Abnormal sound detection method and device, electronic equipment and storage medium

Abstract

The present disclosure provides an abnormal sound detection method, device, electronic equipment and storage medium. The method comprises: acquiring a first noise signal of a noise source collected by a microphone when an active noise reduction system is not started; segmenting the first noise signal to make the first power proportion of each signal segment of the first noise signal less than a proportion threshold, and determining a segmentation strategy of the first noise signal; acquiring a second noise signal of the noise source collected by the microphone when the active noise reduction system is started; segmenting the second noise signal based on the segmentation strategy, and performing abnormal sound detection on the active noise reduction system according to the characteristics of each signal segment of the second noise signal. The present disclosure can quickly monitor the abnormal sound of the active noise reduction system, eliminate the influence of the frequency band characteristics of the range hood itself on the abnormal sound judgment, and accurately monitor the abnormal sound of the range hood active noise reduction.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of noise reduction technology, and in particular to a abnormal sound detection method and device, electronic equipment and storage medium. BACKGROUND

[0002] In an active noise reduction system, the noise reduction system utilizes the superimposed interference effect of the loudspeaker control signal (anti-phase noise) generated according to the input signal (including the collected noise signal and the feedback signal) and the noise signal to achieve the reduction of the noise signal, thereby achieving the purpose of noise reduction. However, in this process, when the feedback signal is greater than the noise signal, a howling phenomenon will occur. Even if the feedback signal is less than the noise signal, when the ratio of the feedback signal to the noise signal is greater than a threshold, some stable single-frequency abnormal sound will still be emitted. The amplitude of the stable single-frequency abnormal sound is much smaller than the noise when howling occurs, and there is no obvious difference in the amplitude of the loudspeaker control signal generated when the stable single-frequency abnormal sound occurs and the loudspeaker control signal generated when the system is normally working. Therefore, the traditional howling monitoring scheme based on the amplitude of the loudspeaker control signal in the prior art cannot effectively identify this stable single-frequency abnormal sound phenomenon. SUMMARY

[0003] The technical problem to be solved by the present disclosure is to overcome the above-mentioned defects in the prior art, and to provide a abnormal sound detection method, device, electronic equipment and storage medium.

[0004] The present disclosure solves the above technical problems by the following technical solutions:

[0005] In a first aspect, a abnormal sound detection method is provided, applied to an active noise reduction system, the active noise reduction system comprising a microphone; the abnormal sound detection method comprising:

[0006] In the case where the active noise reduction system is not started, a first noise signal of a noise source collected by the microphone is obtained;

[0007] The first noise signal is segmented to make the first power ratio of each signal segment of the first noise signal less than a ratio threshold, and a segmentation strategy of the first noise signal is determined;

[0008] In the case where the active noise reduction system is started, a second noise signal is obtained; the second noise signal comprises a noise signal of a noise source collected by the microphone and / or a control signal of the loudspeaker;

[0009] The second noise signal is segmented based on the segmentation strategy, and the active noise reduction system is detected for abnormal sound according to the characteristics of each signal segment of the second noise signal.

[0010] Optionally, the abnormal sound detection on the active noise reduction system according to the feature of each signal segment of the second noise signal comprises:

[0011] In response to the feature meeting the abnormal sound judgment condition, it is determined that the active noise reduction system has a stable single-frequency abnormal sound;

[0012] The abnormal sound judgment condition comprises at least one of the following:

[0013] There is a signal segment in the second noise signal with a second power proportion greater than or equal to the proportion threshold value; the feature comprises the second power proportion; the second power proportion is the ratio of the power of the signal segment to the total power, and the total power is the sum of the powers of each signal segment;

[0014] The difference between the total power and the maximum power of the signal segment is less than a first difference threshold value; the feature comprises the power of the signal segment;

[0015] The total power is within a preset power range; wherein the lower limit value of the preset power range is greater than the maximum power of the noise signal of the noise source, and the upper limit value of the preset power range is less than the power of the second noise signal when the active noise reduction system generates howling;

[0016] The difference between the total power and the power difference value is greater than or equal to a second difference threshold value; the power difference value is the difference between the total power and the maximum power of the noise signal;

[0017] There is a signal segment in the second noise signal with a power difference greater than or equal to a third difference threshold value from an adjacent signal segment.

[0018] Optionally, the first noise signal is segmented to make the first power proportion of each signal segment of the first noise signal less than a proportion threshold value, comprising:

[0019] The first noise signal is divided into at least two signal segments, and it is judged whether the first power proportion of each signal segment is less than the proportion threshold value;

[0020] In the case where the judgment result is no, the signal segment with the first power proportion greater than or equal to the proportion threshold value is segmented again until the first power proportion of each signal segment is less than the proportion threshold value.

[0021] Optionally, the first noise signal is segmented by a band-stop filter;

[0022] And / or, the second noise signal is segmented by the band-stop filter.

[0023] Optionally, the power proportion of the signal segment is calculated according to the following formula:

[0024] H = 1 - ei / E;

[0025]

[0026] wherein H represents a power ratio; e i represents the power of the i-th signal segment in the noise signal; E represents the sum of the powers of the signal segments contained in the noise signal; X j (t) represents the amplitude of the j-th sampling point of the noise signal in the time domain; N represents the number of sampling points contained in the noise signal.

[0027] In a second aspect, an abnormal sound detection device is provided, which is applied to an active noise reduction system, and the active noise reduction system comprises a microphone and a speaker; the abnormal sound detection device comprises:

[0028] An acquisition module, configured to acquire a first noise signal of a noise source collected by the microphone when the active noise reduction system is not started;

[0029] A first segmentation module, configured to perform segmentation processing on the first noise signal, so that the first power ratio of each signal segment of the first noise signal is less than a ratio threshold, and determine a segmentation strategy of the first noise signal;

[0030] The acquisition module is further configured to acquire a second noise signal when the active noise reduction system is started; the second noise signal comprises a noise signal of a noise source collected by the microphone and / or a control signal of the speaker;

[0031] A second segmentation module, further configured to perform segmentation processing on the second noise signal based on the segmentation strategy;

[0032] A detection module, configured to perform abnormal sound detection on the active noise reduction system according to a feature of each signal segment of the second noise signal.

[0033] Optionally, the detection module is specifically configured to:

[0034] in response to the feature meeting an abnormal sound judgment condition, determine that the active noise reduction system has a stable single-frequency abnormal sound;

[0035] The abnormal sound judgment condition comprises at least one of the following:

[0036] there is a signal segment with a second power ratio greater than or equal to the ratio threshold in the second noise signal; the feature comprises the second power ratio; the second power ratio is the ratio of the power of the signal segment to the total power; the total power is the sum of the powers of the signal segments;

[0037] the difference between the total power and the maximum power of the signal segment is less than a first difference threshold; the feature comprises the power of the signal segment.

[0038] The total power is within a preset power range; wherein a lower limit value of the preset power range is greater than a maximum power of the noise signal of the noise source, and an upper limit value of the preset power range is less than a power of the second noise signal when the active noise reduction system occurs howling;

[0039] The difference between the total power and the power difference value is greater than or equal to a second difference threshold value; the power difference value is the difference between the total power and the maximum power of the noise signal;

[0040] The second noise signal has a signal segment whose power difference with an adjacent signal segment is greater than or equal to a third difference threshold value.

[0041] Optionally, the first segmentation module comprises:

[0042] A segmentation unit configured to segment the first noise signal into at least two signal segments;

[0043] A judgment unit configured to judge whether the first power proportion of each signal segment is less than a proportion threshold value, and in the case of no, call the segmentation unit to segment the signal segment whose first power proportion is greater than or equal to the proportion threshold value again until the first power proportion of each signal segment is less than the proportion threshold value.

[0044] Optionally, the first segmentation module segments the first noise signal through a band-stop filter;

[0045] And / or, the second segmentation module segments the second noise signal through the band-stop filter.

[0046] Optionally, the calculation formula of the power proportion of the signal segment is as follows:

[0047] H = 1 - e i / E;

[0048]

[0049] Wherein, H represents the power proportion; e i represents the power of the noise signal corresponding to the i-th signal segment; E represents the sum of the powers of each signal segment contained in the noise signal; X j (t) represents the amplitude of the j-th sampling point of the noise signal in the time domain; N represents the number of sampling points contained in the noise signal.

[0050] In a third aspect, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and used to run on the processor, wherein the processor executes the computer program to realize the abnormal sound detection method of any one of the first aspect.

[0051] In a fourth aspect, a computer readable storage medium is provided, and a computer program is stored on the computer readable storage medium, and the computer program is executed by a processor to implement the abnormal sound detection method according to any one of the first aspect.

[0052] On the basis of common knowledge in the art, the above-mentioned preferred conditions can be combined arbitrarily, that is, to obtain each preferred example of the present disclosure.

[0053] The positive progress effect of the present disclosure is that the present disclosure can quickly monitor the abnormal sound of the active noise reduction system, eliminate the influence of the frequency band characteristics of the range hood itself on the abnormal sound judgment, and realize accurate monitoring of the abnormal sound of the range hood active noise reduction. BRIEF DESCRIPTION OF DRAWINGS

[0054] Figure 1 A flowchart of an abnormal sound detection method is provided for an exemplary embodiment of the present disclosure;

[0055] Figure 2a A frequency domain curve diagram of an active noise reduction system working normally, generating howling, and generating stable single-frequency abnormal sound is provided for an exemplary embodiment of the present disclosure;

[0056] Figure 2b A time domain curve diagram of an active noise reduction system working normally, generating howling, and generating stable single-frequency abnormal sound is provided for an exemplary embodiment of the present disclosure;

[0057] Figure 3 A module schematic diagram of an abnormal sound detection device is provided for an exemplary embodiment of the present disclosure;

[0058] Figure 4 A structural schematic diagram of an electronic device is provided for an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0059] The present disclosure will be further described below by way of examples, but the present disclosure is not limited in the scope of the examples.

[0060] In the embodiments of the present disclosure, the prefix words such as "first", "second" are only used to distinguish different description objects, and have no limiting effect on the position, order, priority, quantity or content of the described objects. The use of ordinal words such as ordinal words in the embodiments of the present disclosure does not constitute a limitation on the described objects, and the description of the described objects should be referred to the description of the context in the claims or embodiments, and should not constitute redundant limitation because of the use of such prefix words. In addition, in the description of the embodiments, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0061] Figure 1The flowchart illustrates an abnormal noise detection method provided as an exemplary embodiment of this disclosure. This abnormal noise detection method is applied to an active noise cancellation system, which includes devices such as microphones, speakers, and controllers.

[0062] The abnormal noise detected in this embodiment refers to a noise emitted by the speaker of the active noise cancellation system due to certain malfunctions or interference during operation, which affects the user experience. Abnormal noise includes howling and stable single-frequency abnormal noise (or stable single-frequency sound).

[0063] The characteristics of howling during active noise cancellation are: see Figure 2a and Figure 2b The noise spectrum exhibits a prominent peak, with the amplitude at its highest point significantly higher than adjacent frequencies. This peak is generally much larger than the peak of a stable single-frequency abnormal sound, accounting for a large portion of the total noise power. From the moment it is generated, the power amplitude in the time domain gradually increases, with the ratio of maximum power to minimum power generally exceeding 5 times, and the amplitude typically approaching or even exceeding the maximum output power of the loudspeaker itself. Figure 2a The second to fifth columns of the table refer to the amplitude (power) at 94.28Hz, 108.75Hz, 0Hz and 6000Hz respectively, and the sixth column, RMS data, refers to the root mean square value of the amplitude from 0 to 6000Hz.

[0064] Unlike howling, stable single-frequency abnormal noise / stable single-frequency sound is characterized by a prominent peak in the noise spectrum. The amplitude of the peak (noise peak value) is higher than the amplitude of the corresponding adjacent frequency, and the power of this peak accounts for a relatively small proportion of the total noise power. That is, the power of the peak accounts for a proportion of the total noise power that is less than or equal to the power threshold, where the power threshold is determined based on experimental data. Figure 2a As shown by the blue curve, the bandwidth of this peak does not exceed 50Hz. See also Figure 2b In stable single-frequency noise, the power amplitude in the time domain is relatively stable from the beginning of its generation, with little power variation. The ratio of the maximum power to the minimum power will not exceed 3 times, and the amplitude is generally much smaller than the maximum sound power of the speaker itself. Figure 2b The left vertical axis represents the power amplitude, and the right vertical axis represents the sound pressure amplitude; the two can be converted to each other.

[0065] This disclosure primarily detects whether a stable single-frequency abnormal sound occurs in the active noise cancellation system. (See also...) Figure 1 The abnormal sound detection method includes the following steps:

[0066] Step 101: Without the active noise cancellation system being activated, acquire the first noise signal from the noise source collected by the microphone.

[0067] The active noise reduction system is not started in step 101, that is, the controller included in the active noise reduction system is not started, and the speaker will not send a control signal.

[0068] The active noise reduction system can be used for noise reduction processing of electric appliances such as range hoods and washing machines. Taking noise reduction processing of a range hood as an example, the noise source may be, for example, a fan of the range hood, and a microphone (first microphone) for collecting a noise signal is arranged near the fan.

[0069] In step 102, the first noise signal is segmented to make the first power ratio of each signal segment of the first noise signal less than a ratio threshold, and a segmentation strategy of the first noise signal is determined.

[0070] The number of signal segments obtained by segmenting the first noise signal is determined according to the first power ratio of each signal segment. If the first power ratio of each signal segment is not less than the ratio threshold, re-segmentation processing is needed. The frequency band of each signal segment can be the same or different. The power ratio of a signal segment is the ratio of the power of the signal segment to the power of the first noise signal.

[0071] The ratio threshold can be set according to actual conditions. For example, the value range of the ratio threshold can be [40%, 50%]. Preferably, the ratio threshold is 40%. The value 40% is used to leave a margin to avoid misjudgment caused by being too close to 50%. This is because: since the criterion for judging abnormal sound is that the power ratio of a signal segment is greater than 50%, and since the power ratio of a signal segment cannot be guaranteed to be an accurate value, there may be fluctuations of up to 5% above and below the value, so if it is too close to 50%, the fluctuations may cause misjudgment of abnormal sound. By setting the ratio threshold to 40%, if the first power ratio is less than 40%, it means that the power of the signal segment has been reduced to a low enough level to avoid misjudgment caused by fluctuations in the power of the signal segment.

[0072] The segmentation strategy includes the following parameters: the number of segments, the upper and lower limit frequencies of each signal segment.

[0073] In step 103, the second noise signal is obtained when the active noise reduction system is started.

[0074] The second noise signal can be a noise signal emitted by a noise source collected by the first microphone. The noise signal emitted by the noise source is used as the basis data for subsequent abnormal sound detection, and the first microphone is arranged near the noise source. It should be noted that the second noise signal can be the collection result of one first microphone or the combination of the collection results of multiple first microphones. At this time, the second noise signal collected by the first microphone is the superposition result of the original noise signal emitted by the noise source and the feedback signal.

[0075] The active noise reduction system can be used for noise reduction of electric appliances such as range hood, washing machine, etc. Taking the noise reduction of the range hood as an example, the noise source may be, for example, the fan of the range hood, and the first microphone for collecting the noise signal is arranged near the fan.

[0076] The second noise signal can be the control signal of the loudspeaker, which will be used as the basis data for the abnormal sound detection. It should be noted that the control signal of the loudspeaker can be obtained directly by acquiring the output result of the controller, or can be collected by the second microphone arranged near the loudspeaker included in the active noise reduction system. The second noise signal can be the control signal of one loudspeaker, or a combination of the control signals of multiple loudspeakers.

[0077] The second noise signal can also be a combination of the noise signal of the noise source and the control signal of the loudspeaker, and the specific combination manner is not particularly limited in the embodiments of the present disclosure.

[0078] In step 103, the active noise reduction system is started, that is, the controller included in the active noise reduction system is started. The controller can generate a control signal and trigger the loudspeaker to emit the control signal to perform active noise reduction on the noise source. At this time, the noise signal collected by the first microphone is the second noise signal.

[0079] In step 104, the second noise signal is segmented based on the segmentation strategy.

[0080] The number of signal segments included in the second noise signal is the same as the number of signal segments included in the first noise signal, and the upper and lower limit frequencies of the signal segments included in the second noise signal are the same as the upper and lower limit frequencies of the signal segments included in the first noise signal.

[0081] In step 105, the active noise reduction system is detected based on the characteristics of each signal segment of the second noise signal.

[0082] The device equipped with the active noise reduction system, such as the range hood, may also generate a sound with a frequency spectrum similar to the stable single-frequency sound caused by the active noise reduction system, which we call "normal abnormal sound". Although this "normal abnormal sound" may also make users feel uncomfortable, it is different from the stable single-frequency sound caused by the active noise reduction system, and is not a "byproduct" of the active noise reduction system. This noise cannot be reduced by turning off or adjusting the active noise reduction system.

[0083] In this embodiment, the abnormal sound of the active noise reduction system can be quickly monitored, and the process of dividing the signal segments is a process of excluding the influence of the frequency characteristics of the device itself on the abnormal sound judgment. Because the power of the device itself may be high in some frequency bands, the high-power frequency bands can be separated out through signal segment division to exclude the influence of the frequency characteristics of the device itself on the abnormal sound judgment, and to accurately monitor the abnormal sound of the range hood.

[0084] In one embodiment, step 105 comprises: in response to the feature meeting the abnormal sound judgment condition, determining that the active noise reduction system has the stable single-frequency abnormal sound.

[0085] The feature of the signal segment may include, but is not limited to, the power of the signal segment, the power ratio of the signal segment, the maximum power of the signal segment, etc. The power ratio is the ratio of the power of the signal segment to the total power. The total power is the sum of the powers of all signal segments. The maximum power of the signal segment is the maximum value among the powers of all signal segments.

[0086] The abnormal sound judgment condition includes at least one of the following:

[0087] (1) there is a signal segment in the second noise signal with a second power ratio greater than or equal to a ratio threshold;

[0088] In the case where it is determined that there is a signal segment in the second noise signal with a second power ratio greater than or equal to a ratio threshold, it is determined that the active noise reduction system has a stable single-frequency abnormal sound.

[0089] If the second power ratio of a certain signal segment of the second noise signal is greater than or equal to the ratio threshold, it is determined that the stable single-frequency abnormal sound occurs in the frequency band of the signal segment.

[0090] (2) the difference between the total power and the maximum power of the signal segment is less than a first difference threshold;

[0091] If the difference between the total power and the maximum power of the signal segment of the second noise signal is less than the first difference threshold, it is determined that the active noise reduction system has a stable single-frequency abnormal sound.

[0092] (3) the total power is within a preset power range; wherein the lower limit of the preset power range is greater than the maximum power of the noise signal of the noise source, and the upper limit of the preset power range is less than the power of the second noise signal when the active noise reduction system generates howling;

[0093] If the total power of the second noise signal is within the preset power range, it is determined that the active noise reduction system has a stable single-frequency abnormal sound.

[0094] (4) the difference between the total power and the filtered power is greater than or equal to a second difference threshold; the filtered power is the result of filtering out the maximum power of the noise signal from the total power;

[0095] If the difference between the total power and the filtered power of the second noise signal is greater than or equal to the second difference threshold, it is determined that the active noise reduction system has a stable single-frequency abnormal sound.

[0096] (5) There is a signal segment in the second noise signal whose power difference with adjacent signal segments is greater than or equal to a third difference threshold. The adjacent signal segments of signal segment i are signal segment i-1 and signal segment i+1. Understandably, the adjacent signal segment of the first signal segment 1 is the adjacent signal segment 2, and the adjacent signal segment of the last signal segment P is the signal segment P-1. Wherein, 1≤i≤P.

[0097] If the above conditions are not met, it is determined that the active noise reduction system does not produce stable single-frequency abnormal sound.

[0098] It should be noted that any one of the above proportion threshold, preset power range, first difference threshold, second difference threshold and third difference threshold can be determined according to experimental data, or can be dynamically optimized.

[0099] Next, taking the first difference threshold as an example, the dynamic optimization process of the threshold is described:

[0100] S1, obtaining abnormal signal and normal sample.

[0101] The abnormal sample is a noise signal containing abnormal sound, and the normal sample is a noise signal not containing abnormal sound. The abnormal sample can be collected by experiment, or it can be the result of superimposing a noise signal with a frequency and amplitude matching the abnormal sound on the normal sample.

[0102] The number of abnormal samples and normal samples can be set according to actual needs. Understandably, the more samples, the better the first difference threshold optimization.

[0103] S2, constructing a target function.

[0104] The target function is constructed according to at least one of the following parameters: the number of abnormal sample missed detection, the number of normal sample false detection, the proportion of abnormal sample missed detection, and the proportion of normal sample false detection.

[0105] The design principle of the target function is to find a combination and value of the judgment parameters, so that the first difference threshold obtained by optimization can detect all stable single-frequency abnormal sounds, and the normal signal is not misjudged as abnormal sound, and has good robustness. The target function of parameter optimization can be set as: (1) (the number of abnormal sample missed detection+the number of normal sample false detection) / the total number of samples, at this time the smaller the target function is the better; (2) (the abnormal sound judgment strength of normal sample) / (the abnormal sound judgment strength of abnormal signal), at this time the smaller the target function is the better.

[0106] The abnormal sound judgment strength is the degree of abnormal sample / normal sample meeting the abnormal sound judgment. If the total abnormal sound threshold is 100, higher than 100 is abnormal sound, if the value of the normal sample is 30, the abnormal sound strength 0.3, which is the abnormal sound judgment strength of the normal sample, the smaller the value, the farther the normal sound from the abnormal sound standard, the greater the probability of the normal sound, and the higher the accuracy of the detection algorithm. If the value of the abnormal sound sample is 200, the abnormal sound strength 2, which is the abnormal sound judgment strength of the abnormal signal, the greater the value, the more likely the sound is abnormal sound, the greater the probability of the abnormal sound, and the higher the accuracy of the detection algorithm. Therefore, the smaller the value of (abnormal sound judgment strength of normal sample) / (abnormal sound judgment strength of abnormal signal), the higher the accuracy of the detection algorithm, and the better the corresponding parameter combination for detection.

[0107] The abnormal sound judgment strength can also be defined in other ways, for example: the abnormal sound judgment strength of the normal sample is the number of samples of the normal sample misjudged as abnormal sound / the total number of normal samples; the abnormal sound judgment strength of the abnormal signal is the number of samples of the abnormal sample accurately judged as abnormal sound / the total number of abnormal samples.

[0108] In addition to the above objective function, other calculation formulas similar to the design principles of the objective function can also be used, and the embodiments of the present disclosure are not particularly limited.

[0109] S3, optimizing the target function in a preset optimization range of the first difference threshold value to determine the final first difference threshold value.

[0110] In one embodiment, the preset optimization range is [1dB, 10dB], that is, the first difference threshold value is searched for the optimal solution in [1dB, 10dB] to make the target function minimum.

[0111] In this embodiment, the optimization range of the first difference threshold value is provided, so that the optimization meets certain physical characteristics of abnormal sound, and the optimization accuracy and efficiency can be improved.

[0112] In one embodiment, the optimization algorithm includes at least one of the following algorithms: genetic algorithm, simulated annealing algorithm, particle swarm algorithm, Bayesian optimization algorithm, hill climbing algorithm. In other implementations, the sound pressure value can also be used as a feature of the signal segment for abnormal sound detection, and the specific implementation process is similar to the power, which will not be repeated here.

[0113] In one embodiment, the first noise signal is segmented by a band-stop filter.

[0114] In one embodiment, step 102 includes the following steps:

[0115] Step 102-1, the first noise signal is divided into at least two signal segments, and it is judged whether the first power proportion of each signal segment is less than the proportion threshold.

[0116] In step 102-1, if the judgment result is yes, step 103 is executed; if the judgment result is no, step 102-2 is executed.

[0117] The initial segmentation number of the first noise signal can be set according to actual needs. Taking the initial segmentation number as 3 segments as an example, 3 signal segments are obtained, and the frequency bands of each signal segment of the first noise signal are [20Hz, 1000Hz), [1000Hz, 2000Hz), and [2000Hz, 3000Hz]. Among them, according to the characteristics of the range hood noise and the characteristics of the active noise reduction abnormal sound, the main frequency band range to be concerned is determined as 20Hz-3000Hz, that is, the first noise signal with a frequency band of 20Hz-3000Hz is segmented and processed.

[0118] The calculation method of the first power proportion of each signal segment when the first noise signal is segmented and processed by the band-stop filter is introduced below, and the formula is as follows:

[0119] H = 1 - e i / E;

[0120]

[0121] Among them, H represents the power proportion; e i represents the power of the first noise signal corresponding to the i-th signal segment; E represents the total power of all signal segments contained in the first noise signal; X j (t) represents the amplitude of the j-th sampling point of the noise signal in the time domain; N represents the number of sampling points contained in the noise signal. e i The calculation method of E is similar to that of E.

[0122] Step 102-2, in the case where the judgment result is no, the signal segment with the first power proportion greater than or equal to the proportion threshold is segmented and processed again until the first power proportion of each signal segment is less than the proportion threshold.

[0123] The following takes a specific example to illustrate the specific implementation process of step 102: the frequency band of the first noise signal is divided into [20Hz, 1000Hz), [1000Hz, 2000Hz), [2000Hz, 3000Hz] three frequency band signal segments, a band-stop filter is designed to filter the frequency band [20Hz, 1000Hz), [1000Hz, 2000Hz), [2000Hz, 3000Hz], and the first noise signal is filtered based on the band-stop filter to obtain the power of the signals corresponding to the three signal segments, that is, the signal power of the first noise signal after filtering out the above three frequency bands is e1, e2, and e3, respectively, and the first power ratios corresponding to the three signal segments are calculated as 1-e1 / E, 1-e2 / E, and 1-e3 / E, respectively. It is judged whether the power ratio of a certain signal segment exceeds the ratio threshold. If yes, the signal segment is further divided into at least two signal segments. Preferably, considering the calculation amount and the accuracy of power division, the signal segment is divided into two signal segments to eliminate the influence of the frequency characteristics of the device (such as a range hood) carrying the active noise reduction system on the subsequent active noise reduction abnormal sound judgment. Here, it is assumed that the first power ratio corresponding to [20Hz, 1000Hz) is greater than 40%, and the [20Hz, 1000Hz) frequency band is further segmented, for example, into [20, 500), [500, 1000).

[0124] It should be noted that for a frequency band [20, 1000], it is initially known only that its proportion of the total power is how much, but it is not known that the frequency point at which the frequency band can be evenly divided in this 20 to 1000Hz is which, so the middle value is taken here, the purpose being to evenly divide the power as much as possible. In an embodiment, the first noise signal is segmented by a band-pass filter, and taking three segments as an example, the corresponding first power ratios are e1 / E, e2 / E, and e3 / E.

[0125] In an embodiment, the second noise signal is segmented by a band-stop filter in step 104. In this step, only one segmentation is needed, the second power ratios of the signal segments of the second noise signal are calculated, and then it is judged whether the active noise reduction system produces abnormal sound according to the second power ratios.

[0126] The calculation method of the second power ratio is similar to that of the first power ratio, which will not be described here.

[0127] Corresponding to the foregoing abnormal sound detection method embodiments, the present disclosure also provides embodiments of an abnormal sound detection device.

[0128] Figure 3A module schematic diagram of an abnormal sound detection device is provided for an exemplary embodiment of the present disclosure, which is applied to an active noise reduction system, the active noise reduction system comprising a microphone; the abnormal sound detection device comprising:

[0129] An acquisition module 31 is configured to acquire a first noise signal of a noise source collected by the microphone when the active noise reduction system is not started;

[0130] A first segmentation module 32 is configured to perform segmentation processing on the first noise signal, so that a first power proportion of each signal segment of the first noise signal is less than a proportion threshold, and determine a segmentation strategy of the first noise signal;

[0131] The acquisition module 31 is further configured to acquire a second noise signal when the active noise reduction system is started; the second noise signal comprises a noise signal of a noise source collected by the microphone and / or a control signal of the loudspeaker;

[0132] A second segmentation module 33 is further configured to perform segmentation processing on the second noise signal based on the segmentation strategy;

[0133] A detection module 34 is configured to perform abnormal sound detection on the active noise reduction system according to a feature of each signal segment of the second noise signal.

[0134] Optionally, the detection module is specifically configured to:

[0135] In response to the feature meeting an abnormal sound judgment condition, it is determined that the active noise reduction system has a stable single-frequency abnormal sound;

[0136] The abnormal sound judgment condition comprises at least one of the following:

[0137] There is a signal segment with a second power proportion greater than or equal to the proportion threshold in the second noise signal; the feature comprises the second power proportion; the second power proportion is a ratio of a power of the signal segment to a total power, and the total power is a sum of powers of each signal segment;

[0138] A difference between the total power and a maximum power of the signal segment is less than a first difference threshold; the feature comprises the power of the signal segment;

[0139] The total power is within a preset power range; a lower limit value of the preset power range is greater than a maximum power of the noise signal of the noise source, and an upper limit value of the preset power range is less than a power of the second noise signal when the active noise reduction system occurs howling;

[0140] A difference between the total power and a power difference value is greater than or equal to a second difference threshold; the power difference value is a difference between the total power and a maximum power of the noise signal;

[0141] The second noise signal has a signal segment whose power difference with an adjacent signal segment is greater than or equal to a third difference threshold.

[0142] Optionally, the first segmentation module comprises:

[0143] a segmentation unit configured to segment the first noise signal into at least two signal segments;

[0144] a judgment unit configured to judge whether the first power proportion of each signal segment is less than a proportion threshold, and in the case of no, call the segmentation unit to segment the signal segment whose first power proportion is greater than or equal to the proportion threshold again until the first power proportion of each signal segment is less than the proportion threshold.

[0145] Optionally, the first segmentation module segments the first noise signal through a band-stop filter.

[0146] And / or, the second segmentation module segments the second noise signal through the band-stop filter.

[0147] Optionally, the calculation formula of the power proportion of the signal segment is as follows:

[0148] H = 1 - e i / E;

[0149]

[0150] wherein H represents the power proportion; e i represents the power corresponding to the i-th signal segment in the noise signal; E represents the total power of the noise signal; N represents the number of signal segments contained in the noise signal; X j (t) represents the amplitude of the j-th sampling point of the noise signal in the time domain; N represents the number of sampling points contained in the noise signal.

[0151] For the device embodiment, since it basically corresponds to the method embodiment, the related parts can be referred to the part of the method embodiment. The device embodiment described above is only illustrative, wherein the units described as separate components can or can not be physically separated, and the components of the unit can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. According to the actual needs, part or all of the modules can be selected to achieve the purpose of the present disclosure.

[0152] The present disclosure also provides a control method of an active noise reduction system, which comprises: detecting the active noise reduction system according to the abnormal sound detection method provided in any of the above embodiments; and in response to the existence of stable single-frequency abnormal sound in the active noise reduction system, restarting the active noise reduction system.

[0153] According to experience, the abnormal sound of the active noise reduction system is generated due to some faults or interferences, restarting the active noise reduction system can weaken or eliminate the faults or interferences, improve the effectiveness of the active noise reduction system, and further improve the user experience.

[0154] Figure 4 A structural schematic diagram of an electronic device is shown for an example embodiment of the present disclosure, the electronic device comprising a memory, a processor, and a computer program stored on the memory and used for running on the processor, and the processor implements the abnormal sound detection method of any of the above embodiments when executing the computer program. Figure 4 The displayed electronic device 40 is only an example and should not bring any limitation to the function and use range of the embodiments of the present disclosure.

[0155] As shown in Figure 4 The electronic device 40 can be in the form of a general computing device, for example, it can be a server device. The components of the electronic device 40 can include but are not limited to the above-mentioned at least one processor 41, the above-mentioned at least one memory 42, and a bus 43 connecting different system components including the memory 42 and the processor 41.

[0156] The bus 43 includes a data bus, an address bus, and a control bus.

[0157] The memory 42 can include volatile memory, such as random access memory (RAM) 421 and / or cache memory 422, and can further include read-only memory (ROM) 423.

[0158] The memory 42 can further include a program tool 425 (or utility tool) having a set of (at least one) program modules 424, such as an operating system, one or more application programs, other program modules, and program data, each of which or some combination of which can include implementation of a network environment.

[0159] The processor 41 performs various functional applications and data processing by running the computer program stored in the memory 42, such as the abnormal sound detection method provided by any of the above embodiments.

[0160] The electronic device 40 can also communicate with one or more external devices 44 such as a keyboard, a pointing device, etc. through an input / output (I / O) interface 45. Further, the electronic device 40 can communicate with one or more networks such as a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet, through a network adapter 46. As depicted, the network adapter 46 communicates with the other modules of the electronic device 40 through the bus 43. It should be appreciated that other hardware and / or software modules can be used in conjunction with the electronic device 40 such as, but not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID (Redundant Array of Independent Disks) systems, tape drives, and data archival storage systems, etc. without deviating from the scope of the disclosure.

[0161] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the foregoing detailed description, such a division is merely exemplary and not mandatory. Indeed, according to embodiments of the disclosure, features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, features and functions of one unit / module described above can be further divided into units / modules embodied by multiple units / modules.

[0162] The embodiments of the disclosure further provide a computer readable storage medium, having stored thereon a computer program, which, when executed by a processor, implements the abnormal sound detection method according to any one of the embodiments described above.

[0163] More specifically, the readable storage medium can include, but is not limited to, a portable disc, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0164] The embodiments of the disclosure further provide a computer program product, comprising a computer program, which, when executed by a processor, implements the abnormal sound detection method according to any one of the embodiments described above.

[0165] The program code for carrying out the computer program product of the disclosure can be written in any combination of one or more programming languages, and can be executed entirely on the user device, partially on the user device, as a standalone software package, partially on the user device and partially on a remote device, or entirely on a remote device.

[0166] Although the specific embodiments of the present disclosure are described above, those skilled in the art should understand that this is only an example, and the protection scope of the present disclosure is defined by the appended claims. Those skilled in the art can make various changes or modifications to the embodiments without departing from the principles and essence of the present disclosure, and these changes and modifications all fall within the protection scope of the present disclosure.

Claims

1. A method of detecting a squeal sound, characterized by, The application is applied to an active noise reduction system, the active noise reduction system comprises a microphone and a speaker; the abnormal sound detection method comprises: In the case that the active noise reduction system is not started, a first noise signal of a noise source collected by the microphone is acquired; The first noise signal is segmented to make the first power proportion of each signal segment of the first noise signal less than a proportion threshold, and a segmentation strategy of the first noise signal is determined; In the case that the active noise reduction system is started, a second noise signal is acquired; the second noise signal comprises a noise signal of a noise source collected by the microphone and / or a control signal of the speaker; The second noise signal is segmented based on the segmentation strategy, and the active noise reduction system is detected based on the characteristics of each signal segment of the second noise signal.

2. The abnormal sound detection method according to claim 1, characterized by, The detection of the active noise reduction system based on the characteristics of each signal segment of the second noise signal comprises: In response to the characteristics meeting an abnormal sound judgment condition, it is determined that the active noise reduction system has a stable single-frequency abnormal sound; The abnormal sound judgment condition comprises at least one of the following: There is a signal segment with a second power proportion greater than or equal to the proportion threshold in the second noise signal; the characteristics comprise the second power proportion; the second power proportion is the ratio of the power of the signal segment to the total power, and the total power is the sum of the powers of the signal segments; The difference between the total power and the maximum power of the signal segment is less than a first difference threshold; the characteristics comprise the power of the signal segment; The total power is within a preset power range; the lower limit of the preset power range is greater than the maximum power of the noise signal of the noise source, and the upper limit of the preset power range is less than the power of the second noise signal when the active noise reduction system produces howling; The difference between the total power and the filtering power is greater than or equal to a second difference threshold; the filtering power is the result of filtering the maximum power of the noise signal from the total power; There is a signal segment in the second noise signal, and the power difference between adjacent signal segments is greater than or equal to a third difference threshold.

3. The abnormal sound detection method according to claim 1, characterized by, The segmentation of the first noise signal to make the first power proportion of each signal segment of the first noise signal less than the proportion threshold comprises: The first noise signal is segmented into at least two signal segments, and it is judged whether the first power proportion of each signal segment is less than the proportion threshold; In the case that the judgment result is no, the signal segment with the first power proportion greater than or equal to the proportion threshold is segmented again until the first power proportion of each signal segment is less than the proportion threshold.

4. The abnormal sound detection method according to any one of claims 1 to 3, characterized by, The first noise signal is segmented by a band-stop filter; And / or, the second noise signal is segmented by the band-stop filter.

5. The abnormal sound detection method according to claim 4, characterized by, The calculation formula of the power proportion of the signal segment is as follows: H = 1 - e i / E; wherein H represents the power proportion; e i represents the power of the i-th signal segment in the noise signal; E represents the sum of the powers of the signal segments contained in the noise signal; X j (t) represents the amplitude of the j-th sampling point of the noise signal in the time domain; N represents the number of sampling points contained in the noise signal.

6. A squeal detection device characterized by comprising: The application is applied to an active noise reduction system, the active noise reduction system comprises a microphone and a speaker; The abnormal sound detection device comprises: An acquisition module is configured to acquire a first noise signal of a noise source collected by the microphone in the case that the active noise reduction system is not started; The first segmentation module is configured to segment the first noise signal, so that a first power proportion of each signal segment of the first noise signal is less than a proportion threshold, and determine a segmentation strategy of the first noise signal. The acquisition module is further configured to acquire a second noise signal when the active noise reduction system is started, wherein the second noise signal comprises a noise signal of a noise source collected by the microphone and / or a control signal of the loudspeaker. The second segmentation module is further configured to segment the second noise signal based on the segmentation strategy. The detection module is configured to detect an abnormal sound of the active noise reduction system according to a feature of each signal segment of the second noise signal.

7. The discord detection apparatus of claim 6, wherein The first segmentation module comprises: A segmentation unit configured to divide the first noise signal into at least two signal segments. A judgment unit configured to judge whether the first power proportion of each signal segment is less than the proportion threshold, and call the segmentation unit to segment the signal segment whose first power proportion is greater than or equal to the proportion threshold again until the first power proportion of each signal segment is less than the proportion threshold, when the judgment result is no.

8. The squeal detection device of claim 6 or 7, wherein The first segmentation module segments the first noise signal by using a band-stop filter. The second segmentation module segments the second noise signal by using the band-stop filter.

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory for running on the processor, characterized in that, The processor executes the computer program to implement the abnormal sound detection method in any one of claims 1 to 4.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the abnormal sound detection method in any one of claims 1 to 4.

Images