CN114974301A - Abnormal sound detection method, computer readable storage medium and electronic device - Google Patents
Abnormal sound detection method, computer readable storage medium and electronic device Download PDFInfo
- Publication number
- CN114974301A CN114974301A CN202210398909.1A CN202210398909A CN114974301A CN 114974301 A CN114974301 A CN 114974301A CN 202210398909 A CN202210398909 A CN 202210398909A CN 114974301 A CN114974301 A CN 114974301A
- Authority
- CN
- China
- Prior art keywords
- domain signal
- abnormal sound
- detection method
- abnormal
- time domain
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
- G10L25/18—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being spectral information of each sub-band
Abstract
The invention relates to an abnormal sound detection method, a computer readable storage medium and an electronic device, wherein the abnormal sound detection method comprises the following steps: acquiring a time domain signal in equipment to be detected, wherein the time domain signal comprises sound information to be analyzed; processing the time domain signal into a frequency domain signal; modifying the acoustic model; calculating and processing the frequency domain signal by the acoustic model to obtain processed sound information; selecting the processed sound information to include a range of abnormal sound wave bands; and obtaining the acoustic power in the range of the abnormal sound wave band, and determining whether the equipment to be detected has abnormal sound according to the acoustic power value. The abnormal sound detection method is suitable for non-sinusoidal signal scenes, can detect abnormal sounds by 100 percent, and has good application prospect.
Description
Technical Field
The present invention relates to the field of abnormal sound detection technologies, and in particular, to an abnormal sound detection method, a computer-readable storage medium, and an electronic device.
Background
In the field of electroacoustic and vibration testing, subjective listening and objective testing means for detecting abnormal sound of products always have the condition that the subjective listening and the objective testing means cannot completely correspond to each other. Subjective human ears hear more obvious abnormal sounds, and objective testing means can not be distinguished; or some good products are judged as defective products by mistake. And the abnormal sound detection technology of many manufacturers is limited to sine sweep frequency signals, and the abnormal sound detection algorithm is designed according to the characteristics of the sine signals.
The abnormal sound detection technology of the rub & buzz algorithm of the listen company in the prior art: feeding the electro-acoustic product with a sinusoidal sweep signal; separating fundamental wave, 2 harmonic and 3 harmonic … N harmonic by using Harmonic track technology of listen company; according to the frequency masking effect of human ears (fig. 1), low-order harmonics are easily masked by the fundamental wave, and high-order harmonics are not easily masked by the fundamental wave; the high-order harmonic listening feeling is completely different from the fundamental wave, and the high-order harmonic listening feeling is considered as abnormal sound generated by the product; the energy components of the higher harmonics are extracted and defined as heteronym Rub & Buzz.
In the prior art, the PureSound abnormal sound detection technology of NTI company: feeding a chirp sinusoidal signal of an electroacoustic product; simulating an auditory model of human ears, and filtering the acquired signals in 6 frequency bands to obtain 6 curves; by derivation and taking absolute values, etc., the abrupt change component of each curve is amplified, and the abrupt change component is identified as an abnormal sound.
The prior art (abnormal sound detection means such as rub & buzz, puresound, ICHD) has two problems: 1. the hearing of human ears can not correspond to 100% of an objective detection algorithm; 2. the existing abnormal sound detection algorithm is generally designed according to a sine excitation signal and is not suitable for non-sine signal scenes (112 voice abnormal sound, motor abnormal sound, fan abnormal sound and the like).
Disclosure of Invention
According to the problems in the prior art, the invention provides an abnormal sound detection method, which is a method suitable for a non-sinusoidal signal scene and capable of detecting abnormal sounds by 100% according to Trust software.
The technical scheme of the invention is as follows:
an abnormal sound detection method comprises the following steps:
acquiring a time domain signal in equipment to be detected, wherein the time domain signal comprises sound information to be analyzed;
processing the time domain signal into a frequency domain signal;
modifying the acoustic model;
calculating and processing the frequency domain signal through an acoustic model to obtain processed sound information;
selecting the processed sound information to include the range of the abnormal sound wave band;
and obtaining the acoustic power within the range of the abnormal sound wave band, and determining whether the equipment to be detected has the abnormal sound according to the acoustic power value.
As a preferred technical scheme, a time domain signal in the equipment to be detected is obtained, wherein the time domain signal comprises sound information to be analyzed, and the time domain signal comprises sampling rate and discretized sound information.
As a preferred technical scheme, processing a time domain signal into a frequency domain signal specifically includes: and the time domain signal is subjected to Fourier transform to obtain a frequency domain signal.
As a preferable technical scheme, the acoustic model is corrected, wherein the acoustic model comprises an outer ear and middle ear program algorithm and an inner ear noise program algorithm, and the outer ear and middle ear model is corrected to be 5khz without attenuation.
As a preferred technical scheme, the frequency domain signal is subjected to calculation processing by an acoustic model, specifically: and the frequency domain signal is processed by an external ear program algorithm and a middle ear program algorithm and an internal ear noise program algorithm in sequence to obtain processed sound information.
As a preferred technical solution, the selected processed sound information includes a range of different sound bands, specifically: and selecting the bandwidth or frequency band of the processed sound information.
As a preferable technical scheme, the bandwidth or the frequency band is set by an analysis module and is set to be 4k-20k and/or 8k-20 k.
As a preferred technical solution, the acoustic power in the range of the abnormal sound wave band is obtained, and then the abnormal sound curve changing with time can be made according to the acoustic power.
The present application also provides a computer readable storage medium storing one or more programs which, when executed by a processor, cause the processor to perform the method of detecting an abnormal sound as described above.
The present application also provides an electronic device comprising a computer readable storage medium storing one or more programs, wherein the one or more programs, when executed by a processor, cause the processor to perform the method of detecting an abnormal sound as any one of the above.
The technical scheme adopted by the invention achieves the following beneficial effects:
1. the abnormal sound detection method is applied to items such as abnormal sound of a touch screen, 112 voice abnormal sound, abnormal sound detection of a notebook fan and the like, can detect the abnormal sound by 100 percent and can be introduced into the items for use;
2. aiming at the detection means in the prior art, Trustsystem software is adopted, and the proposed abnormal sound detection method has considerable market prospect in abnormal sound detection.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below to form a part of the present invention, and the exemplary embodiments and the description thereof illustrate the present invention and do not constitute a limitation of the present invention. In the drawings:
fig. 1 is a schematic diagram of an abnormal sound detection method disclosed in embodiment 1 of the present invention;
fig. 2 is a schematic diagram of an abnormal sound detection method disclosed in embodiment 1 of the present invention;
fig. 3 is a schematic diagram of an abnormal sound detection method disclosed in embodiment 1 of the present invention;
fig. 4 is a schematic diagram of an abnormal sound detection method disclosed in embodiment 1 of the present invention;
fig. 5 is a schematic diagram of an abnormal sound detection method disclosed in embodiment 1 of the present invention;
fig. 6 is a schematic diagram of an abnormal sound detection method disclosed in embodiment 1 of the present invention;
fig. 7 is a schematic diagram of an abnormal sound detection method disclosed in embodiment 1 of the present invention;
fig. 8 is a schematic view of an abnormal sound detection method disclosed in embodiment 1 of the present invention;
fig. 9 is a schematic diagram of an abnormal sound detection method disclosed in embodiment 1 of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the specific embodiments of the present invention and the accompanying drawings. In the description of the present invention, it should be noted that the term "or" is generally employed in its sense including "and/or" unless the content clearly dictates otherwise.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
Trust software is audio testing software and is also a large software platform. Trust software is PC-based electric sound testing software, can provide a wide platform for customers, and different module combinations can be applied to different fields, so that the testing requirements of multiple projects and multiple tasks are met.
In this embodiment, Trust software is used to provide an abnormal sound detection method, which includes, according to fig. 1:
acquiring a time domain signal in equipment to be detected, wherein the time domain signal comprises sound information to be analyzed;
processing the time domain signal into a frequency domain signal;
modifying the acoustic model;
calculating and processing the frequency domain signal through an acoustic model to obtain processed sound information;
selecting the processed sound information to include the range of the abnormal sound wave band;
and obtaining the acoustic power within the range of the abnormal sound wave band, and determining whether the equipment to be detected has the abnormal sound according to the acoustic power value.
Subjective human ears listen to a plurality of good products and defective products, and Trust software picks up time domain signals of the products, which is shown in figure 2;
preferably, a time domain signal in the device to be tested is obtained, wherein the time domain signal comprises sound information to be analyzed.
Preferably, the time domain signal comprises a sample rate, the sound information being discretized.
Preferably, the time domain signal is transformed by fourier transform to obtain a frequency domain signal. Processing the time domain signal into a time-frequency-amplitude diagram through Trust software, wherein a time resolution dt and a frequency resolution df are self-set by combining an actual situation to distinguish long noise from short noise as shown in figure 3; the amplitude value at m × dt is denoted as spl (m × dt), where m × dt represents the mth dt time.
Preferably, the acoustic model includes the outer and middle ear programming algorithms, see fig. 4, and the inner ear noise programming algorithm, see fig. 6, with no attenuation after the outer and middle ear models are modified to 5khz, see fig. 5.
Preferably, the frequency domain signal is processed by the external ear and middle ear program algorithm and the internal ear noise program algorithm in sequence, and then processed sound information is obtained. The spl values were modeled after the external and middle ear models. The attenuation of the original acoustic model after 5khz is shown in fig. 4, the model is corrected considering that subjective human ears are sensitive to product listening and the human ears are sensitive to high-frequency sound, the attenuation is not carried out after 5khz, the model is shown in fig. 5, and then signals are superposed with an inner ear noise program algorithm.
Preferably, the bandwidth or frequency band of the processed sound information is selected. The signal sets a proper bandwidth, see fig. 7, or defines a frequency band, see fig. 8, and the frequency band is defined by filtering out inherent sound on a production line or inherent nonlinear components of a product, and extracting sound power in the bandwidth, that is, the sound power is taken as an abnormal sound component and is recorded as rb (m × dt).
Preferably, the bandwidth or frequency band is set by an analysis module, and the bandwidth or frequency band is set to be 4k-20k, and/or 8k-20 k. The bandwidth and the frequency band are set in Trust software, an analysis module in Trust and an rb curve branch in the analysis module are set.
The selection of the bandwidth or the frequency band and the setting range are selected and set according to actual requirements, and may also be limited according to requirements by those skilled in the art, which is not specifically described in this embodiment.
Preferably, after obtaining the sound power in the range of the different-tone wave band, a time-varying different-tone Curve, i.e. RB Curve, can be made according to the sound power, see fig. 9, and different products are detected, wherein RB Curve has different states. The abnormal sound detection method provided by the embodiment can analyze abnormal sounds of a non-swept frequency scene, such as 112 voice abnormal sounds, motor abnormal sounds, fan abnormal sounds and the like, is convenient for production test frame management and control, and can achieve the effect of matching subjective listening and objective test means.
Example 2
The present application also provides a computer-readable storage medium storing one or more programs which, when executed by a processor, cause the processor to perform the abnormal sound detection method of embodiment 1.
The present application also provides an electronic device comprising a computer-readable storage medium storing one or more programs which, when executed by a processor, cause the processor to perform the abnormal sound detection method of embodiment 1.
The abnormal sound detection method, the computer-readable storage medium and the electronic device in the embodiment of the present application are described in detail above, and a specific example is applied in the present application to explain the principle and the implementation of the present application, and the description of the above embodiment is only used to help understanding the method and the core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (10)
1. An abnormal sound detection method is characterized by comprising the following steps:
acquiring a time domain signal in equipment to be detected, wherein the time domain signal comprises sound information to be analyzed;
processing the time domain signal into a frequency domain signal;
modifying the acoustic model;
calculating and processing the frequency domain signal by the acoustic model to obtain processed sound information;
selecting the processed sound information to include a range of abnormal sound wave bands;
and obtaining the acoustic power in the range of the abnormal sound wave band, and determining whether the equipment to be detected has abnormal sound according to the acoustic power value.
2. The abnormal sound detection method according to claim 1, wherein a time domain signal in the device to be detected is obtained, the time domain signal including sound information to be analyzed,
wherein the time domain signal comprises a sampling rate, the discretized sound information.
3. The abnormal noise detection method according to claim 1, wherein the time domain signal is processed into a frequency domain signal, specifically:
and obtaining a frequency domain signal by the time domain signal through Fourier transform.
4. The abnormal sound detection method according to claim 1, wherein the acoustic model is corrected,
wherein the acoustic model comprises an outer ear and middle ear program algorithm and an inner ear noise program algorithm, and no attenuation is performed after the outer ear and middle ear model is corrected to be 5 khz.
5. The abnormal sound detection method according to claim 1, wherein the frequency domain signal is subjected to the calculation processing by the acoustic model, specifically:
and the frequency domain signal is processed by the external ear and middle ear program algorithm and the internal ear noise program algorithm in sequence to obtain processed sound information.
6. The abnormal sound detection method according to claim 1, wherein the processed sound information is selected to include an abnormal sound waveband range, specifically:
and selecting the bandwidth or frequency band of the processed sound information.
7. The abnormal sound detection method according to claim 6, wherein the bandwidth or the frequency band is set by an analysis module, and the bandwidth or the frequency band is set to be 4k-20k, and/or 8k-20 k.
8. The abnormal tone detection method according to claim 1, wherein the acoustic power in the abnormal tone band range is obtained, and thereafter,
and making a time-varying abnormal sound curve according to the sound power.
9. A computer readable storage medium storing one or more programs which, when executed by a processor, cause the processor to perform the alien sound detection method of any one of claims 1-8.
10. An electronic device comprising a computer readable storage medium storing one or more programs, wherein the one or more programs, when executed by a processor, cause the processor to perform the alien-tone detection method of any of claims 1-8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210398909.1A CN114974301A (en) | 2022-04-15 | 2022-04-15 | Abnormal sound detection method, computer readable storage medium and electronic device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210398909.1A CN114974301A (en) | 2022-04-15 | 2022-04-15 | Abnormal sound detection method, computer readable storage medium and electronic device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114974301A true CN114974301A (en) | 2022-08-30 |
Family
ID=82977136
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210398909.1A Pending CN114974301A (en) | 2022-04-15 | 2022-04-15 | Abnormal sound detection method, computer readable storage medium and electronic device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114974301A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117454300A (en) * | 2023-12-21 | 2024-01-26 | 广东美的制冷设备有限公司 | Motor abnormal sound detection method and device, electronic equipment and storage medium |
-
2022
- 2022-04-15 CN CN202210398909.1A patent/CN114974301A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117454300A (en) * | 2023-12-21 | 2024-01-26 | 广东美的制冷设备有限公司 | Motor abnormal sound detection method and device, electronic equipment and storage medium |
CN117454300B (en) * | 2023-12-21 | 2024-04-05 | 广东美的制冷设备有限公司 | Motor abnormal sound detection method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101600144B (en) | Method and system for obtaining a plurality of parameters of electro-acoustic product by adopting continuous logarithmic swept-frequency signal | |
EP2730099B1 (en) | Estimating nonlinear distortion and parameter tuning for boosting sound | |
CN101426168B (en) | Sounding body abnormal sound detection method and system | |
EP3166239B1 (en) | Method and system for scoring human sound voice quality | |
CN105530565A (en) | Automatic sound equalization device | |
CN112017693B (en) | Audio quality assessment method and device | |
CN110942781B (en) | Sound processing method and sound processing apparatus | |
CN102547526A (en) | Real-time monitoring method and system of microphone working state | |
CN114974301A (en) | Abnormal sound detection method, computer readable storage medium and electronic device | |
CN112700399B (en) | Defect detection visualization method and system | |
CN112135235B (en) | Quality detection method, system and computer readable storage medium | |
Barrera-Figueroa | Free-field reciprocity calibration of measurement microphones at frequencies up to 150 kHz | |
CN116684806A (en) | Method for testing abnormal sound of loudspeaker | |
CN107438221B (en) | Online loudspeaker sound pressure detector and detection method | |
CN110390954B (en) | Method and device for evaluating quality of voice product | |
Voishvillo | Assessment of Nonlinearity in Transducers and Sound Systems–from THD to Perceptual Models | |
CN108040315A (en) | A kind of test machine of computer-readable recording medium and the application medium | |
CN109688503A (en) | Psychological response condition detecting system and method | |
CN115002642A (en) | Feature extraction method for abnormal sound of loudspeaker based on combination of auditory masking and SVD-MRMR | |
CN109862458B (en) | Psychological perception state detection system and method | |
CN111885474A (en) | Microphone testing method and device | |
CN112908347A (en) | Noise detection method and terminal | |
CN110996205A (en) | Earphone control method, earphone and readable storage medium | |
US20230209240A1 (en) | Method and system for authentication and compensation | |
CN112312258B (en) | Intelligent earphone with hearing protection and hearing compensation |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |