CN115460530A - Stereo set inspection management system - Google Patents

Stereo set inspection management system Download PDF

Info

Publication number
CN115460530A
CN115460530A CN202211080169.3A CN202211080169A CN115460530A CN 115460530 A CN115460530 A CN 115460530A CN 202211080169 A CN202211080169 A CN 202211080169A CN 115460530 A CN115460530 A CN 115460530A
Authority
CN
China
Prior art keywords
sound
fault
module
audio
external
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.)
Withdrawn
Application number
CN202211080169.3A
Other languages
Chinese (zh)
Inventor
梁杰林
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Shengjiu Acousto Optic Technology Co ltd
Original Assignee
Guangzhou Shengjiu Acousto Optic Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou Shengjiu Acousto Optic Technology Co ltd filed Critical Guangzhou Shengjiu Acousto Optic Technology Co ltd
Priority to CN202211080169.3A priority Critical patent/CN115460530A/en
Publication of CN115460530A publication Critical patent/CN115460530A/en
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R29/00—Monitoring arrangements; Testing arrangements
    • H04R29/001—Monitoring arrangements; Testing arrangements for loudspeakers
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/01—Arrangements or apparatus for facilitating the optical investigation
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/28—Testing of electronic circuits, e.g. by signal tracer
    • G01R31/2851—Testing of integrated circuits [IC]
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
    • G01R31/52—Testing for short-circuits, leakage current or ground faults
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/56—Extraction of image or video features relating to colour
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/18—Status alarms
    • G08B21/185—Electrical failure alarms
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B7/00—Signalling systems according to more than one of groups G08B3/00 - G08B6/00; Personal calling systems according to more than one of groups G08B3/00 - G08B6/00
    • G08B7/06—Signalling systems according to more than one of groups G08B3/00 - G08B6/00; Personal calling systems according to more than one of groups G08B3/00 - G08B6/00 using electric transmission, e.g. involving audible and visible signalling through the use of sound and light sources
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; 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
    • G10L25/21—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 power information
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; 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
    • G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
    • G10L25/30—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique using neural networks
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; 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
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/01—Arrangements or apparatus for facilitating the optical investigation
    • G01N2021/0106—General arrangement of respective parts
    • G01N2021/0112—Apparatus in one mechanical, optical or electronic block

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Acoustics & Sound (AREA)
  • Signal Processing (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Otolaryngology (AREA)
  • Emergency Management (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Business, Economics & Management (AREA)
  • Computer Hardware Design (AREA)
  • Microelectronics & Electronic Packaging (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)

Abstract

The invention discloses a sound inspection management system which comprises an external detection module for identifying external damage of a sound, a fault detection module for identifying a fault part of the sound, an audio acquisition module for acquiring sound playing data, an audio analysis module for identifying noise in audio, and a fault prompt module for early warning according to identification results of the modules. The invention can realize the omnibearing detection of external damage, circuit fault and unclear tone quality of the sound, extracts and identifies the damaged part of the sound through the color characteristic of the external detection module, detects the circuit fault in the sound through the universal meter resistor in the fault detection module, identifies the tone quality of the sound through the convolutional neural network established by the audio analysis module, optimizes the model to improve the tone quality identification precision, and finally carries out early warning according to different identification results, thereby being convenient for removing the fault in time.

Description

Stereo set inspection management system
Technical Field
The invention belongs to the technical field of sound detection, and particularly relates to a sound inspection management system.
Background
With the development of science and technology and the improvement of living standard in recent years, people's pursuit for entertainment is more and more diversified. One such entertainment effect is the presentation of sound. Such as movie theaters, concerts, opera shows, phase shows or others, many require sound as a primary or secondary performance. Therefore, the sound quality affects the people's experience during the entertainment process.
In general, a sound system is composed of three modules, namely an audio processor, power amplifier equipment and sound box equipment. Wherein audio amplifier equipment contains high frequency, intermediate frequency, the three frequency channel unit of low frequency, when the audio amplifier broke down, needed to detect the frequency channel unit of specific trouble. However, in the existing detection method, a sound tester can detect a specific frequency band unit with a fault only by means of professional hearing, and needs to fix a sound at the same time and continuously adjust the position of detection equipment, so as to perform tests at different angles and distances. Usually fixed by artifical manual, complex operation to the position that manual adjustment detected, artifical intervention degree is higher, seriously reduces work efficiency, and the position precision is wayward, makes the detection effect difference big, and the testing result has certain error.
Disclosure of Invention
The invention aims to provide a sound inspection management system to solve the problems in the prior art.
In order to achieve the purpose, the invention provides a sound inspection management system, which comprises an external detection module, a fault detection module, an audio acquisition module, an audio analysis module and a fault prompt module, wherein the external detection module is used for detecting a fault;
the external detection module is used for identifying external damage of the sound equipment, acquiring an external identification result and transmitting the external identification result to the fault prompt module;
the fault detection module is used for identifying circuit faults and component faults of the sound, acquiring circuit identification results and transmitting the circuit identification results to the fault prompt module;
the audio acquisition module is used for acquiring playing data of the sound equipment, preprocessing the playing data and transmitting the preprocessed playing data to the audio analysis module;
the audio analysis module is used for analyzing the audio data, identifying a noise part in the playing data and a component part in the sound which causes the noise to appear, acquiring a tone quality identification result, and transmitting the tone quality identification result to the fault prompt module;
and the fault prompting module is used for receiving the external identification result, the circuit identification result and the tone quality identification result and carrying out early warning based on different identification results.
Optionally, the external detection module includes a high-definition camera device, and the high-definition camera device is configured to obtain an external image of the sound; and the external detection module identifies an external damaged part of the sound equipment by performing binarization processing on the external image.
Optionally, the fault detection module includes a universal meter, the universal meter is used for judging whether there is the short circuit phenomenon in the chip circuit of stereo set, still is used for discerning whether there is the trouble in the components and parts of stereo set.
Optionally, the audio acquisition module includes a band-pass filter, the band-pass filter is configured to perform filtering processing on the playing data, and the preprocessing includes filtering, framing and windowing processing.
Optionally, the audio analysis module performs fast fourier transform on the preprocessed playing data to obtain frequency spectrums of each frame in the playing data, and performs a modular square operation on the frequency spectrums of each frame to obtain a power spectrum of the playing data.
Optionally, the audio analysis module sets a label based on the power spectrogram, constructs an audio recognition model based on a convolutional neural network, inputs the power spectrogram into the audio recognition model for training, acquires a recognition result based on the trained audio recognition model, judges a noise part in playing data based on the recognition result, and judges a component part in the sound which causes noise to appear based on the set label and the recognition result.
Optionally, the audio acquisition module further includes a data storage unit, and the data storage unit is configured to store the playing data identified by the audio analysis module and the voice quality identification result.
Optionally, the audio analysis module calculates an error between the recognition result and the tag based on the set tag; loss is reduced based on a random gradient descent method, and parameter updating is carried out by using back propagation to complete the back learning of one iteration; obtaining a set of optimal parameter sets for the audio recognition model after model convergence; and inputting the power spectrogram into the audio recognition model again, recognizing the noise category in the playing data to obtain a highest probability category, and outputting the highest probability category as a noise recognition result.
Optionally, the fault prompting module includes a fault prompting lamp set and a fault alarm;
the fault prompting lamp group comprises three prompting lamps with different colors, and is used for controlling the prompting lamps with different colors to be turned on according to the external identification result, the circuit identification result and the tone quality identification result;
and when the three prompt lamps with different colors are simultaneously lightened, the fault alarm gives out sound alarm prompt.
The invention has the technical effects that:
the invention can realize the omnibearing detection of external damage, circuit fault and unclear tone quality of the sound, extracts and identifies the damaged part of the sound through the color characteristic of the external detection module, detects the circuit fault in the sound through the universal meter resistor in the fault detection module, constructs the convolutional neural network through the audio analysis module to identify the tone quality of the sound, and optimizes the model to improve the accuracy of tone quality identification.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application. In the drawings:
fig. 1 is a schematic structural diagram of a sound inspection management system in an embodiment of the present invention.
Detailed Description
It should be noted that, in the present application, the embodiments and features of the embodiments may be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than here.
Example one
As shown in fig. 1, the present embodiment provides a sound inspection management system, which includes an external detection module, a fault detection module, an audio acquisition module, an audio analysis module, and a fault prompt module, which are connected in sequence;
when there is the stereo set that needs to carry out the inspection, whether at first detect the external structure of stereo set and damage, be provided with a high definition digtal camera in the detection module of externally, carry out the shooting of outside picture through high definition digtal camera to the shell of stereo set, then the outside detection module carries out binary processing according to the outside picture of stereo set, because damaged position will be obvious relatively in comparison in the colour characteristic of other positions, consequently damaged position can be observed through the stereo set outward appearance image of binary, the obvious position of colour characteristic in the outside image is drawed to the detection module of externally this moment, can judge the externally damaged position of stereo set, generate outside identification result and transmit to trouble suggestion module.
After the external damage of the sound equipment is detected, whether the sound equipment can normally play sound or not can be detected through the fault detection module, whether the internal circuit has a fault or not is detected, the fault detection module is internally provided with a universal meter, and when the sound equipment cannot play audio due to the fault, the fault detection module detects the resistance between a positive power line and a negative power line of the sound equipment and the resistance of each local circuit through the resistance block of the universal meter so as to judge whether the sound chip circuit has a short circuit phenomenon or not; and forward and reverse resistance, a capacitor, a diode, a triode, a potentiometer, on-off of a switch contact and on-off of a transformer of each pin of the sound chip integrated circuit are measured through a universal meter so as to identify fault positions of each component of the sound, and a circuit identification result is generated and transmitted to a fault prompt module.
There are not circuit short circuit and components and parts trouble when the stereo set, when can broadcast the audio frequency, can detect the tone quality of stereo set, when the unclear trouble of tone quality appears, need carry out the analysis to audio data, and audio acquisition module is through to stereo set input audio data, gathering the broadcast data of stereo set. After the playing data are obtained, the audio acquisition module firstly carries out filtering processing on the playing data through a built-in band-pass filter to eliminate a noise part in the playing data, then carries out framing and windowing on the filtered playing data so as to be convenient for the audio analysis module to analyze, and finally transmits the processed playing data to the audio analysis module.
Since the characteristics of the sound signal are usually difficult to distinguish by transforming the sound signal in the time domain, the sound signal is usually transformed into energy distribution in the frequency domain to be observed, and different energy distributions represent the characteristics of different voices. Therefore, after the preprocessed playing data is obtained, the audio analysis module performs fast Fourier transform on the framed and windowed playing data to obtain the frequency spectrum of each frame in the playing data, performs modular squaring on the frequency spectrum of the playing book to obtain the power spectrogram of the playing data, and can convert the playing data in the form of the sound signal into the form of the energy distribution image.
After the power spectrogram of the playing data is obtained, the audio analysis module builds an audio recognition model based on a convolutional neural network, performs tone quality detection on the playing data, inputs the power spectrogram of the playing data into the audio recognition model for training, and can recognize the noise part in the playing data and the component part in the sound equipment, which causes the noise, through the trained audio recognition model.
The convolutional neural network constructed by the audio analysis module comprises 5 convolutional layers and 3 full-connection layers, when an input signal is a power spectrogram of 227 × 227 × 3 in the present embodiment, the audio analysis module sets a label for a normal sound quality in the power spectrogram to be 1 and sets a label for a noise to be 0, firstly, in a convolutional layer of a first layer, 96 convolutional filters with the size of 11 × 11 and the step length of 4 are used to reduce the size of the input signal of the power spectrogram to 55 × 55, and then a maximum pooling layer is constructed by using one convolution filter of 3 × 3 to reduce the size of the convolutional layer to 27 × 27 × 96. Then a 5 × 5 convolution is performed at layer 2, and after padding, the size of the output result is 27 × 27 × 256; then maximum pooling is performed. The same convolution as the previous step is performed again in layer 3, the same padding, and the size of the result obtained is 13 × 13 × 384; then, the same convolution is performed for 2 times at 3 × 3 in the 4 th and 5 th layers, and finally, the maximum pooling is performed again, and the size of the result is reduced to 6 × 6 × 256. And inputting the result into a full-connection layer, finally generating a noise prediction type result for the input power spectrogram, and acquiring a component part corresponding to the noise according to the noise type result.
After the initial identification, the audio analysis module calculates the error between the identification result and the actual class label according to the set label, and completes the forward reasoning operation in one iteration. Next, a random gradient descent method is used to continuously reduce the loss, and the parameters are updated by using back propagation, so that an iterative reverse learning is completed. And after the model is converged, obtaining a group of optimal parameter sets of the network to finish the training process of the model. After the model is trained, the power spectrogram of the playing data is input into the audio recognition model again, and the category of the noise in the power spectrogram is recognized by using the stored model. At this stage, only forward propagation is performed, and the class with the highest probability is the final voice quality recognition result of the audio recognition model, and the voice quality recognition result is transmitted to the fault prompting module.
The audio analysis module in the system also comprises a data storage unit, the data storage unit can store the noise category data acquired by the analysis module after each sound quality detection, the corresponding component part data and the playing data acquired by the audio acquisition module, and has a data query function, so that managers can download historical data in real time, and judge the quality of the sound according to the noise parts and the component failure times in the data.
Finally, the trouble suggestion module includes trouble suggestion banks and a fault alarm, and wherein trouble suggestion banks includes the warning light of three different colours, and every warning light corresponds different trouble respectively, and the colour of warning light can set up according to actual demand, sets up red, yellow, blue respectively in this embodiment. For example: when an external fault occurs in an external identification result, the fault prompting module controls the red prompting lamp to light up, when a circuit fault occurs, the yellow prompting lamp lights up, and when a tone quality fault occurs, the blue prompting lamp lights up. When three warning light lights simultaneously (discerning external fault, circuit fault, tone quality simultaneously and not being clear the trouble), then explain the fault degree of this stereo set darker, trouble suggestion module control fault alarm ware carries out the warning of sound form this moment, and the suggestion staff maintains at once.
This system can realize carrying out outside damage to the stereo set, the circuit fault, the unclear all-round detection of tone quality, the damaged position of discernment stereo set is drawed to the colour characteristic through outside detection module, circuit fault in the universal meter resistance detection stereo set through the fault detection module, it discerns to the tone quality of stereo set to construct convolution neural network through the audio analysis module, and optimize the model, with the precision that improves tone quality discernment, carry out the early warning suggestion according to the recognition result of difference at last, the staff of being convenient for in time maintains, troubleshooting.
The above description is only for the preferred embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (9)

1. A sound inspection management system is characterized by comprising an external detection module, a fault detection module, an audio acquisition module, an audio analysis module and a fault prompt module;
the external detection module is used for identifying external damage of the sound equipment, acquiring an external identification result and transmitting the external identification result to the fault prompt module;
the fault detection module is used for identifying circuit faults and component faults of the sound equipment, acquiring circuit identification results and transmitting the circuit identification results to the fault prompt module;
the audio acquisition module is used for acquiring playing data of the sound equipment, preprocessing the playing data and transmitting the preprocessed playing data to the audio analysis module;
the audio analysis module is used for analyzing the audio data, identifying a noise part in the playing data and a component part in the sound which causes the noise to appear, acquiring a tone quality identification result, and transmitting the tone quality identification result to the fault prompt module;
the fault prompting module is used for receiving the external identification result, the circuit identification result and the tone quality identification result and carrying out early warning based on different identification results.
2. The sound inspection management system according to claim 1, wherein the external detection module comprises a high-definition camera device for acquiring an external image of the sound; the external detection module identifies an external damaged part of the sound equipment by performing binarization processing on the external image.
3. The sound inspection management system according to claim 1, wherein the fault detection module comprises a multimeter, and the multimeter is used for judging whether a chip circuit of the sound has a short circuit phenomenon or not and identifying whether components and parts of the sound have faults or not.
4. The sound inspection management system of claim 1, wherein the audio acquisition module comprises a band-pass filter, the band-pass filter is configured to filter the playback data, and the pre-processing comprises filtering, framing, and windowing.
5. The sound inspection management system according to claim 1, wherein the audio analysis module performs fast fourier transform on the preprocessed playing data to obtain frequency spectrums of each frame in the playing data, and performs modulo square on the frequency spectrums of each frame to obtain power spectrums of the playing data.
6. The sound inspection management system according to claim 5, wherein the audio analysis module sets a label based on the power spectrogram, constructs an audio recognition model based on a convolutional neural network, inputs the power spectrogram into the audio recognition model for training, obtains a recognition result based on the trained audio recognition model, determines a noise part in the playing data based on the recognition result, and determines a component part in the sound which causes noise to appear based on the set label and the recognition result.
7. The sound inspection management system of claim 1, wherein the audio acquisition module further comprises a data storage unit, and the data storage unit is configured to store the playing data identified by the audio analysis module and the voice quality identification result.
8. The sound inspection management system according to claim 6, wherein the audio analysis module calculates an error between the recognition result and the tag based on the set tag; loss is reduced based on a random gradient descent method, and parameter updating is carried out by using back propagation to complete the back learning of one iteration; obtaining a set of optimal parameter sets for the audio recognition model after model convergence; and inputting the power spectrogram into the audio recognition model again, recognizing the category of the noise in the playing data to obtain the category of the highest probability, and outputting the category of the highest probability as the noise recognition result.
9. The sound inspection management system of claim 1, wherein the fault notification module comprises a fault notification lamp set and a fault alarm;
the fault prompting lamp group comprises three prompting lamps with different colors, and is used for controlling the prompting lamps with different colors to be turned on according to the external identification result, the circuit identification result and the tone quality identification result;
when the three prompt lamps with different colors are simultaneously lightened, the fault alarm carries out sound alarm prompt.
CN202211080169.3A 2022-09-05 2022-09-05 Stereo set inspection management system Withdrawn CN115460530A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211080169.3A CN115460530A (en) 2022-09-05 2022-09-05 Stereo set inspection management system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211080169.3A CN115460530A (en) 2022-09-05 2022-09-05 Stereo set inspection management system

Publications (1)

Publication Number Publication Date
CN115460530A true CN115460530A (en) 2022-12-09

Family

ID=84302302

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211080169.3A Withdrawn CN115460530A (en) 2022-09-05 2022-09-05 Stereo set inspection management system

Country Status (1)

Country Link
CN (1) CN115460530A (en)

Similar Documents

Publication Publication Date Title
CN103456301B (en) A kind of scene recognition method and device and mobile terminal based on ambient sound
WO2018068396A1 (en) Voice quality evaluation method and apparatus
CN107808659A (en) Intelligent sound signal type recognition system device
CN112232476A (en) Method and device for updating test sample set
CN108511000A (en) A kind of test intelligent sound box wakes up the method and system of word discrimination
CN109271533A (en) A kind of multimedia document retrieval method
CN107958668A (en) The acoustic control of smart television selects broadcasting method, acoustic control to select broadcast system
CN110265012A (en) It can interactive intelligence voice home control device and control method based on open source hardware
CN110148418B (en) Scene record analysis system, method and device
CN110827793A (en) Language identification method
CN110278415A (en) A kind of web camera video quality improvements method
CN109474877A (en) The method of the defects of hearing device for identification
Mezza et al. Unsupervised domain adaptation for acoustic scene classification using band-wise statistics matching
CN115460530A (en) Stereo set inspection management system
CN115457980A (en) Automatic voice quality evaluation method and system without reference voice
CN109165574A (en) video detecting method and device
CN111933186B (en) Method, device and system for fault identification of on-load tap-changer
CN107197404B (en) Automatic sound effect adjusting method and device and recording and broadcasting system
CN113409781B (en) 5G intelligent rod
CN111370031A (en) Voice separation method, system, mobile terminal and storage medium
CN111951809A (en) Multi-person voiceprint identification method and system
CN114157023B (en) Distribution transformer early warning information acquisition method
CN116052041A (en) Indicating lamp state identification method based on depth network
KR102428885B1 (en) Apparatus and Method for Monitoring Optical Fiber
WO2022000141A1 (en) Epidemic investigation method employing robotic process automation (rpa), and device

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
WW01 Invention patent application withdrawn after publication
WW01 Invention patent application withdrawn after publication

Application publication date: 20221209