Detection method and device of audio input module and storage medium
阅读说明：本技术 音频输入模组的检测方法及装置、存储介质 (Detection method and device of audio input module and storage medium ) 是由 刘金刚 于 2019-09-26 设计创作，主要内容包括：本公开是关于一种音频输入模组的检测方法及装置、存储介质。该方法包括：获取所述音频输入模组的至少两个信号通道接收到的音频信号的信号能量值；根据至少两个所述音频信号之间的相关性,确定至少两个所述音频信号之间的相关程度值；根据所述信号能量值和所述相关程度值,确定所述音频输入模组的性能状况。通过本公开的技术方案,从信号能量值与不同信号通道之间的相关程度值这两个角度来衡量音频输入模组各信号通道的性能,具有较高的准确性和鲁棒性,适用范围广泛。(The disclosure relates to a detection method and device of an audio input module and a storage medium. The method comprises the following steps: acquiring signal energy values of audio signals received by at least two signal channels of the audio input module; determining a correlation degree value between at least two audio signals according to the correlation between the at least two audio signals; and determining the performance condition of the audio input module according to the signal energy value and the correlation degree value. According to the technical scheme, the performance of each signal channel of the audio input module is measured from two angles of the signal energy value and the correlation degree value between different signal channels, and the audio input module has high accuracy and robustness and wide application range.)
1. A method for detecting an audio input module, comprising:
acquiring signal energy values of audio signals received by at least two signal channels of the audio input module;
determining a correlation degree value between at least two audio signals according to the correlation between the at least two audio signals;
and determining the performance condition of the audio input module according to the signal energy value and the correlation degree value.
2. The detection method according to claim 1, further comprising:
switching to a target detection mode according to the running state of the electronic equipment where the audio input module is located, wherein the target detection mode comprises: a first detection mode and a second detection mode; the electronic equipment detects the performance condition in the first detection mode or the second detection mode, wherein the detection duration of the first detection mode is shorter than that of the second detection mode;
and in the detection time interval of the detection duration of the target detection mode, at least two signal channels of the audio input module receive the audio signals.
3. The method according to claim 2, wherein the switching to the target detection mode according to the operation state of the electronic device where the audio input module is located comprises:
when the running state of the electronic equipment is within a preset time after power-on, switching to the first detection mode;
and when the running state of the electronic equipment is outside the preset time after the electronic equipment is powered on, switching to the second detection mode.
4. The detection method according to claim 3, further comprising:
determining a normal signal channel capable of normally receiving an audio signal based on the performance condition of the audio input module;
and determining the normal signal channel as a working channel, wherein the working channel is used for collecting the audio signal.
5. The method for detecting according to claim 4, wherein the determining a normal signal channel capable of normally receiving an audio signal based on the performance condition of the audio input module comprises:
determining a first type abnormal signal channel with a first type abnormal condition according to the signal channel with the signal energy value smaller than the energy threshold;
determining a second type abnormal signal channel with a second type abnormal condition according to the signal channel with the correlation degree value not meeting the correlation threshold range;
and determining signal channels except the first abnormal signal channel and the second abnormal signal channel in the audio input module as the normal signal channels.
6. The method according to claim 5, wherein the determining the second type of abnormal signal channel having the second type of abnormal condition according to the signal channel whose correlation degree value does not satisfy the correlation threshold range comprises:
if the correlation degree values between the audio signals of the at least two signal channels do not belong to the correlation threshold interval, determining the correlation degree values between the at least two signal channels and other signal channels respectively;
and if the correlation degree value between any one of the at least two signal channels and the other signal channels does not belong to the correlation threshold interval, determining that the current signal channel of the at least two signal channels is the second-class abnormal channel.
7. The method for detecting according to claim 5, wherein said determining a signal channel other than the first abnormal signal channel and the second abnormal signal channel in the audio input module as the normal signal channel comprises:
in the signal channels except the first-class abnormal signal channel and the second-class abnormal signal channel in the audio input module, if the correlation degree value between the audio signals of at least two signal channels belongs to the correlation threshold interval, the at least two signal channels are determined to be the normal signal channels.
8. The detection method according to claim 5, characterized in that in the first detection mode at least one of the following is fulfilled:
the energy threshold is less than the energy threshold in the second detection mode;
the minimum value of the correlation threshold range is less than or equal to the minimum value of the correlation threshold range in the second detection mode;
the maximum value of the correlation threshold range is greater than or equal to the maximum value of the correlation threshold range in the second detection mode.
9. The method according to any of claims 5 to 8, wherein in the second detection mode, the method further comprises:
if the signal energy value of the signal channel is greater than or equal to the energy threshold value, determining that the signal channel is a channel to be detected;
the determining a correlation degree value between at least two audio signals according to the correlation between the at least two audio signals comprises:
and determining the correlation degree value between the audio signals of the at least two channels to be detected according to the correlation between the audio signals of the at least two channels to be detected.
10. The method according to any one of claims 5 to 8, wherein in the second detection mode, the determining the performance status of the audio input module according to the signal energy value and the correlation degree value comprises:
determining at least two groups of detection results according to at least two groups of signal energy values and the correlation degree values obtained at specified intervals;
if the same signal channel is determined to be the normal signal channel in the at least two groups of detection results, determining that the current signal channel is the normal signal channel;
if the same signal channel is determined to be an abnormal signal channel in the at least two groups of detection results, determining that the current signal channel is the abnormal signal channel, wherein the abnormal signal channel comprises: a first type of exception signal path and a second type of exception signal path.
11. The method according to any of claims 1 to 8, wherein the audio signal comprises at least two segments of audio sub-signals; the determining a correlation degree value between at least two audio signals according to the correlation between the at least two audio signals comprises:
determining at least two sub-correlation degree values corresponding to at least two audio signals according to the correlation between each section of audio sub-signal;
and summing the at least two sub-correlation degree values to obtain the correlation degree value.
12. A detection device for an audio input module, comprising:
the first determining module is used for acquiring signal energy values of audio signals received by at least two signal channels of the audio input module;
the second determining module is used for determining a correlation degree value between at least two audio signals according to the correlation between the at least two audio signals;
and the third determining module is used for determining the performance condition of the audio input module according to the signal energy value and the correlation degree value.
13. The detection apparatus of claim 12, further comprising:
the switching module is used for switching to a target detection mode according to the running state of the electronic equipment where the audio input module is located, wherein the target detection mode comprises the following steps: a first detection mode and a second detection mode; the electronic equipment detects the performance condition in the first detection mode or the second detection mode, wherein the detection duration of the first detection mode is shorter than that of the second detection mode;
and the receiving module is used for receiving the audio signal in the detection time interval of the detection duration of the target detection mode.
14. The detection apparatus according to claim 13, wherein the switching module comprises:
a first switching submodule, configured to switch to the first detection mode within a predetermined time after the electronic device is powered on
And the second switching submodule is used for switching to the second detection mode when the running state of the electronic equipment is beyond a preset time after the electronic equipment is powered on.
15. The detection apparatus of claim 14, further comprising:
the fourth determining module is used for determining a normal signal channel capable of normally receiving the audio signal based on the performance condition of the audio input module;
and the fifth determining module is used for determining the normal signal channel as a working channel, wherein the working channel is used for collecting the audio signal.
16. The detection apparatus according to claim 15, wherein the fourth determination module comprises:
the first determining submodule is used for determining a first-class abnormal signal channel with a first-class abnormal condition according to the signal channel with the signal energy value smaller than the energy threshold;
the second determining submodule is used for determining a second abnormal signal channel with a second abnormal condition according to the signal channel of which the correlation degree value does not meet the correlation threshold range;
and the third determining submodule is used for determining signal channels except the first abnormal signal channel and the second abnormal signal channel in the audio input module as the normal signal channels.
17. The detection apparatus according to claim 16, wherein the second determination submodule is specifically configured to:
if the correlation degree values between the audio signals of the at least two signal channels do not belong to the correlation threshold interval, determining the correlation degree values between the at least two signal channels and other signal channels respectively;
and if the correlation degree value between any one of the at least two signal channels and the other signal channels does not belong to the correlation threshold interval, determining that the current signal channel of the at least two signal channels is the second-class abnormal channel.
18. The detection apparatus according to claim 16, wherein the third determination submodule is specifically configured to:
in the signal channels except the first-class abnormal signal channel and the second-class abnormal signal channel in the audio input module, if the correlation degree value between the audio signals of at least two signal channels belongs to the correlation threshold interval, the at least two signal channels are determined to be the normal signal channels.
19. The detection apparatus according to claim 16, wherein in the first detection mode, at least one of the following is satisfied:
the energy threshold is less than the energy threshold in the second detection mode;
the minimum value of the correlation threshold range is less than or equal to the minimum value of the correlation threshold range in the second detection mode;
the maximum value of the correlation threshold range is greater than or equal to the maximum value of the correlation threshold range in the second detection mode.
20. The apparatus according to any one of claims 16 to 19, wherein in the second detection mode, the apparatus further comprises:
a sixth determining module, configured to determine that a signal channel is a channel to be detected if a signal energy value of the signal channel is greater than or equal to the energy threshold;
the second determining module is specifically configured to:
and determining the correlation degree value between the audio signals of the at least two channels to be detected according to the correlation between the audio signals of the at least two channels to be detected.
21. The detecting device according to any one of claims 16 to 19, wherein in the second detecting mode, the third determining module includes:
the fourth determining submodule is used for determining at least two groups of detection results according to at least two groups of signal energy values and the correlation degree values obtained by appointed time intervals;
a fifth determining submodule, configured to determine that the current signal channel is a normal signal channel if the same signal channel is determined as the normal signal channel in the at least two groups of detection results;
a sixth determining submodule, configured to determine that the current signal channel is an abnormal signal channel if the same signal channel in the at least two groups of detection results is determined to be the abnormal signal channel, where the abnormal signal channel includes: a first type of exception signal path and a second type of exception signal path.
22. The apparatus according to any one of claims 12 to 21, wherein the audio signal comprises at least two segments of audio sub-signals; the second determining module includes:
a seventh determining sub-module, configured to determine at least two sub-correlation degree values corresponding to the audio signal according to a correlation between each segment of the audio sub-signal;
and the summation submodule is used for summing at least two sub-correlation degree values of the at least two signal channels to obtain the correlation degree value.
23. A device for detecting an audio input module, the device comprising: a processor and a memory for storing executable instructions operable on the processor, wherein:
the processor is configured to execute the executable instructions, and the executable instructions perform the steps of the method for detecting an audio input module according to any one of the preceding claims 1 to 11.
24. A non-transitory computer-readable storage medium, wherein computer-executable instructions are stored in the computer-readable storage medium, and when executed by a processor, implement the steps in the method for detecting an audio input module according to any one of claims 1 to 11.
Technical Field
The present disclosure relates to electronic technologies, and in particular, to a method and an apparatus for detecting an audio input module, and a storage medium.
Background
Voice interaction is one of the important man-machine interaction modes for the development of electronic devices in recent years, and audio input modules such as smart microphones and voice assistants are widely used. However, the audio input module is affected by the environment and is easily damaged, so that the problems that the pickup algorithm fails, the device cannot be awakened normally through voice and the like are caused.
Disclosure of Invention
The disclosure provides a detection method and device of an audio input module and a storage medium.
According to a first aspect of the embodiments of the present disclosure, there is provided a method for detecting an audio input module, the method including:
acquiring signal energy values of audio signals received by at least two signal channels of the audio input module;
determining a correlation degree value between at least two audio signals according to the correlation between the at least two audio signals;
and determining the performance condition of the audio input module according to the signal energy value and the correlation degree value.
In some embodiments, the method further comprises:
switching to a target detection mode according to the running state of the electronic equipment where the audio input module is located, wherein the target detection mode comprises: a first detection mode and a second detection mode; wherein the detection duration of the first detection mode is less than the detection duration of the second detection mode;
and in the detection time interval of the detection duration of the target detection mode, at least two signal channels of the audio input module receive the audio signals.
In some embodiments, the switching to the target detection mode according to the operation state of the electronic device where the audio input module is located includes:
when the running state of the electronic equipment is within the preset time after being electrified, the electronic equipment is switched to the first detection mode
And when the running state of the electronic equipment is outside the preset time after the electronic equipment is powered on, switching to the second detection mode.
In some embodiments, the method further comprises:
determining a normal signal channel capable of normally receiving an audio signal based on the performance condition of the audio input module;
and determining the normal signal channel as a working channel, wherein the working channel is used for collecting the audio signal.
In some embodiments, the determining a normal signal channel capable of normally receiving an audio signal based on the performance condition of the audio input module includes:
determining a first type abnormal signal channel with a first type abnormal condition according to the signal channel with the signal energy value smaller than the energy threshold;
determining a second type abnormal signal channel with a second type abnormal condition according to the signal channel with the correlation degree value not meeting the correlation threshold range;
and determining signal channels except the first abnormal signal channel and the second abnormal signal channel in the audio input module as the normal signal channels.
In some embodiments, said determining a second type of abnormal signal path for which a second type of abnormal condition exists based on signal paths for which the degree of correlation value does not satisfy the correlation threshold range comprises:
if the correlation degree values between the audio signals of the at least two signal channels do not belong to the correlation threshold interval, determining the correlation degree values between the at least two signal channels and other signal channels respectively;
and if the correlation degree value between any one of the at least two signal channels and the other signal channels does not belong to the correlation threshold interval, determining that the current signal channel of the at least two signal channels is the second-class abnormal channel.
In some embodiments, the determining a signal channel other than the first abnormal signal channel and the second abnormal signal channel in the audio input module as the normal signal channel includes:
in the signal channels except the first-class abnormal signal channel and the second-class abnormal signal channel in the audio input module, if the correlation degree value between the audio signals of at least two signal channels belongs to the correlation threshold interval, the at least two signal channels are determined to be the normal signal channels.
In some embodiments, in the first detection mode, at least one of:
the energy threshold is less than the energy threshold in the second detection mode;
the minimum value of the correlation threshold range is less than or equal to the minimum value of the correlation threshold range in the second detection mode;
the maximum value of the correlation threshold range is greater than or equal to the maximum value of the correlation threshold range in the second detection mode.
In some embodiments, in the second detection mode, the method further comprises:
if the signal energy value of the signal channel is greater than or equal to the energy threshold value, determining that the signal channel is a channel to be detected;
the determining a correlation degree value between at least two audio signals according to the correlation between the at least two audio signals comprises:
and determining the correlation degree value between the audio signals of the at least two channels to be detected according to the correlation between the audio signals of the at least two channels to be detected.
In some embodiments, in the second detection mode, the determining the performance condition of the audio input module according to the signal energy value and the degree of correlation value includes:
determining at least two groups of detection results according to at least two groups of signal energy values and the correlation degree values obtained at specified intervals;
if the same signal channel is determined to be the normal signal channel in the at least two groups of detection results, determining that the current signal channel is the normal signal channel;
if the same signal channel is determined to be an abnormal signal channel in the at least two groups of detection results, determining that the current signal channel is the abnormal signal channel, wherein the abnormal signal channel comprises: a first type of exception signal path and a second type of exception signal path.
In some embodiments, the audio signal comprises at least two segments of audio sub-signals; the determining a correlation degree value between at least two audio signals according to the correlation between the at least two audio signals comprises:
determining at least two sub-correlation degree values corresponding to at least two audio signals according to the correlation between each section of audio sub-signal;
and summing at least two sub-correlation degree values of the at least two signal channels to obtain the correlation degree value.
According to a second aspect of the embodiments of the present disclosure, there is provided a detection apparatus for an audio input module, including:
the first determining module is used for acquiring signal energy values of audio signals received by at least two signal channels of the audio input module;
the second determining module is used for determining a correlation degree value between at least two audio signals according to the correlation between the at least two audio signals;
and the third determining module is used for determining the performance condition of the audio input module according to the signal energy value and the correlation degree value.
In some embodiments, the apparatus further comprises:
the switching module is used for switching to a target detection mode according to the running state of the electronic equipment where the audio input module is located, wherein the target detection mode comprises the following steps: a first detection mode and a second detection mode; wherein the detection duration of the first detection mode is less than the detection duration of the second detection mode;
and the receiving module is used for receiving the audio signal in the detection time interval of the detection duration of the target detection mode.
In some embodiments, the switching module comprises:
a first switching submodule, configured to switch to the first detection mode within a predetermined time after the electronic device is powered on
And the second switching submodule is used for switching to the second detection mode when the running state of the electronic equipment is beyond a preset time after the electronic equipment is powered on.
In some embodiments, the apparatus further comprises:
the fourth determining module is used for determining a normal signal channel capable of normally receiving the audio signal based on the performance condition of the audio input module;
and the fifth determining module is used for determining the normal signal channel as a working channel, wherein the working channel is used for collecting the audio signal.
In some embodiments, the fourth determining module comprises:
the first determining submodule is used for determining a first-class abnormal signal channel with a first-class abnormal condition according to the signal channel with the signal energy value smaller than the energy threshold;
the second determining submodule is used for determining a second abnormal signal channel with a second abnormal condition according to the signal channel of which the correlation degree value does not meet the correlation threshold range;
and the third determining submodule is used for determining signal channels except the first abnormal signal channel and the second abnormal signal channel in the audio input module as the normal signal channels.
In some embodiments, the second determining submodule is specifically configured to:
if the correlation degree values between the audio signals of the at least two signal channels do not belong to the correlation threshold interval, determining the correlation degree values between the at least two signal channels and other signal channels respectively;
and if the correlation degree value between any one of the at least two signal channels and the other signal channels does not belong to the correlation threshold interval, the current signal channel of the at least two signal channels is the second-class abnormal channel.
In some embodiments, the third determining submodule is specifically configured to:
in the signal channels except the first-class abnormal signal channel and the second-class abnormal signal channel in the audio input module, if the correlation degree value between the audio signals of at least two signal channels belongs to the correlation threshold interval, the at least two signal channels are determined to be the normal signal channels.
In some embodiments, in the first detection mode, at least one of:
the energy threshold is less than the energy threshold in the second detection mode;
the minimum value of the correlation threshold range is less than or equal to the minimum value of the correlation threshold range in the second detection mode;
the maximum value of the correlation threshold range is greater than or equal to the maximum value of the correlation threshold range in the second detection mode.
In some embodiments, in the second detection mode, the apparatus further comprises:
a sixth determining module, configured to determine that a signal channel is a channel to be detected if a signal energy value of the signal channel is greater than or equal to the energy threshold;
the second determining module is specifically configured to:
and determining the correlation degree value between the audio signals of the at least two channels to be detected according to the correlation between the audio signals of the at least two channels to be detected.
In some embodiments, in the second detection mode, the third determining module includes:
the fourth determining submodule is used for determining at least two groups of detection results according to at least two groups of signal energy values and the correlation degree values obtained by appointed time intervals;
a fifth determining submodule, configured to determine that the current signal channel is a normal signal channel if the same signal channel is determined as the normal signal channel in the at least two groups of detection results;
a sixth determining submodule, configured to determine that the current signal channel is an abnormal signal channel if the same signal channel in the at least two groups of detection results is determined to be the abnormal signal channel, where the abnormal signal channel includes: a first type of exception signal path and a second type of exception signal path.
In some embodiments, the audio signal comprises at least two segments of audio sub-signals; the second determining module includes:
a seventh determining sub-module, configured to determine at least two sub-correlation degree values corresponding to the audio signal according to a correlation between each segment of the audio sub-signal;
and the summation submodule is used for summing at least two sub-correlation degree values of the at least two signal channels to obtain the correlation degree value.
According to a third aspect of the embodiments of the present disclosure, there is provided a detection apparatus of an audio input module, the apparatus at least including: a processor and a memory for storing executable instructions operable on the processor, wherein:
when the processor is used for executing the executable instruction, the executable instruction executes the steps in the detection method of any audio input module.
According to a fourth aspect of the embodiments of the present disclosure, there is provided a non-transitory computer-readable storage medium having stored therein computer-executable instructions, which when executed by a processor, implement the steps in the method for detecting an audio input module described above.
The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects: through the technical scheme of the application, the performance of each signal channel of the audio input module is measured from two angles of the signal energy value and the correlation degree value between different signal channels, and the audio input module has high accuracy and robustness and wide application range.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
FIG. 1 is a flow chart illustrating a method of detection of an audio input module according to an exemplary embodiment;
FIG. 2 is a flow chart illustrating another method of detection of an audio input module in accordance with an exemplary embodiment;
FIG. 3 is a flow chart illustrating yet another method of audio input module detection according to an exemplary embodiment;
FIG. 4 is a flow chart illustrating yet another method of audio input module detection according to an exemplary embodiment;
FIG. 5 is a flow chart illustrating yet another method of audio input module detection according to an exemplary embodiment;
FIG. 6 is a flow chart illustrating yet another method of audio input module detection according to an exemplary embodiment;
FIG. 7 is a block diagram illustrating a detection apparatus of an audio input module according to an exemplary embodiment;
fig. 8 is a block diagram illustrating an exemplary embodiment of an apparatus for detecting an audio input module.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.
Fig. 1 is a flowchart illustrating a method for detecting an audio input module according to an exemplary embodiment, which may be applied to a terminal, as shown in fig. 1, and includes the following steps:
in step S101, signal energy values of audio signals received by at least two signal channels of the audio input module are obtained;
in step S102, determining a correlation degree value between at least two audio signals according to a correlation between the at least two audio signals;
in step S103, the performance status of the audio input module is determined according to the signal energy value and the correlation degree value.
The audio input module is a sound receiving device having a plurality of signal channels for receiving audio signals, each of which is capable of independently receiving audio signals with different frequencies and different intensities in the surrounding environment and converting the audio signals into electrical signals. For example, a microphone array is composed of a certain number of acoustic sensors, and can sample and process spatial characteristics of a sound field. The audio signals are simultaneously collected in the signal channels in different directions, so that the spatial information of sound can be obtained, and the method can be used for positioning sound sources and other scenes.
The intensity of audio signal is different, and the energy that has is also different, and through the power size of the signal of telecommunication that detects audio signal and correspond, can judge audio signal's energy size, also namely confirm audio signal's signal energy value. When the microphone is damaged and cannot accept the audio signal, the corresponding electric signal cannot be generated, and therefore the detected signal energy value is extremely low or zero. That is, when the signal energy value is extremely low or even zero, it can be determined that the audio signal is not received by the corresponding signal channel. Therefore, whether the signal channel can receive the audio signal can be determined through the signal energy value.
The signal energy value is zero, and there may be cases where: one is that the environment where the signal channel is located has no sound, and no sound signal is actually collected; the other is that the environment where the signal channel is located has sound, and the signal channel itself is abnormal, so that the sound signal cannot be collected or is very small. Therefore, when a plurality of signal channels located in the same environment collect sound, one signal channel collects sound signals, but the other signal channel does not collect sound or the collected sound signals are very low, the signal channel is abnormal.
For an audio input module with multiple signal channels, when different signal channels are simultaneously turned on and receive audio signals, the received audio signals are all from the environment, i.e. from the same sound source, and therefore, the received audio signals between different signal channels should have high correlation. Here, the correlation refers to the degree of similarity between different signals, and may be described by a correlation parameter such as a correlation degree value. The correlation degree value is a parameter obtained by calculating the correlation between at least two groups of audio signals. The degree of correlation between the signals is determined, for example, by calculating correlation coefficients of two sets of signals. The correlation coefficient is a parameter for describing the correlation between signal waveforms, and can be calculated by the variance and covariance between two signals, the absolute value of the correlation coefficient is between 0 and 1, when the correlation coefficient is 0, there is no linear relationship between the two signals, and when the correlation coefficient is 1, it indicates that the signal waveforms of the two signals are completely consistent.
Through the two indexes of the signal energy value and the correlation degree value, whether each signal channel of the audio input module can normally receive the audio signal is judged. Appropriate threshold values can be respectively set for the signal energy value and the correlation degree value of the audio signal, and whether each signal channel is normal or not is determined according to actual requirements. Through the scheme, the performance of each signal channel of the audio input module is measured from two angles of the signal energy value and the correlation degree value between different signal channels, and the audio input module has high accuracy and robustness and wide application range. In addition, because reference signal channels or reference microphones and the like do not need to be set, and detection is directly carried out through each signal channel of the audio input module, the scheme is not limited to detection of products before delivery, the products can be detected at any time in the using process, and the working modes, parameters and the like of the products can be adjusted in real time according to the detection results.
In some embodiments, the method further comprises:
according to the running state of the electronic equipment where the audio input module is located, switching to a target detection mode, wherein the target detection mode comprises the following steps: a first detection mode and a second detection mode; the electronic equipment detects the performance condition in the first detection mode or the second detection mode, wherein the detection duration of the first detection mode is shorter than that of the second detection mode;
at least two signal channels of the audio input module receive audio signals within a detection period of a detection duration of the target detection mode.
Here, different detection modes can be set according to the operation state of the electronic device where the audio input module is located. The electronic device is provided with the audio input module, and has audio signal acquisition and related functions, such as a mobile phone, a computer, a microphone and a microphone, and various electronic products with voice interaction functions, such as an intelligent voice sound, an intelligent robot, an intelligent toy and the like.
The operation states of the electronic device include a power-on state, a standby state, a use state, a low power mode, and the like of the electronic device, and different detection modes can be set based on different operation states of the electronic device to adapt to the current operation state of the electronic device. For example, after the electronic equipment is powered on, the electronic equipment can perform one-time rapid detection and report the abnormal condition of the audio input module in a short time; in a standby state or a use state of the electronic equipment, more accurate detection with lower speed can be carried out, so that more accurate detection results can be given in the use process, and the working mode of the audio input module can be adjusted at any time according to the detection results; and when the running state of the electronic equipment is in the low-power mode, the automatic detection is stopped, so that the power is saved.
The first detection mode and the second detection mode are two detection modes with different detection durations, and due to the detection of the audio input module, each signal channel needs to collect a section of audio signal, the detection can be set by setting the number of collected signal frames or the collection duration, and when the collection duration is longer, the detection result is more accurate; and when the acquisition time is short, the detection result can be obtained quickly. Since the rapid detection is susceptible to various external disturbances, e.g., noise disturbances, signal instability, etc. Therefore, for the fast first detection mode, a looser detection standard can be set.
For example, it is determined that the current channel is abnormal only when the signal energy value is 0, because the signal channel cannot detect the audio signal at this time, and is a damaged signal channel; if the correlation degree value of the two signal channels is 0, the two signal channels acquire completely different audio signals, or if one of the two signal channels does not receive the audio signal, it is determined that the two signal channels have a damaged signal channel. And to the second detection mode of slow speed, then need more accurate testing result, consequently, can set for stricter detection standard, carry out the detection for a long time, or many times to the accurate signal channel who determines the damage.
By the method, the audio input module can be detected in different detection modes under different operation modes of the electronic equipment, and the method is suitable for different scenes and requirements.
In some embodiments, switching to the target detection mode according to the operating state of the electronic device in which the audio input module is located includes:
when the running state of the electronic equipment is within a preset time after power-on, switching to a first detection mode;
and when the running state of the electronic equipment is outside the preset time after the electronic equipment is powered on, switching to a second detection mode.
The predetermined time may be configured in advance according to requirements, for example, when the electronic device is powered on, that is, the power-on state is set to give a detection result within 2 seconds, that is, the first detection mode is adopted within 2 seconds after the electronic device is powered on, and the second detection mode is adopted at a time other than 2 seconds.
After the electronic equipment is powered on, the electronic equipment can carry out one-time rapid detection and rapidly report an abnormal signal channel. Therefore, the abnormity can be found in time and corresponding processing can be carried out. Therefore, here, the first detection mode may be set to be adopted at a predetermined time after power-on. In addition, the detection of the first detection mode can be automatically triggered after the power-on, and a detection result can be obtained. After the electronic equipment is powered on for a period of time, the electronic equipment can be switched to a second detection mode in the operation process, and when the electronic equipment needs to be detected, the second detection mode is adopted for detection, so that a more accurate result is obtained. In addition, the time interval of detection can be set, so that the electronic equipment can automatically perform detection once every a period of time, and the quasi-real-time monitoring can be performed. If the audio input module is damaged and abnormal in the running process of the electronic equipment, the abnormality can be found through detection in real time and corresponding processing is carried out.
In some embodiments, as shown in fig. 2, the method further comprises:
step S104, determining a normal signal channel capable of normally receiving the audio signal based on the performance condition of the audio input module;
and S105, determining the normal signal channel as a working channel, wherein the working channel is used for collecting audio signals.
And comparing the signal energy value and the correlation degree value of each signal channel of the audio input module with a preset judgment standard so as to determine the signal channel which can normally receive the audio signal and meets the requirement. Here, these signal paths satisfying the requirements are determined as normal signal paths.
When the audio input module is used, the normal signal channel can be selected as a working channel according to the spatial position distribution of the normal signal channel on the electronic equipment and the actual requirement to collect audio signals, and the abnormal signal channel can be closed in use to prevent the normal signal channel from being interfered. For example, for an audio input module with 6-microphone mode, after finding a damaged signal channel, it can be downgraded to 4-microphone or 5-microphone mode, i.e. to select 4 or directly use 5 normal signal channels as working channels. For the pickup algorithm of the microphone array, for example, a 6-microphone algorithm, a 4-microphone algorithm and the like can be configured in advance, and after damaged or abnormal signal channels occur, corresponding algorithms can be called according to the number of normal signal channels, so that the using effect of the microphone is ensured.
In some embodiments, as shown in fig. 3, the determining, in step S104, a normal signal channel capable of normally receiving the audio signal based on the performance condition of the audio input module includes:
step S11, determining a first-class abnormal signal channel with a first-class abnormal condition according to the signal channel with the signal energy value smaller than the energy threshold;
step S12, determining a second abnormal signal channel with a second abnormal condition according to the signal channel with the correlation degree value not meeting the correlation threshold range;
step S13, determining the signal channels other than the first-type abnormal signal channel and the second-type abnormal signal channel in the audio input module as normal signal channels.
The first type of abnormal condition is determined based on a signal energy value of the audio signal received by the signal channel, and when the signal energy value is smaller than an energy threshold value, the signal channel is considered to have no received audio signal or the received audio signal is very weak, and the signal channel may be damaged or abnormal. Therefore, the signal channels with the detected signal energy value smaller than the energy threshold are determined as the first type abnormal signal channels. Of course, an upper threshold of the signal energy value may be set, and when the signal energy value is greater than the upper threshold, that is, the signal energy is too high, other signal interference may occur, and it may be considered that an abnormality occurs in the signal channel.
When the correlation degree values of the audio signals received by the two signal channels do not satisfy the correlation threshold range, an abnormality may exist even if the two signal channels can receive the audio signals and the signal energy values of the received audio signals satisfy a preset condition. If the correlation degree value is lower than the threshold range, the difference of the received audio signals of the two signal channels is larger, and under the same environment, the difference of the audio signals received by the two signal channels is larger, the situation that the audio signal received by at least one signal channel is distorted and the like is caused, and the use requirement cannot be met. Because there is a certain difference between the positions of the different signal channels, when two signals are transmitted to the same sound source, the acquired audio signals should have a certain difference, so if the correlation degree of the two signal channels is too high, which indicates that the two sets of audio signals have extremely high similarity (almost identical in a specific case), there is also a possibility that an abnormality occurs, for example, a short circuit occurs between the two signal channels.
Therefore, the threshold value is set according to the signal energy value and the correlation degree value of the signal, whether each signal channel meets the use requirement is judged, and various possible abnormal conditions of each signal channel of the audio input equipment can be detected.
In some embodiments, in step S12, determining the second type of abnormal signal path having the second type of abnormal condition according to the signal path whose correlation degree value does not satisfy the correlation threshold range includes:
if the correlation degree values between the audio signals of the at least two signal channels do not belong to the correlation threshold interval, determining the correlation degree values between the at least two signal channels and other signal channels respectively;
and if the correlation degree value between any one of the at least two signal channels and other signal channels does not belong to the correlation threshold interval, determining that the current signal channel of the at least two signal channels is the second-class abnormal channel.
Here, the correlation detection may be performed on the audio signals received by two different signal channels, a correlation degree value between the two audio signals is determined, and when the correlation degree value does not satisfy the correlation threshold interval, it is determined that at least one of the two signal channels is abnormal. Therefore, one of the signal channels and the other signal channels can be continuously detected, and if a condition that the correlation degree value does not meet the correlation threshold interval also exists between the signal channel and the other signal channels, the signal channel with the abnormality can be determined.
In the method, exhaustive detection can be adopted, correlation detection is performed between every two signal channels, and the abnormal signal channel is determined according to the detection result between each signal channel and other signal channels.
Through the steps, the abnormal signal channel can be accurately positioned, and the sending of misjudgment is reduced.
In some embodiments, determining signal channels other than the first-type abnormal signal channel and the second-type abnormal signal channel in the audio input module as normal signal channels includes:
in the signal channels except the first-class abnormal signal channel and the second-class abnormal signal channel in the audio input module, if the correlation degree value between the audio signals of at least two signal channels belongs to the correlation threshold interval, the at least two signal channels are determined to be normal signal channels.
After the first-type abnormal signal channel and the second-type abnormal signal channel are excluded, a normal signal channel can be determined in the remaining signal channels. If the correlation degree values of the audio signals collected by the two signal channels are within a preset interval, the two signal channels are considered to be capable of normally collecting the audio signals, and the collected audio signals are synchronous, so that the two signal channels can be directly determined to be both normal channels.
In some embodiments, in the first detection mode, at least one of:
the energy threshold is smaller than the energy threshold in the second detection mode;
the minimum value of the correlation threshold range is less than or equal to the minimum value of the correlation threshold range in the second detection mode;
the maximum value of the correlation threshold range is greater than or equal to the maximum value of the correlation threshold range in the second detection mode.
The detection method in the above embodiment can be applied to the first detection mode and the second detection mode. However, since the first detection mode requires a shorter detection time, rapid detection may be performed, and external interference may occur, or an error may be large due to the shorter detection time. Therefore, a relatively loose detection standard can be set for the first detection mode, and the first detection mode can be used for determining a signal channel with serious damage or abnormality so as to reduce various false detections caused by the strict detection standard.
Here, the above distinction is realized by setting different detection threshold ranges. For the first detection mode, the energy threshold is smaller than that of the second detection mode, so that in the first detection mode, the signal channel is considered abnormal only when the energy is extremely weak. In addition, the correlation threshold range in the first detection mode may be larger than that in the second detection mode, so that only signal channels with extremely poor correlation are screened out.
In addition, in the first detection mode, it is also possible to determine that an abnormality has occurred for two channels whose correlation degree value is extremely high. For example, the correlation coefficient between the audio signals of the two signal channels is 1, that is, the audio signals collected by the two signal channels are completely consistent, which is almost impossible for the audio input component, so that it can be determined that at least one of the signal channels is seriously damaged or short-circuited with the other signal channels.
Therefore, when the electronic equipment is powered on, the signal channel which is seriously damaged can be quickly detected, then more accurate screening is carried out in subsequent detection, and other abnormal signal channels are determined, so that the robustness and the accuracy of detection are ensured.
In some embodiments, in the second detection mode, as shown in fig. 4, the method further comprises:
step S21, if the signal energy value of the signal channel is greater than or equal to the energy threshold value, determining the signal channel as a channel to be detected;
in the step S102, determining a correlation degree value between at least two audio signals according to the correlation between the at least two audio signals includes:
and step S22, determining the correlation degree value between the audio signals of the at least two channels to be detected according to the correlation between the audio signals of the at least two channels to be detected.
Here, in the second detection mode, the detection of the signal energy value can be used as a condition for screening the correlation between the signals to be detected. The detection of the correlation tends to be less accurate when the signal energy value is smaller, and therefore, here, the detection of the correlation continues for the corresponding signal channel only when the signal energy value is greater than or equal to a preset energy threshold value, and a correlation degree value between the audio signals of at least two signal channels is determined.
The channels to be detected are determined to be the signal channels to be detected with correlation when the signal energy value meets the preset energy threshold condition, and after the correlation degree value among the channels to be detected is continuously detected, whether each channel is normal or not is determined.
In some embodiments, in the second detection mode, the determining the performance status of the audio input module according to the signal energy value and the correlation degree value in step S103 includes:
determining at least two groups of detection results according to at least two groups of signal energy values and correlation degree values obtained at specified intervals;
if the same signal channel is determined to be a normal signal channel in at least two groups of detection results, determining that the current signal channel is a normal signal channel;
if the same signal channel is determined to be an abnormal signal channel in at least two groups of detection results, determining that the current signal channel is the abnormal signal channel, wherein the abnormal signal channel comprises: a first type of exception signal path and a second type of exception signal path.
Here, since a more accurate result is required in the second detection mode, a plurality of detections can be performed with a set interval time. For example, the detection is performed every 5 seconds, the detection result is obtained after 3 times of detection, and when the detection results of 3 times are consistent, the final detection result is determined. That is, when the same signal channel in the at least two sets of detection results is determined to be a normal signal channel, it indicates that the detection result is relatively accurate, and it can be determined that the signal channel is a normal signal channel; similarly, when the same signal channel is abnormal in at least two groups of detection results, it can be determined that the signal channel is an abnormal signal channel.
If different detection results exist in at least two set detections, for example, the same detection channel is abnormal in one detection and normal in another detection, it indicates that the detection results of the two detections may have a large error, and therefore, the detection result may be ignored, and a new round of detection is performed again.
Therefore, through multiple detections, whether each signal channel is abnormal or not can be determined more accurately, and the robustness of the detection is improved.
In some embodiments, the audio signal comprises at least two segments of audio sub-signals; determining a correlation degree value between at least two audio signals according to a correlation between the at least two audio signals, comprising:
determining at least two sub-correlation degree values corresponding to at least two audio signals according to the correlation between each section of audio sub-signal;
and summing at least two sub-correlation degree values to obtain a correlation degree value.
Here, a plurality of pieces of audio signals may be extracted, and correlations may be determined, respectively, and then weighted correlation degree values may be calculated. For the detection in the first detection mode with higher speed, multiple sections of audio signals can be collected within a period of time, or audio signals of a continuous period of time are collected and divided into multiple sections of audio signals, then the correlation is respectively determined, and the weighted value is used as the final correlation degree value; for the detection in the second detection mode, a plurality of segments of the audio signal may also be acquired, for example, once every a period of time. And then, the correlation among different signal channels is determined for each section of audio signal, and finally, the weighted value is used as a final correlation degree value, so that the detection robustness is effectively improved.
To facilitate understanding of the technical solutions of the embodiments of the present disclosure, the present disclosure also provides the following examples:
in order to improve the robustness of the microphone array, a detection method of the microphone is proposed. And detecting the state of each microphone in the microphone array after sound pickup, and rejecting abnormal microphones. The method can be applied to equipment with multiple microphones for picking up sound, abnormal microphones are searched through a set detection and judgment mechanism, and then a degraded microphone array algorithm is adopted for the microphones without the abnormality. For example, a six-microphone device, after finding a microphone with a problem, may use a four-microphone algorithm or a two-microphone algorithm. The detection and judgment mechanism can adopt parameters such as correlation among microphones and check the convergence condition of the sound signals in an echo scene so as to judge the state of the microphones.
A method as shown in fig. 5 is generally employed for microphone detection, comprising:
step S1, connecting the microphone to be tested and the reference microphone to the processing unit;
step S2, receiving sound waves of a loudspeaker, generating a first characteristic point distribution graph by a microphone to be tested, and generating a second characteristic point distribution graph by a reference microphone;
step S3, comparing the first characteristic point distribution map with the second characteristic point distribution map, and determining the state of the microphone to be tested by the difference of the numbers of the characteristic points in a specified frequency quantization value interval.
The distribution diagram of the characteristic points is obtained by sampling the waveform of the sound signal, and the collected sound wave signal can be roughly observed according to the distribution diagram of the characteristic points. And comparing the characteristic point distribution diagrams respectively generated by the microphone to be tested and the reference microphone, namely observing whether the signal waveforms received by the two microphones have larger difference, and if so, considering that the microphone to be tested has abnormity.
The waveform diagram may be a time-dependent change in sound intensity, a time-dependent change in signal energy value at a specific frequency, or the like. Therefore, the above feature points include at least: signal capability values at specific frequencies.
The method for detecting the single frequency point by comparing the reference microphone can only carry out related detection when leaving a factory, so that an adjustment algorithm cannot be corrected in time when a problem occurs in the using process of a user; moreover, only a single frequency point is judged, and all frequency bands cannot be guaranteed to have no problem; in addition, this method can only analyze the difference between the numerical feature points, and cannot accurately feed back the state of the microphone.
In order to enable a user to quickly know the state of the microphone as soon as the electronic device is powered on, a quick detection may be performed at power-on. However, since various factors of the environment easily affect the short-term characteristics of the microphone, a fast and slow detection combination method is proposed. When the electronic equipment is just started, the check is carried out within a specified time and a quick detection result is obtained. During the use process, the slow detection mode is adopted for checking. The slow detection is mainly used for obtaining an accurate detection result and an accurate adjustment scheme, so that the robustness of the microphone state is improved.
In the slow detection process, the energy of the signal acquired by each signal channel is calculated, if the minimum value of the energy of each signal channel is greater than a set threshold value, the detection of the correlation is carried out, and in order to obtain a detection result with stronger robustness, multiple detections can be adopted to obtain a final detection result. For example, each time the slow detection time is set to 2 seconds, it is set that if and only if the three slow detection results of the microphones coincide, the final detection result is determined, and the microphone state is adjusted according to the final detection result.
As shown in fig. 6, the fast detection 110 is to obtain a result in time after the device is powered on, but the obtained data is often unreliable because the data is less and the time is shorter. Therefore, only the microphone state having a serious problem is detected here, and a higher threshold value is set.
1) And energy detection, wherein if the energy of a channel is less than a set threshold value during detection, the channel does not receive a valid voice signal. As shown in fig. 6, low energy signal detection 111 is performed to determine the signal path having a signal energy value less than a threshold.
2) And detecting correlation between every two signals of each channel, and indicating that a pair of microphones are normal at the moment when the correlation of the signals of the pair of microphones is greater than a threshold value.
3) And a second correlation detection step, namely detecting the correlation between every two signals of each channel, summing the correlation of each microphone, comparing the sum with a threshold value, and if the sum is higher than the threshold value, indicating that the microphone is normal.
The correlation detection described above includes strong correlation noise detection 112 in fig. 6, and low correlation signal detection 113. Strong correlated noise detection 112, i.e., the signal path whose correlation is above a threshold range, is determined. For example, a short circuit may occur when the signals received by the two signal paths are nearly identical. The low correlation signal detection 113 selects signal channels with poor correlation with other signal channels, which may be abnormal and distort the received signal.
After the fast detection is completed, a detection result is obtained, then the microphone state 130 can be reset according to the detection result, and a proper algorithm is called, so that the microphone can be normally used, and the interference of a damaged channel on the whole pickup effect of the microphone is reduced as little as possible.
For slow detection 120, in order to minimize false positives, slow detection needs to provide stable and accurate judgments. And the number of slow detections may be adjusted, for example, 3 times, 5 times, etc., or the frame length of slow detection may be adjusted, for example, 150 frames, 200 frames, 300 frames, etc., where one frame represents a small segment of the audio signal. The time for fast detection may also be adjusted, e.g. determining the result within 1 or 2 seconds, etc.
1) Energy detection, which is different from fast detection, is to screen the signal channels of the microphone by energy detection, and only enter correlation detection when the energy of each signal channel is greater than a threshold value. The signal channels with signal energy greater than the threshold are screened out and correlation is continued to be calculated 122, as shown by energy threshold decision 121 in fig. 6.
2) And detecting correlation between every two channel signals, wherein the correlation of a pair of microphone signals is greater than a threshold value, which indicates that the pair of microphones are normal, and the set threshold value is lower than the threshold value set in the fast detection.
3) And a second correlation detection step, detecting the correlation between every two signals of each channel, summing the correlation of each microphone, comparing the sum with a threshold value, and if the sum is higher than the threshold value, determining that the microphone is normal, wherein the detection method is similar to the detection method of the fast detection, but a lower threshold value can be set.
After the correlation is calculated through the above steps, the normal signal channel 123 is determined, and then when it is determined that the multiple detection results are consistent, the microphone state may be reset 130 based on the detection results, and a suitable algorithm may be invoked.
In the method, an energy judgment and correlation judgment combined judgment mechanism is introduced; a fast detection and slow detection joint decision mechanism is introduced; multiple decisions are also introduced to ensure the robustness of the detection system. Therefore, the false detection rate can be effectively reduced, and the user experience of equipment without damage is reduced; because the quick detection time is short, the equipment with serious damage can be found in time; meanwhile, the method has strong robustness, and the accuracy of the detection result is ensured.
Fig. 7 is a block diagram illustrating a structure of a detecting apparatus of an audio input module according to an exemplary embodiment. Referring to fig. 7, the apparatus 700 includes: a first determining module 701, a second determining module 702, and a third determining module 703, wherein:
a first determining module 701, configured to obtain signal energy values of audio signals received by at least two signal channels of the audio input module;
a second determining module 702, configured to determine a correlation degree value between at least two audio signals according to a correlation between the at least two audio signals;
a third determining module 703, configured to determine a performance status of the audio input module according to the signal energy value and the correlation degree value.
In some embodiments, the apparatus further comprises:
the switching module is used for switching to a target detection mode according to the running state of the electronic equipment where the audio input module is located, wherein the target detection mode comprises the following steps: a first detection mode and a second detection mode; the electronic equipment detects the performance condition in the first detection mode or the second detection mode, wherein the detection duration of the first detection mode is shorter than that of the second detection mode;
and the receiving module is used for receiving the audio signal in the detection time interval of the detection duration of the target detection mode.
In some embodiments, the switching module comprises:
a first switching submodule, configured to switch to the first detection mode within a predetermined time after the electronic device is powered on
And the second switching submodule is used for switching to the second detection mode when the running state of the electronic equipment is beyond a preset time after the electronic equipment is powered on.
In some embodiments, the apparatus further comprises:
the fourth determining module is used for determining a normal signal channel capable of normally receiving the audio signal based on the performance condition of the audio input module;
and the fifth determining module is used for determining the normal signal channel as a working channel, wherein the working channel is used for collecting the audio signal.
In some embodiments, the fourth determining module comprises:
the first determining submodule is used for determining a first-class abnormal signal channel with a first-class abnormal condition according to the signal channel with the signal energy value smaller than the energy threshold;
the second determining submodule is used for determining a second abnormal signal channel with a second abnormal condition according to the signal channel of which the correlation degree value does not meet the correlation threshold range;
and the third determining submodule is used for determining signal channels except the first abnormal signal channel and the second abnormal signal channel in the audio input module as the normal signal channels.
In some embodiments, the second determining submodule is specifically configured to:
if the correlation degree values between the audio signals of the at least two signal channels do not belong to the correlation threshold interval, determining the correlation degree values between the at least two signal channels and other signal channels respectively;
and if the correlation degree value between any one of the at least two signal channels and the other signal channels does not belong to the correlation threshold interval, determining that the current signal channel of the at least two signal channels is the second-class abnormal channel.
In some embodiments, the third determining submodule is specifically configured to:
in the signal channels except the first-class abnormal signal channel and the second-class abnormal signal channel in the audio input module, if the correlation degree value between the audio signals of at least two signal channels belongs to the correlation threshold interval, the at least two signal channels are determined to be the normal signal channels.
In some embodiments, in the first detection mode, at least one of:
the energy threshold is less than the energy threshold in the second detection mode; the minimum value of the correlation threshold range is less than or equal to the minimum value of the correlation threshold range in the second detection mode;
the maximum value of the correlation threshold range is greater than or equal to the maximum value of the correlation threshold range in the second detection mode.
In some embodiments, in the second detection mode, the apparatus further comprises:
a sixth determining module, configured to determine that a signal channel is a channel to be detected if a signal energy value of the signal channel is greater than or equal to the energy threshold;
the second determining module is specifically configured to:
and determining the correlation degree value between the audio signals of the at least two channels to be detected according to the correlation between the audio signals of the at least two channels to be detected.
In some embodiments, in the second detection mode, the third determining module includes:
the fourth determining submodule is used for determining at least two groups of detection results according to at least two groups of signal energy values and the correlation degree values obtained by appointed time intervals;
a fifth determining submodule, configured to determine that the current signal channel is a normal signal channel if the same signal channel is determined as the normal signal channel in the at least two groups of detection results;
a sixth determining submodule, configured to determine that the current signal channel is an abnormal signal channel if the same signal channel in the at least two groups of detection results is determined to be the abnormal signal channel, where the abnormal signal channel includes: a first type of exception signal path and a second type of exception signal path.
In some embodiments, the audio signal comprises at least two segments of audio sub-signals; the second determining module includes:
a seventh determining sub-module, configured to determine at least two sub-correlation degree values corresponding to the audio signal according to a correlation between each segment of the audio sub-signal;
and the summation submodule is used for summing at least two sub-correlation degree values of the at least two signal channels to obtain the correlation degree value.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Fig. 8 is a block diagram illustrating an
Referring to fig. 8, the
The
The
The
The
The
The I/
The
The
In an exemplary embodiment, the
In an exemplary embodiment, a non-transitory computer readable storage medium comprising instructions, such as the
The embodiments of the present disclosure also provide a non-transitory computer-readable storage medium, where instructions in the storage medium, when executed by a processor of a mobile terminal, enable the mobile terminal to perform the method for detecting an audio input module provided in any of the above embodiments, where the method may include the following steps:
determining signal energy values of audio signals received by at least two signal channels of the audio input module;
determining a degree of correlation value between the audio signals of the at least two signal channels according to a correlation between the audio signals of the at least two signal channels;
and determining the performance condition of the audio input module by combining the signal energy value and the correlation degree value.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.
It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.