CN110364180A - A kind of examination system and method based on audio-video processing - Google Patents
A kind of examination system and method based on audio-video processing Download PDFInfo
- Publication number
- CN110364180A CN110364180A CN201910489030.6A CN201910489030A CN110364180A CN 110364180 A CN110364180 A CN 110364180A CN 201910489030 A CN201910489030 A CN 201910489030A CN 110364180 A CN110364180 A CN 110364180A
- Authority
- CN
- China
- Prior art keywords
- audio
- data
- module
- user
- frequency
- 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.)
- Granted
Links
- 238000012545 processing Methods 0.000 title claims abstract description 73
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000004891 communication Methods 0.000 claims abstract description 6
- 238000012937 correction Methods 0.000 claims abstract description 4
- 238000003860 storage Methods 0.000 claims description 11
- 230000003321 amplification Effects 0.000 claims description 10
- 230000007613 environmental effect Effects 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 10
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 8
- 239000000284 extract Substances 0.000 claims description 7
- 238000012550 audit Methods 0.000 claims description 6
- 238000012790 confirmation Methods 0.000 claims description 3
- 239000000463 material Substances 0.000 claims description 3
- 230000008520 organization Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000008030 elimination Effects 0.000 claims description 2
- 238000003379 elimination reaction Methods 0.000 claims description 2
- 230000006399 behavior Effects 0.000 claims 1
- 238000011157 data evaluation Methods 0.000 claims 1
- 230000006870 function Effects 0.000 abstract description 9
- 238000011156 evaluation Methods 0.000 abstract description 6
- 238000012795 verification Methods 0.000 abstract description 2
- 241000208340 Araliaceae Species 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- 235000014676 Phragmites communis Nutrition 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- GOLXNESZZPUPJE-UHFFFAOYSA-N spiromesifen Chemical compound CC1=CC(C)=CC(C)=C1C(C(O1)=O)=C(OC(=O)CC(C)(C)C)C11CCCC1 GOLXNESZZPUPJE-UHFFFAOYSA-N 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/70—Multimodal biometrics, e.g. combining information from different biometric modalities
-
- 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
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
-
- 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
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/06—Protocols specially adapted for file transfer, e.g. file transfer protocol [FTP]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- General Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Strategic Management (AREA)
- Computational Linguistics (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Electrically Operated Instructional Devices (AREA)
- Electrophonic Musical Instruments (AREA)
Abstract
The present invention relates to a kind of examination systems based on audio-video processing and method, the system to specifically include: user terminal, server and judging panel's terminal；The user terminal further comprises data input module, acquisition module, processing module, memory module, display module, communication module.The musical instrument examination system is able to use family and participates in musical instrument whenever and wherever possible by terminal and examine for the levels, and is not limited by time and region, flexibility with higher.The system has user identity identification function, can effectively ensure that the validity of examination, avoids cheating.The system has audition function, and user can be assisted to carry out the accuracy in pitch correction of musical instrument, avoided because of the case where musical instrument intonation problems influence examinee's achievement generation.The system has automatic evaluation function, can upload data according to user and calculate the score of the examination automatically, while judging panel's terminal is arranged and carries out secondary verification to the score of the examination provided is calculated automatically, to ensure that the accuracy of achievement.
Description
Technical field
The present invention relates to audio-videos to identify field, and in particular to a kind of examination system and method based on audio-video processing.
Background technique
With the reform of state education system, teenagers' education more focuses on the development in terms of style.More and more families
Long selection allows child's learning instrument.Musical instrument refers to the implements that tone color, musical note can be played out with various methods.It is generally divided into nationality
Musical instrument and western musical instrument.National musical instruments include Chinese zither, Chinese lute, urheen etc., and western musical instrument includes piano, violin, clarinet, double
Reed pipe etc..
It is directed to various musical instruments at present, domestic and international various examining bodies are all provided with system of examining for the levels accordingly, for embodying pleasure
The ability grade of device learner.Existing various examining bodies organize regularly musical instrument to take an examination every year, and e.g., Chinese Musicians Association is every
Winter vacation in year and stage in summer vacation can organize to take an examination twice respectively, be drilled at the appointed time by scene after the personnel's registration taken an examination
The mode played takes an exam.Existing examination mode is all very high to time and regional requirement, as examinee at the appointed time fails
It takes an examination, not can be carried out make-up examination, missing device for examining can only can take an examination again when unified examination next time, waiting time mistake
It is long, many inconvenience are brought to examinee.
In view of the above technical problems, it is badly in need of a kind of examination system for being capable of providing convenient service and method, so that candidate
It can not be limited by test time and region, can be taken an examination whenever and wherever possible.
Summary of the invention
In order to overcome above-mentioned the deficiencies in the prior art, the present invention provides a kind of examinations based on audio-video processing
System and method, the examination system can allow candidate that can take an examination whenever and wherever possible, and the system has higher safety
Property.
To achieve the above object, the invention provides the following technical scheme:
A kind of examination system based on audio-video processing, including user terminal, server and judging panel's terminal；
The user terminal further comprises data input module, acquisition module, processing module, memory module, display mould
Block, communication module；
The data input module further comprises user basic information recording module and exam information recording module, uses
In the basic letter for obtaining user
Breath and exam information；
The acquisition module further comprises finger print acquisition module, audio collection module, image capture module；
The processing module, further comprises identification module, audio rectification module, audio processing modules, at image
Manage module；
The memory module, for storing finger print data, image and the voice data of acquisition；
The display module, for showing examination relevant information；
The communication module realizes the upload and downloading of data for being communicated with server；
Fingerprint, image and the voice data of the server stores user, the basic pitch data of various musical instruments, for each
The standard audio data of each rank of kind musical instrument；
Judging panel's terminal is used to obtain the audio, video data that user uploads from server, carries out to audio, video data secondary
Audit evaluation, will most terminate
Fruit feeds back to user terminal.
The identification module further comprises fingerprint identification module, picture recognition module and speech recognition module, uses
Fingerprint, image and voice information in identification user carry out authentication identification to login user；The fingerprint identification module,
Picture recognition module and speech recognition module
The finger print acquisition module that will be stored in storage unit respectively, audio collection module, the number of image capture module acquisition
According to store in server
Fingerprint, image and the voice data of user is compared, and comparison result A1, A2, A3 is obtained respectively, according to setting in advance
Weighted value k1, k2, k3 shared by fingerprint, image and the voice data set, determine final matching results M, M=k1*A1+k2*A2+
K3*A3, if final matching
As a result it is greater than preset threshold M0, then confirms that the user is examinee, it is allowed to carry out next step operation, otherwise,
The notice of authentification failure is issued by display module, is reminded user to authenticate again, is forbidden the user after authentification failure three times
It takes an exam.
The audio rectification module, musical instrument for using user carry out the confirmation of pitch, and with it is pre- in memory module
The basic pitch first stored is compared, and comparison result is fed back to user by display module；Before examination starts, pass through
Display module prompts user to carry out audition, and user inputs corresponding key or string according to the note input sequence that display module prompts
Sound, the note input duration of each key or string is at least 2 seconds；The audio rectification module will pass through audio collection mould
The audition data that block obtains are compared with basis pre-stored in server pitch data, when the pitch of musical instrument is in error model
When enclosing interior, by display module to the normal information alert of user feedback musical instrument, user can normally be taken an examination, when the sound of musical instrument
When height is more than preset error range, by display module to the information alert of user feedback musical instrument pitch exception, and provide every
A key or the higher or relatively low specifying information of string tone.
Basic pitch data pre-stored in the audition data obtained by audio collection module and server are carried out
The process of comparison is specific as follows: step 1) carries out signal amplification and filtering processing to audition data, eliminates environmental noise；
Step 2) carries out discrete Fu's formula to the audition data after denoising and converts, and extracts audition data frequency；
Audition data frequency is compared by step 3) with the base frequency of corresponding musical instrument pre-stored in server, when
When the error of audition data frequency and base frequency is less than or equal to 0.3Hz, indicate that musical instrument accuracy in pitch is normal, when audition data frequency is big
It when base frequency 0.3Hz, prompts musical instrument tone higher, when base frequency is greater than audition data frequency 0.3Hz, prompts musical instrument
Tone is relatively low.
The audio processing modules, for handling the audio data that audio collection module acquires in real time；The sound
The treatment process of frequency evidence the following steps are included:
Step 1) carries out signal amplification and filtering processing to the audio data acquired in real time, eliminates environmental noise；
Step 2) carries out editing to the audio data after denoising, removes audio data unrelated with performance end to end, will be remaining
Audio data determines the total duration of audio data to be compared as audio data to be compared；
The audio data to be compared is divided into n sub-piece by step 3), for the n sub-piece carry out adding window and
Audio characteristic data is extracted after overlap processing respectively, the audio characteristic data includes frequency and amplitude；
Step 4) obtains the standard audio data of pre-stored corresponding musical instrument, corresponding level, corresponding song from server,
Processing is zoomed in and out to standard audio data according to the total duration of audio data to be compared；By the audio data ginseng after scaling processing
It is equally divided into n sub-piece according to step 3), is based on different songs, determines the frequency and amplitude weighted value of n sub-piece, for
The n sub-piece extracts audio characteristic data after carrying out adding window and overlap processing respectively, and the audio characteristic data includes frequency
Rate and amplitude；
Step 5) is special by the audio of the audio frequency characteristics of audio data to be compared and standard audio data based on the weighted value
Sign is compared, and obtains the similarity value of the two, determines total marks of the examination based on similarity value.
The determination method of similarity value in the step 5) is as follows:Wherein,
Fi, FiAnd Wi, Wi' be respectively audio data and standard audio data to be compared frequency and amplitude, αi, βiIt is weighed for frequency and amplitude
Weight values.
Described image processing module, for handling the image data that image capture module acquires in real time；The figure
As data processing include background eliminate and face characteristic identification, the human face data after identification is sent to identification module.
A kind of method of examination based on audio-video processing, specifically includes the following steps:
1) user acquires fingerprint, image and voice data to designated place before examination, identity when for subsequent examination
Certification；
2) by user terminal typing user basic information and exam information, user basic information includes age of user, property
Not, nationality, identification card number, date of birth, contact method, affiliated area, certificate address；Exam information includes musical instrument class
Type, examination rank, teaching material used, selected song, instructor, training organization；
3) by the finger print acquisition module of user terminal, image capture module, audio collection module acquires user's respectively
Fingerprint, image and voice data, by the fingerprint identification module of user terminal, picture recognition module and speech recognition module to stepping on
It employs family and carries out authentication identification；The fingerprint identification module, picture recognition module and speech recognition module respectively will storages
The finger print acquisition module that stores in unit, audio collection module store in the data and server of image capture module acquisition
Fingerprint, image and the voice data of user is compared, and comparison result A1, A2, A3 is obtained respectively, according to pre-set finger
Weighted value k1, k2, k3 shared by line, image and voice data determine final matching results M, M=k1*A1+k2*A2+k3*A3, such as
Fruit final matching results are greater than preset threshold M0, then confirm that the user is examinee, allow it to carry out next step operation, enter
Step 4) otherwise issues the notice of authentification failure by display module, reminds user to authenticate again, three times authentification failure
After forbid the user to take an exam；
4) user is prompted to carry out audition by display module, user inputs according to the note input sequence that display module prompts
The note input duration of the sound of corresponding key or string, each key or string is at least 2 seconds, will by audio rectification module
The audition data obtained by audio collection module are compared with basis pre-stored in server pitch data, work as musical instrument
Pitch in error range when, by display module to the normal information alert of user feedback musical instrument, user can be carried out normally
5) examination enters step, when the pitch of musical instrument is more than preset error range, by display module to user feedback musical instrument sound
High abnormal information alert, and provide each key or the higher or relatively low specifying information of string tone, user are carrying out audio
The step is repeated after correction；
5) the performance audio for acquiring user in real time by audio collection module, by audio processing modules, to audio collection
The audio data that module acquires in real time is handled, and determines total marks of the examination；
6) judging panel's terminal is used to obtain the audio, video data that user uploads and the total marks of the examination automatically generated from server, right
Audio, video data carries out secondary audit evaluation, and final result is fed back to user terminal.
Wherein in step 4) by pre-stored base in the audition data obtained by audio collection module and server
Plinth pitch data are compared that specific step is as follows:
Step 1) carries out signal amplification and filtering processing to audition data, eliminates environmental noise；
Step 2) carries out discrete Fu's formula to the audition data after denoising and converts, and extracts audition data frequency；
Audition data frequency is compared by step 3) with the base frequency of corresponding musical instrument pre-stored in server, when
When the error of audition data frequency and base frequency is less than or equal to 0.3Hz, indicate that musical instrument accuracy in pitch is normal, when audition data frequency is big
It when base frequency 0.3Hz, prompts musical instrument tone higher, when base frequency is greater than audition data frequency 0.3Hz, prompts musical instrument
Tone is relatively low.
The treatment process of the audio data the following steps are included:
Step 1) carries out signal amplification and filtering processing to the audio data acquired in real time, eliminates environmental noise；
Step 2) carries out editing to the audio data after denoising, removes audio data unrelated with performance end to end, will be remaining
Audio data determines the total duration of audio data to be compared as audio data to be compared；
The audio data to be compared is divided into n sub-piece by step 3), for the n sub-piece carry out adding window and
Audio characteristic data is extracted after overlap processing respectively, the audio characteristic data includes frequency and amplitude；
Step 4) obtains the standard audio data of pre-stored corresponding musical instrument, corresponding level, corresponding song from server,
Processing is zoomed in and out to standard audio data according to the total duration of audio data to be compared；By the audio data ginseng after scaling processing
It is equally divided into n sub-piece according to step 3), is based on different songs, determines the frequency and amplitude weighted value of n sub-piece, for
The n sub-piece extracts audio characteristic data after carrying out adding window and overlap processing respectively, and the audio characteristic data includes frequency
Rate and amplitude；
Step 5) is special by the audio of the audio frequency characteristics of audio data to be compared and standard audio data based on the weighted value
Sign is compared, and obtains the similarity value of the two, determines total marks of the examination based on similarity value；
The determination method of similarity value in the step 5) is as follows:Wherein,
Fi, FiAnd Wi, Wi' be respectively audio data and standard audio data to be compared frequency and amplitude, αi, βiIt is weighed for frequency and amplitude
Weight values.
Compared with prior art, the beneficial effects of the present invention are:
The musical instrument examination system is able to use family and participates in musical instrument whenever and wherever possible by terminal and examine for the levels, not by time and region
Limitation, flexibility with higher, meanwhile, which, directly facing examiner, avoids examinee outer because of environment etc. without examinee
Boundary's pressure causes to play not normal, can preferably embody the true horizon of examinee.
The system has user identity identification function, can effectively ensure that the validity of examination, avoids cheating.
The system has audition function, and user can be assisted to carry out the accuracy in pitch correction of musical instrument, avoided because of musical instrument intonation problems
The case where influencing examinee's achievement, occurs.
The system has automatic evaluation function, can upload data according to user and calculate the score of the examination automatically, and in order to
Guarantee the accuracy of examination result, setting judging panel's terminal carries out secondary verification to the score of the examination provided is calculated automatically, to protect
The accuracy of achievement is demonstrate,proved.
Detailed description of the invention
A kind of examination system structure chart based on audio-video processing of Fig. 1 embodiment of the present invention；
The user terminal structure figure of Fig. 2 embodiment of the present invention；
A kind of method of examination flow chart based on audio-video processing of Fig. 3 embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
A kind of examination system based on audio-video processing, including user terminal, server and judging panel's terminal；
The user terminal further comprises data input module, acquisition module, processing module, memory module, display mould
Block, communication module；
The data input module further comprises user basic information recording module and exam information recording module, uses
In the essential information and exam information that obtain user；
User basic information includes age of user, gender, nationality, identification card number, date of birth, contact method, institute possession
Area, certificate address etc.；
Exam information includes instrument type, examination rank, teaching material used, selected song, instructor, training organization etc.；
The acquisition module further comprises finger print acquisition module, audio collection module, image capture module；
The finger print acquisition module is stored for acquiring user fingerprints, and by the data of acquisition to memory module；
The audio collection module is stored for acquiring the audio data of user in real time, and by the data of acquisition to storage
Module；
Described image acquisition module is stored for acquiring the image data of user in real time, and by the data of acquisition to storage
Module；
The processing module, further comprises identification module, audio rectification module, audio processing modules, at image
Manage module；
The identification module further comprises fingerprint identification module, picture recognition module and speech recognition module, uses
Fingerprint, image and voice information in identification user carry out authentication identification to login user；
The fingerprint that the fingerprint identification module, picture recognition module and speech recognition module will store in storage unit respectively
Acquisition module, audio collection module, the fingerprint of user stored in the data and server of image capture module acquisition, image and
Voice data is compared, and comparison result A1, A2, A3 is obtained respectively, according to pre-set fingerprint, image and voice data institute
Weighted value k1, k2, k3 are accounted for, determines final matching results M, M=k1*A1+k2*A2+k3*A3, if final matching results are greater than
Preset threshold M0 then confirms that the user is examinee, allows it to carry out next step operation and is otherwise issued by display module
The notice of authentification failure reminds user to authenticate again, forbids the user to take an exam after authentification failure three times.
The audio rectification module, musical instrument for using user carry out the confirmation of pitch, and with it is pre- in memory module
The basic pitch first stored is compared, and comparison result is fed back to user by display module；
Before examination starts, user is prompted to carry out audition, the note that user prompts according to display module by display module
The note input duration of the sound of the corresponding key of input sequence input or string, each key or string is at least 2 seconds.
The audio rectification module, by the audition data obtained by audio collection module with it is pre-stored in server
Basic pitch data are compared, when the pitch of musical instrument in error range when, by display module to user feedback musical instrument just
Normal information alert, user can normally be taken an examination, and when the pitch of musical instrument is more than preset error range, pass through display module
To the information alert of user feedback musical instrument pitch exception, and provide each key or the higher or relatively low specific letter of string tone
Breath.
Basic pitch data pre-stored in the audition data obtained by audio collection module and server are carried out
The process of comparison is specific as follows:
1) signal amplification and filtering processing are carried out to audition data, eliminates environmental noise；
2) discrete Fu's formula is carried out to the audition data after denoising to convert, extract audition data frequency；
3) audition data frequency is compared with the base frequency of corresponding musical instrument pre-stored in server, works as audition
When the error of data frequency and base frequency is less than or equal to 0.3Hz, indicate that musical instrument accuracy in pitch is normal, when audition data frequency is greater than base
It when plinth frequency 0.3Hz, prompts musical instrument tone higher, when base frequency is greater than audition data frequency 0.3Hz, prompts musical instrument tone
It is relatively low.
The audio processing modules, for handling the audio data that audio collection module acquires in real time；
The treatment process of the audio data the following steps are included:
1) signal amplification and filtering processing are carried out to the audio data acquired in real time, eliminates environmental noise；
2) editing is carried out to the audio data after denoising, removes audio data unrelated with performance end to end, by remaining audio
Data determine the total duration of audio data to be compared as audio data to be compared；
3) audio data to be compared is divided into n sub-piece, carries out adding window and overlapping for the n sub-piece
Audio characteristic data is extracted after processing respectively, the audio characteristic data includes frequency and amplitude；
4) standard audio data that pre-stored corresponding musical instrument, corresponding level, corresponding song are obtained from server, according to
The total duration of audio data to be compared zooms in and out processing to standard audio data；By the audio data after scaling processing referring to step
It is rapid 3) to be equally divided into n sub-piece, different songs are based on, the frequency and amplitude weighted value of n sub-piece are determined, for described
N sub-piece carries out extracting audio characteristic data after adding window and overlap processing respectively, the audio characteristic data include frequency and
Amplitude；
5) based on the weighted value by the audio frequency characteristics of the audio frequency characteristics of audio data to be compared and standard audio data into
Row compares, and obtains the similarity value of the two, determines total marks of the examination according to similarity value.
The determination method of similarity value in the step 5) is as follows:Wherein,
Fi, FiAnd Wi, Wi' be respectively audio data and standard audio data to be compared frequency and amplitude, αi, βiIt is weighed for frequency and amplitude
Weight values.
Described image processing module, for handling the image data that image capture module acquires in real time；
Described image data processing includes background elimination and face characteristic identification, and the human face data after identification is sent to body
Part identification module；
The memory module, for storing finger print data, image and the voice data of acquisition；
The display module, for showing examination relevant information；
The communication module realizes the upload and downloading of data for being communicated with server；
Realize that treated that image data uploads by audio processing modules treated audio data and image processing module
To server；
Realize fingerprint, image and the voice data that user is downloaded from server, the basic pitch data of various musical instruments, needle
To the standard audio data of each rank of each kind musical instrument；
Fingerprint, image and the voice data of the server stores user, the basic pitch data of various musical instruments, for each
The standard audio data of each rank of kind musical instrument；
User needs the pre- designated place that arrives first to acquire fingerprint, image and voice data before examination, when for subsequent examination
Authentication, the acquisition time is random, need to only complete before examination, examinee is facilitated to acquire at any time.
Judging panel's terminal is used to obtain the audio, video data that user uploads and the total marks of the examination automatically generated from server,
Secondary audit evaluation is carried out to audio, video data, final result is fed back into user terminal.In order to avoid system calculates automatically
There are systematic errors for the score of the examination, and the accurate and effective of achievement can be guaranteed by carrying out secondary audit evaluation by expert.
Professional should further appreciate that, described in conjunction with the examples disclosed in the embodiments of the present disclosure
Unit and algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, hard in order to clearly demonstrate
The interchangeability of part and software generally describes each exemplary composition and step according to function in the above description.
These functions are implemented in hardware or software actually, the specific application and design constraint depending on technical solution.
Professional technician can use different methods to achieve the described function each specific application, but this realization
It should not be considered as beyond the scope of the present invention.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can be executed with hardware, processor
The combination of software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only memory
(ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technical field
In any other form of storage medium well known to interior.
Above-described specific embodiment has carried out further the purpose of the present invention, technical scheme and beneficial effects
It is described in detail, it should be understood that being not intended to limit the present invention the foregoing is merely a specific embodiment of the invention
Protection scope, all any modification, equivalent substitution, improvement and etc. within the scope of the present invention, done should be included in this hair
Within bright protection scope.
Claims (10)
1. a kind of examination system based on audio-video processing, including user terminal, server and judging panel's terminal；
The user terminal further comprises data input module, acquisition module, processing module, memory module, display module, is led to
Believe module；
The data input module, further comprises user basic information recording module and exam information recording module, for obtaining
Take the essential information and exam information at family；
The acquisition module further comprises finger print acquisition module, audio collection module, image capture module；
The processing module further comprises identification module, audio rectification module, audio processing modules, image procossing mould
Block；
The memory module, for storing finger print data, image and the voice data of acquisition；
The display module, for showing examination relevant information；
The communication module realizes the upload and downloading of data for being communicated with server；
Fingerprint, image and the voice data of the server stores user, the basic pitch data of various musical instruments, for all kinds of pleasures
The standard audio data of each rank of device；
Judging panel's terminal is used to obtain the audio, video data that user uploads from server, carries out secondary audit to audio, video data
Evaluation, feeds back to user terminal for final result.
2. a kind of examination system based on audio-video processing according to claim 1, the identification module, further
Including fingerprint identification module, picture recognition module and speech recognition module, the fingerprint, image and voice of user is believed for identification
Breath carries out authentication identification to login user；The fingerprint identification module, picture recognition module and speech recognition module difference
The finger print acquisition module that will be stored in storage unit, audio collection module, image capture module acquisition data and server in
Fingerprint, image and the voice data of the user of storage is compared, and comparison result A1, A2, A3 is obtained respectively, according to presetting
Fingerprint, weighted value k1, k2, k3 shared by image and voice data, determine final matching results M, M=k1*A1+k2*A2+k3*
A3 confirms that the user is examinee, it is allowed to carry out next step behaviour if final matching results are greater than preset threshold M0
Make, otherwise, the notice of authentification failure is issued by display module, remind user to authenticate again, prohibit after authentification failure three times
Only the user takes an exam.
3. it is according to claim 2 it is a kind of based on audio-video processing examination system, the audio rectification module, for pair
The musical instrument that user uses carries out the confirmation of pitch, and is compared with basis pre-stored in memory module pitch, and will compare
User is fed back to by display module to result；Before examination starts, user is prompted to carry out audition by display module, user presses
According to the corresponding key of note input sequence input of display module prompt or the sound of string, when the note of each key or string inputs
It is long to be at least 2 seconds；The audio rectification module deposits the audition data obtained by audio collection module with server in advance
The basic pitch data of storage are compared, when the pitch of musical instrument in error range when, it is happy to user feedback by display module
The normal information alert of device, user can normally be taken an examination, and when the pitch of musical instrument is more than preset error range, pass through display
Module and provides each key or higher or relatively low specific of string tone to the information alert of user feedback musical instrument pitch exception
Information.
4. a kind of examination system based on audio-video processing according to claim 3, will be obtained by audio collection module
Audition data and the pitch data process that is compared in basis pre-stored in server it is specific as follows:
Step 1) carries out signal amplification and filtering processing to audition data, eliminates environmental noise；
Step 2) carries out discrete Fu's formula to the audition data after denoising and converts, and extracts audition data frequency；
Audition data frequency is compared by step 3) with the base frequency of corresponding musical instrument pre-stored in server, works as audition
When the error of data frequency and base frequency is less than or equal to 0.3Hz, indicate that musical instrument accuracy in pitch is normal, when audition data frequency is greater than base
It when plinth frequency 0.3Hz, prompts musical instrument tone higher, when base frequency is greater than audition data frequency 0.3Hz, prompts musical instrument tone
It is relatively low.
5. it is according to claim 1 it is a kind of based on audio-video processing examination system, the audio processing modules, for pair
The audio data that audio collection module acquires in real time is handled；The treatment process of the audio data the following steps are included:
Step 1) carries out signal amplification and filtering processing to the audio data acquired in real time, eliminates environmental noise；
Step 2) carries out editing to the audio data after denoising, removes audio data unrelated with performance end to end, by remaining audio
Data determine the total duration of audio data to be compared as audio data to be compared；
The audio data to be compared is divided into n sub-piece by step 3), carries out adding window and overlapping for the n sub-piece
Audio characteristic data is extracted after processing respectively, the audio characteristic data includes frequency and amplitude；
Step 4) obtains the standard audio data of pre-stored corresponding musical instrument, corresponding level, corresponding song from server, according to
The total duration of audio data to be compared zooms in and out processing to standard audio data；By the audio data after scaling processing referring to step
It is rapid 3) to be equally divided into n sub-piece, different songs are based on, the frequency and amplitude weighted value of n sub-piece are determined, for described
N sub-piece carries out extracting audio characteristic data after adding window and overlap processing respectively, the audio characteristic data include frequency and
Amplitude；
Step 5) based on the weighted value by the audio frequency characteristics of the audio frequency characteristics of audio data to be compared and standard audio data into
Row compares, and obtains the similarity value of the two, determines total marks of the examination based on similarity value.
6. a kind of examination system based on audio-video processing according to claim 5, the similarity value in the step 5)
Determination method it is as follows:Wherein, Fi, Fi' and Wi, Wi' it is respectively audio number to be compared
According to the frequency and amplitude with standard audio data, αi, βiFor frequency and amplitude weighted value.
7. it is according to claim 2 it is a kind of based on audio-video processing examination system, described image processing module, for pair
The image data that image capture module acquires in real time is handled；Described image data processing includes background elimination and face characteristic
Identification, is sent to identification module for the human face data after identification.
8. a kind of method of examination based on audio-video processing, specifically includes the following steps:
1) user acquires fingerprint, image and voice data to designated place before examination, authentication when for subsequent examination；
2) by user terminal typing user basic information and exam information, user basic information includes age of user, gender, the people
Race, identification card number, date of birth, contact method, affiliated area, certificate address；Exam information includes instrument type, examination
Rank, teaching material used, selected song, instructor, training organization；
3) by the finger print acquisition module of user terminal, image capture module, audio collection module acquire respectively user fingerprint,
Image and voice data use login by the fingerprint identification module of user terminal, picture recognition module and speech recognition module
Family carries out authentication identification；The fingerprint identification module, picture recognition module and speech recognition module are respectively by storage unit
The finger print acquisition module of middle storage, audio collection module, the user that stores in the data and server of image capture module acquisition
Fingerprint, image and voice data be compared, respectively obtain comparison result A1, A2, A3, according to pre-set fingerprint, figure
Weighted value k1, k2, k3 shared by picture and voice data, determine final matching results M, M=k1*A1+k2*A2+k3*A3, if most
Whole matching result is greater than preset threshold M0, then confirms that the user is examinee, allow it to carry out next step operation, enter step
4) notice of authentification failure, otherwise, is issued by display module, is reminded user to authenticate again, is prohibited after authentification failure three times
Only the user takes an exam；
4) user is prompted to carry out audition by display module, the note input sequence input that user prompts according to display module corresponds to
The note input duration of the sound of key or string, each key or string is at least 2 seconds, by audio rectification module, will pass through
The audition data that audio collection module obtains are compared with basis pre-stored in server pitch data, when the sound of musical instrument
It is high in error range when, by display module to the normal information alert of user feedback musical instrument, user can normally be taken an examination,
It enters step 5), it is different to user feedback musical instrument pitch by display module when the pitch of musical instrument is more than preset error range
Normal information alert, and each key or the higher or relatively low specifying information of string tone are provided, user is carrying out audio correction
After repeat the step；
5) the performance audio for acquiring user in real time by audio collection module, by audio processing modules, to audio collection module
The audio data acquired in real time is handled, and determines total marks of the examination；
6) judging panel's terminal is used to obtain the audio, video data that user uploads and the total marks of the examination automatically generated from server, regards to sound
Frequency is evaluated according to secondary audit is carried out, and final result is fed back to user terminal.
9. a kind of method of examination based on audio-video processing according to claim 8, wherein will pass through sound in step 4)
The specific steps that the audition data that frequency acquisition module obtains are compared with basis pre-stored in server pitch data are such as
Under:
Step 1) carries out signal amplification and filtering processing to audition data, eliminates environmental noise；
Step 2) carries out discrete Fu's formula to the audition data after denoising and converts, and extracts audition data frequency；
Audition data frequency is compared by step 3) with the base frequency of corresponding musical instrument pre-stored in server, works as audition
When the error of data frequency and base frequency is less than or equal to 0.3Hz, indicate that musical instrument accuracy in pitch is normal, when audition data frequency is greater than base
It when plinth frequency 0.3Hz, prompts musical instrument tone higher, when base frequency is greater than audition data frequency 0.3Hz, prompts musical instrument tone
It is relatively low.
10. a kind of method of examination based on audio-video processing according to claim 8, the treatment process of the audio data
The following steps are included:
Step 1) carries out signal amplification and filtering processing to the audio data acquired in real time, eliminates environmental noise；
Step 2) carries out editing to the audio data after denoising, removes audio data unrelated with performance end to end, by remaining audio
Data determine the total duration of audio data to be compared as audio data to be compared；
The audio data to be compared is divided into n sub-piece by step 3), carries out adding window and overlapping for the n sub-piece
Audio characteristic data is extracted after processing respectively, the audio characteristic data includes frequency and amplitude；
Step 4) obtains the standard audio data of pre-stored corresponding musical instrument, corresponding level, corresponding song from server, according to
The total duration of audio data to be compared zooms in and out processing to standard audio data；By the audio data after scaling processing referring to step
It is rapid 3) to be equally divided into n sub-piece, different songs are based on, the frequency and amplitude weighted value of n sub-piece are determined, for described
N sub-piece carries out extracting audio characteristic data after adding window and overlap processing respectively, the audio characteristic data include frequency and
Amplitude；
Step 5) based on the weighted value by the audio frequency characteristics of the audio frequency characteristics of audio data to be compared and standard audio data into
Row compares, and obtains the similarity value of the two, determines total marks of the examination based on similarity value；
The determination method of similarity value in the step 5) is as follows:Wherein, Fi,
Fi' and Wi, Wi' be respectively audio data and standard audio data to be compared frequency and amplitude, αi, βiFor frequency and amplitude weight
Value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910489030.6A CN110364180B (en) | 2019-06-06 | 2019-06-06 | Examination system and method based on audio and video processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910489030.6A CN110364180B (en) | 2019-06-06 | 2019-06-06 | Examination system and method based on audio and video processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110364180A true CN110364180A (en) | 2019-10-22 |
| CN110364180B CN110364180B (en) | 2021-10-22 |
Family
ID=68215685
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910489030.6A Active CN110364180B (en) | 2019-06-06 | 2019-06-06 | Examination system and method based on audio and video processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110364180B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111415682A (en) * | 2020-04-03 | 2020-07-14 | 北京乐界乐科技有限公司 | Intelligent evaluation method for musical instrument |
| CN111477249A (en) * | 2020-04-03 | 2020-07-31 | 北京乐界乐科技有限公司 | Intelligent scoring method for musical instrument |
| CN112601048A (en) * | 2020-12-04 | 2021-04-02 | 抖动科技(深圳)有限公司 | Online examination monitoring method, electronic device and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6150598A (en) * | 1997-09-30 | 2000-11-21 | Yamaha Corporation | Tone data making method and device and recording medium |
| CN105224850A (en) * | 2015-10-24 | 2016-01-06 | 北京进化者机器人科技有限公司 | Combined right-discriminating method and intelligent interactive system |
| CN106205561A (en) * | 2015-01-20 | 2016-12-07 | 株式会社扩乐格 | Variator and tuning display packing |
| CN107818796A (en) * | 2017-11-16 | 2018-03-20 | 重庆师范大学 | A kind of music exam assessment method and system |
| CN108154884A (en) * | 2017-12-07 | 2018-06-12 | 浙江海洋大学 | A kind of anti-identification system impersonated |
| CN108833375A (en) * | 2018-05-30 | 2018-11-16 | 广州爱易学智能信息科技有限公司 | A kind of intelligent examination system |
| CN109741658A (en) * | 2019-03-20 | 2019-05-10 | 任磊 | A kind of Multi-function electronic music instrument tutoring system for music teaching |
-
2019
- 2019-06-06 CN CN201910489030.6A patent/CN110364180B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6150598A (en) * | 1997-09-30 | 2000-11-21 | Yamaha Corporation | Tone data making method and device and recording medium |
| CN106205561A (en) * | 2015-01-20 | 2016-12-07 | 株式会社扩乐格 | Variator and tuning display packing |
| CN105224850A (en) * | 2015-10-24 | 2016-01-06 | 北京进化者机器人科技有限公司 | Combined right-discriminating method and intelligent interactive system |
| CN107818796A (en) * | 2017-11-16 | 2018-03-20 | 重庆师范大学 | A kind of music exam assessment method and system |
| CN108154884A (en) * | 2017-12-07 | 2018-06-12 | 浙江海洋大学 | A kind of anti-identification system impersonated |
| CN108833375A (en) * | 2018-05-30 | 2018-11-16 | 广州爱易学智能信息科技有限公司 | A kind of intelligent examination system |
| CN109741658A (en) * | 2019-03-20 | 2019-05-10 | 任磊 | A kind of Multi-function electronic music instrument tutoring system for music teaching |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111415682A (en) * | 2020-04-03 | 2020-07-14 | 北京乐界乐科技有限公司 | Intelligent evaluation method for musical instrument |
| CN111477249A (en) * | 2020-04-03 | 2020-07-31 | 北京乐界乐科技有限公司 | Intelligent scoring method for musical instrument |
| CN112601048A (en) * | 2020-12-04 | 2021-04-02 | 抖动科技(深圳)有限公司 | Online examination monitoring method, electronic device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110364180B (en) | 2021-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106098068B (en) | A kind of method for recognizing sound-groove and device | |
| Thomas | Sociophonetics: an introduction | |
| Bolt et al. | Speaker identification by speech spectrograms: a scientists' view of its reliability for legal purposes | |
| Cucchiarini | Phonetic transcription: a methodological and empirical study | |
| US9792912B2 (en) | Method for verifying the identity of a speaker, system therefore and computer readable medium | |
| JP4002401B2 (en) | Subject ability measurement system and subject ability measurement method | |
| Treiman et al. | What methods of scoring young children's spelling best predict later spelling performance? | |
| Schweinberger et al. | Recognizing famous voices: Influence of stimulus duration and different types of retrieval cues | |
| CN110364180A (en) | A kind of examination system and method based on audio-video processing | |
| CN102737634A (en) | Authentication method and device based on voice | |
| Watt | The identification of the individual through speech | |
| Beigi | Challenges of LargeScale Speaker Recognition | |
| McLeod et al. | Screening children's speech: The impact of imitated elicitation and word position | |
| KR100995847B1 (en) | Language training method and system based sound analysis on internet | |
| RU2292079C2 (en) | Method for human identification by his biometrical image | |
| Jing et al. | Speech-language pathologists' ratings of speech accuracy in children with speech sound disorders | |
| Ivanova et al. | Enhancing trust in eassessment-the tesla system solution | |
| EP2557555A1 (en) | System and method for music education | |
| Stadler et al. | Rhyming and vocabulary: Effects of lexical restructuring | |
| CN110338747B (en) | Auxiliary method, storage medium, intelligent terminal and auxiliary device for visual inspection | |
| CN110517695A (en) | Verification method and device based on vocal print | |
| Yang | Speech recognition rates and acoustic analyses of English vowels produced by Korean students | |
| JP7479013B2 (en) | Method, program, and system for assessing cognitive function | |
| Davis et al. | Reliability and Validity of TOCS-30 for Young Children with Severe Speech and Expressive Language Delay. | |
| Nie et al. | Mandarin tone recognition in English speakers with normal hearing and with cochlear implants |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |