are implemented.

[0242] An embodiment of the present application further provides a computer program product, including a computer program, which, when executed by a processor, implements part or all of the steps in any one of the microphone detection methods provided in the above embodiments.

[0243] Those skilled in the art will understand that Figure 10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the vehicle to which the solution of the present application is applied. The specific vehicle may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0244] It should be noted that the descriptions of the above embodiments of the apparatus, vehicle, computer-readable storage medium, and computer program product are similar to the descriptions of the above-mentioned method embodiments and have similar beneficial effects as the method embodiments. For technical details not disclosed in the embodiments of the apparatus, vehicle, computer-readable storage medium, and computer program product of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0245] It should be understood that "one embodiment" or "an embodiment" or "some embodiments" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" or "in some embodiments" appearing throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The above-mentioned serial numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments. The above description of the various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other. For the sake of brevity, they will not be repeated here.

[0246] The term "and / or" in this article is only a description of the association relationship between associated objects, indicating that there can be three relationships. For example, object A and / or object B can mean: object A exists alone, object A and object B exist at the same time, and object B exists alone.

[0247] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0248] In the several embodiments provided in this application, it should be understood that the disclosed methods, devices and vehicles can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of the modules above is only a logical function division. There may be other division methods in actual implementation, such as: multiple modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0249] Those skilled in the art will understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM), magnetic disks or optical disks, and other media that can store program codes.

[0250] The methods disclosed in the several method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0251] The features disclosed in the several device embodiments provided in this application can be arbitrarily combined without conflict to obtain new device embodiments.

[0252] The above is merely an embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A microphone detection method, characterized in that: Applied to a vehicle, the vehicle including a microphone, the method comprising: Acquire the current audio signal collected by the microphone; It is determined that the microphone is blocked by a target type of blocking object according to the current audio signal and a reference audio signal, where the reference audio signal is an audio signal obtained when the microphone is not blocked.

2. The method according to claim 1, characterized in that The determining, based on the current audio signal and the reference audio signal, that the microphone is blocked by a target type of blocking object includes: It is determined that the microphone is blocked by the target type of blocking object according to a current frequency response curve corresponding to the current audio signal and a reference frequency response curve corresponding to the reference audio signal.

3. The method according to claim 2, characterized in that The determining, based on the current frequency response curve corresponding to the current audio signal and the reference frequency response curve corresponding to the reference audio signal, that the microphone is blocked by the target type of blocking object includes: comparing a current frequency response curve corresponding to the current audio signal with a reference frequency response curve corresponding to the reference audio signal, determining a signal attenuation frequency band in the current frequency response curve, wherein an amplitude attenuation value of the signal attenuation frequency band is greater than or equal to an amplitude attenuation threshold; According to the signal attenuation frequency band and / or the amplitude attenuation value of the signal attenuation frequency band, it is determined that the microphone is blocked by the target type of obstruction, wherein different signal attenuation frequency bands and / or different amplitude attenuation values correspond to different types of obstructions.

4. The method according to claim 3, characterized in that The method further comprises: Correcting the signal attenuation frequency band according to the reference frequency response curve to obtain a corrected signal attenuation frequency band; A revised current frequency response curve is obtained according to the revised signal attenuation frequency band.

5. The method according to claim 4, characterized in that The step of correcting the signal attenuation frequency band according to the reference frequency response curve to obtain the corrected signal attenuation frequency band includes: Determining the number of segments according to the amplitude attenuation value of the signal attenuation frequency band, wherein the number of segments is positively correlated with the amplitude attenuation value of the signal attenuation frequency band; Segmenting the signal attenuation frequency band according to the number of segments to obtain at least one segmented signal attenuation frequency point; Determining a reference attenuation value corresponding to each of the signal attenuation frequency points according to the reference frequency response curve; The signal attenuation frequency band is corrected according to the reference attenuation value corresponding to each signal attenuation frequency point to obtain the corrected signal attenuation frequency band.

6. The method according to claim 1, characterized in that The vehicle further includes a speaker, and the method further includes: obtaining current environmental parameters of the vehicle, the current environmental parameters including the distance between the microphone and the speaker, and / or the noise level within the vehicle, wherein the current audio signal is obtained by the microphone collecting a sound signal played by the speaker; The determining, based on the current audio signal and the reference audio signal, that the microphone is blocked by a target type of blocking object includes: When at least one parameter of the current environmental parameters is greater than a corresponding threshold, compensating the current audio signal according to the current environmental parameters to obtain the compensated current audio signal; It is determined that the microphone is blocked by the target type of blocking object according to the compensated current audio signal and the reference audio signal.

7. The method according to claim 6, characterized in that When at least one parameter of the current environmental parameters is greater than a corresponding threshold value, compensating the current audio signal according to the current environmental parameters to obtain the compensated current audio signal includes: Obtaining a baseline attenuation value of the current audio signal corresponding to each parameter of the at least one parameter; The current audio signal is compensated according to the reference attenuation value of the current audio signal corresponding to each parameter to obtain the compensated current audio signal.

8. The method according to any one of claims 1 to 7, characterized in that The method further comprises: Acquire abnormal data of detecting that the microphone is blocked, the abnormal data including at least one of the following: the number of times the microphone is blocked, and the blocking duration of the microphone; An abnormality response operation for the microphone is performed according to the abnormality data.

9. The method according to claim 8, characterized in that When the number of obstructions reaches the first number, the abnormal response operation is to record the number of obstructions and / or the type of obstruction that obstructs the microphone each time; and / or, If the number of obstructions reaches a second number consecutively within a preset time period, the abnormal response operation is to output a prompt message, the prompt message being used to prompt the user to clear the obstruction blocking the microphone, and the second number of obstructions is greater than the first number of obstructions; and / or, When the blocking duration reaches a preset duration, the abnormal response operation is to reduce the audio signal strength of the microphone when it is woken up by voice.

10. The method according to claim 9, characterized in that Different types of obstructions correspond to different prompting modes of the prompt information, and the prompting mode is determined according to the degree of signal attenuation of the current audio signal compared to the reference audio signal.

11. A microphone detection device, characterized in that: Applied to a vehicle, the vehicle includes a microphone, and the device includes: An acquisition module, configured to acquire the current audio signal collected by the microphone; A determination module is configured to determine whether the microphone is blocked by a target type of blocking object based on the current audio signal and a reference audio signal, wherein the reference audio signal is an audio signal obtained when the microphone is not blocked.

12. A vehicle comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, wherein: When the processor executes the program, the steps of the method according to any one of claims 1 to 10 are implemented.

13. 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 10 is implemented.

14. A computer program product, characterized in that The invention comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 10 is implemented.

Images