CN108766439A - A kind of monitoring method and device based on Application on Voiceprint Recognition - Google Patents
A kind of monitoring method and device based on Application on Voiceprint Recognition Download PDFInfo
- Publication number
- CN108766439A CN108766439A CN201810394740.6A CN201810394740A CN108766439A CN 108766439 A CN108766439 A CN 108766439A CN 201810394740 A CN201810394740 A CN 201810394740A CN 108766439 A CN108766439 A CN 108766439A
- Authority
- CN
- China
- Prior art keywords
- audio
- vocal print
- typing
- preset
- application
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000001755 vocal effect Effects 0.000 claims abstract description 99
- 238000001514 detection method Methods 0.000 claims description 14
- 238000012806 monitoring device Methods 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 7
- 108010001267 Protein Subunits Proteins 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 11
- 238000010168 coupling process Methods 0.000 description 5
- 238000005859 coupling reaction Methods 0.000 description 5
- 230000008878 coupling Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
Classifications
-
- 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
- G10L17/00—Speaker identification or verification techniques
-
- 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
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
-
- 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
- G10L17/00—Speaker identification or verification techniques
- G10L17/02—Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
-
- 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
-
- 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
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L2015/088—Word spotting
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The embodiment of the invention discloses a kind of monitoring method and device based on Application on Voiceprint Recognition; it solves existing monitoring technology and generally uses camera; and camera can not normally obtain image after being blocked intentionally; and the result of camera shooting is easy to be limited by angle and light environment, the infull technical problem of caused monitoring.Present invention method includes：The audio that S1, acquisition listen to；S2, speech recognition is carried out to the audio listened to, when the audio listened to includes preset keyword, executes step S3；S3, Application on Voiceprint Recognition is carried out to the audio listened to, and corresponding first vocal print of the audio listened to is compared with the second vocal print in preset vocal print library, if being matched to identical vocal print, location information is sent to early warning platform and responds the early warning platform.
Description
Technical field
The present invention relates to monitoring technology field more particularly to a kind of monitoring method and device based on Application on Voiceprint Recognition.
Background technology
With camera and the growing prosperity of face recognition technology, the block used, the application scenarios such as interior, Ke Yishi
When monitoring and regional extent of deploying to ensure effective monitoring and control of illegal activities, target tracking, public security safety etc. practical applications.
Existing monitoring technology generally uses camera, and camera can not normally obtain image after being blocked intentionally, and
The result of camera shooting is easy to be limited by angle and light environment, causes to monitor infull technical problem.
Invention content
The present invention provides a kind of monitoring method and device based on Application on Voiceprint Recognition, it is general to solve existing monitoring technology
Camera is used, and camera can not normally obtain image after being blocked intentionally, and the result imaged is easy by angle and light
Thread environment limits, the infull technical problem of caused monitoring.
The present invention provides a kind of monitoring methods based on Application on Voiceprint Recognition, including：
The audio that S1, acquisition listen to；
S2, speech recognition is carried out to the audio listened to, when the audio listened to includes preset keyword
When, execute step S3；
S3, Application on Voiceprint Recognition is carried out to the audio that listens to, and by corresponding first vocal print of the audio listened to
It is compared with the second vocal print in preset vocal print library, if being matched to identical vocal print, sends location information to early warning platform
And respond the early warning platform.
Optionally, further include before the step S1：
S01, the audio for obtaining typing；
S02, the extraction typing audio in the second vocal print and preserve into preset vocal print library.
Optionally, after the step S01, further include before the step S02：
To progress voice quality detection in the audio of the typing, including：
Calculate the first signal-to-noise ratio, first the average energy value and the first efficient voice duration of the audio of the typing；
Successively by the first signal-to-noise ratio of the audio of the typing, first the average energy value and the first efficient voice duration with it is right
The first preset threshold value answered is compared, if the first signal-to-noise ratio, first the average energy value and the first efficient voice duration are above
Corresponding first predetermined threshold value, it is determined that the voice quality of the audio of the typing is qualified, and executes next step, and otherwise prompt is used
Family re-types audio and returns to the audio for reacquiring typing.
Optionally, the first signal-to-noise ratio, first the average energy value and the first effective language of the audio for calculating the typing
Further include before sound duration：
Judge that the content type in the audio of the typing, content type include random digit, random phrase, random long sentence
And fixed phrase；
Corresponding first preset threshold value of the first efficient voice duration is determined according to the content type in the audio of the typing.
Optionally, the step S3 is specifically included：
Application on Voiceprint Recognition, the first vocal print in the audio listened to described in extraction are carried out to the audio listened to；
The first vocal print in the audio listened to is compared with the second vocal print in preset vocal print library, is obtained
With value；
Judge whether matching value is higher than preset matching threshold, when determining that matching value is higher than preset matching threshold, it is fixed to send
Position information to early warning platform and responds the early warning platform.
Optionally, when matching value is less than preset matching threshold, the first vocal print in the audio listened to is added
Extremely in the preset vocal print library, and respond early warning platform.
The present invention provides a kind of monitoring devices based on Application on Voiceprint Recognition, including：
First acquisition unit, for obtaining the audio listened to；
Voice recognition unit, for carrying out speech recognition to the audio listened to, when in the audio listened to
When including preset keyword, vocal print comparing unit is jumped to；
Vocal print comparing unit, for carrying out Application on Voiceprint Recognition to the audio that listens to, and by the audio listened to
Corresponding first vocal print is compared with the second vocal print in preset vocal print library, if being matched to identical vocal print, sends positioning
Information is to early warning platform and responds the early warning platform.
Optionally, a kind of monitoring device based on Application on Voiceprint Recognition provided by the invention further includes：
Second acquisition unit, the audio for obtaining typing；
Voiceprint extraction unit, the second vocal print in audio for extracting the typing are simultaneously preserved into preset vocal print library.
Optionally, a kind of monitoring device based on Application on Voiceprint Recognition provided by the invention further includes：
Voice quality detection unit, for carrying out voice quality detection in the audio of the typing；
Institute's Voice Quality detection unit includes：
Computation subunit, the first signal-to-noise ratio, first the average energy value and first of the audio for calculating the typing have
Imitate voice duration；
Comparison subunit, for successively by the first signal-to-noise ratio of the audio of the typing, first the average energy value and first
Efficient voice duration is compared with corresponding first preset threshold value, if the first signal-to-noise ratio, first the average energy value and first have
Effect voice duration is above corresponding first predetermined threshold value, it is determined that the voice quality of the audio of the typing is qualified, and executes
In next step, otherwise prompt user re-types audio and returns to the audio for reacquiring typing.
Optionally, voice quality detection unit further includes：
Judgment sub-unit, the content type in audio for judging the typing, content type include random digit, with
Machine phrase, random long sentence and fixed phrase；
Threshold value determination subelement determines the first efficient voice duration for the content type in the audio according to the typing
Corresponding first preset threshold value.
As can be seen from the above technical solutions, the present invention has the following advantages：
The present invention provides a kind of monitoring methods based on Application on Voiceprint Recognition, including：The audio that S1, acquisition listen to；It is S2, right
The audio listened to carries out speech recognition, when the audio listened to includes preset keyword, executes step S3；
S3, Application on Voiceprint Recognition is carried out to the audio that listens to, and by corresponding first vocal print of the audio listened to and preset sound
The second vocal print in line library is compared, if being matched to identical vocal print, sends location information to early warning platform and responds institute
State early warning platform.
In the present invention, by obtaining the audio listened to, and the preset keyword in the audio listened to is identified, if monitoring
Preset keyword has been arrived, then Application on Voiceprint Recognition has been carried out to the audio that listens to, and by the first vocal print recognized and preset vocal print library
In the second vocal print be compared, judge whether be tracking target, solve existing monitoring technology generally use camera,
And camera can not normally obtain image after being blocked intentionally, and the result imaged is easy to be limited by angle and light environment,
The infull technical problem of caused monitoring.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention without having to pay creative labor, may be used also for those of ordinary skill in the art
To obtain other attached drawings according to these attached drawings.
Fig. 1 is a kind of flow diagram of one embodiment of the monitoring method based on Application on Voiceprint Recognition provided by the invention；
Fig. 2 is a kind of flow signal of another embodiment of the monitoring method based on Application on Voiceprint Recognition provided by the invention
Figure；
Fig. 3 is a kind of structural schematic diagram of one embodiment of the monitoring device based on Application on Voiceprint Recognition provided by the invention；
Fig. 4 is a kind of structural representation of another embodiment of the monitoring device based on Application on Voiceprint Recognition provided by the invention
Figure.
Specific implementation mode
An embodiment of the present invention provides a kind of monitoring method and device based on Application on Voiceprint Recognition, solve existing monitoring skill
Art generally uses camera, and camera can not normally obtain image after being blocked intentionally, and the result imaged is easy by angle
Degree and light environment limitation, the infull technical problem of caused monitoring.
In order to make the invention's purpose, features and advantages of the invention more obvious and easy to understand, below in conjunction with the present invention
Attached drawing in embodiment, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that disclosed below
Embodiment be only a part of the embodiment of the present invention, and not all embodiment.Based on the embodiments of the present invention, this field
All other embodiment that those of ordinary skill is obtained without making creative work, belongs to protection of the present invention
Range.
Referring to Fig. 1, the present invention provides a kind of monitoring methods based on Application on Voiceprint Recognition, including：
101, the audio listened to is obtained；
102, speech recognition is carried out to the audio listened to, when the audio listened to includes preset keyword, executed
Step 103；
103, Application on Voiceprint Recognition carried out to the audio that listens to, and by corresponding first vocal print of the audio listened to and preset sound
The second vocal print in line library is compared, if being matched to identical vocal print, sends location information to early warning platform and responds pre-
Alert platform.
In the embodiment of the present invention, by obtaining the audio listened to, and the preset keyword in the audio listened to is identified,
If having listened to preset keyword, Application on Voiceprint Recognition carried out to the audio that listens to, and by the first vocal print recognized with it is preset
The second vocal print in vocal print library is compared, and judges whether it is the target tracked, solves existing monitoring technology and generally use
Camera, and camera can not normally obtain image after being blocked intentionally, and the result imaged is easy by angle and light ring
Border limits, the infull technical problem of caused monitoring.
It is the explanation carried out to a kind of one embodiment of the monitoring method based on Application on Voiceprint Recognition provided by the invention above,
A kind of another embodiment of the monitoring method based on Application on Voiceprint Recognition provided by the invention will be illustrated below.
Referring to Fig. 2, the present invention provides a kind of monitoring methods based on Application on Voiceprint Recognition, including：
201, the audio of typing is obtained；
It should be noted that before building preset vocal print library, first choice obtains the audio for needing typing.
202, to progress voice quality detection in the audio of typing, including：
2021, judge that the content type in the audio of typing, content type include random digit, random phrase, with captain
Sentence and fixed phrase；
It should be noted that the content type in judging the audio of typing, content type includes random digit, random short
Language, random long sentence and fixed phrase.
2022, the corresponding first preset threshold of the first efficient voice duration is determined according to the content type in the audio of typing
Value；
It should be noted that determining the first efficient voice duration corresponding first according to the content type in the audio of typing
Preset threshold value, if random digit, then corresponding first preset threshold value of the first efficient voice duration is 1.2 seconds；If random short
Language, then corresponding first preset threshold value of the first efficient voice duration is 1.8 seconds；If random long sentence, then when the first efficient voice
Long corresponding first preset threshold value is 16 seconds；If fixed phrase, then corresponding first preset threshold value of the first efficient voice duration
It is 0.8 second.
2023, the first signal-to-noise ratio, first the average energy value and the first efficient voice duration of the audio of typing are calculated；
It should be noted that calculating the first signal-to-noise ratio, first the average energy value and the first efficient voice of the audio of typing
Duration.
2024, successively by the first signal-to-noise ratio of the audio of typing, first the average energy value and the first efficient voice duration with
Corresponding first preset threshold value is compared, if the first signal-to-noise ratio, first the average energy value and the first efficient voice duration are high
In corresponding first predetermined threshold value, it is determined that the voice quality of the audio of typing is qualified, and executes next step, otherwise prompts user
It re-types audio and returns to the audio for reacquiring typing；
It should be noted that successively by the first signal-to-noise ratio of the audio of typing, first the average energy value and first effective language
Sound duration is compared with corresponding first preset threshold value, if the first signal-to-noise ratio, first the average energy value and the first efficient voice
Duration is above corresponding first predetermined threshold value, it is determined that the voice quality of the audio of typing is qualified, and executes next step, otherwise
Prompt user re-types audio and returns to the audio for reacquiring typing, wherein the corresponding first default threshold of the first signal-to-noise ratio
Value is 10 decibels, and corresponding first predetermined threshold value of first the average energy value is [1000,30000], the first efficient voice duration pair
The first preset threshold value answered has determined in previous step.
203, it extracts the second vocal print in the audio of typing and preserves into preset vocal print library；
It should be noted that after the voice quality qualification for the audio for determining typing, second in the audio of typing is extracted
Vocal print is simultaneously preserved into preset vocal print library.
204, the audio listened to is obtained；
It should be noted that in monitoring, the audio listened to is obtained.
205, speech recognition is carried out to the audio listened to, when the audio listened to includes preset keyword, executed
Step 206；
It should be noted that carry out speech recognition to the audio that listens to, judge among the audio listened to whether include
Preset keyword, if so, thening follow the steps 206, wherein preset keyword is user's sets itself.
206, Application on Voiceprint Recognition is carried out to the audio listened to, extracts the first vocal print in the audio listened to；
It should be noted that there are the audios of the typing of preset keyword to carry out Application on Voiceprint Recognition, the sound listened to is extracted
The first vocal print in frequency.
207, the first vocal print in the audio listened to is compared with the second vocal print in preset vocal print library, is obtained
With value；
It should be noted that the first vocal print in the audio listened to is compared with the second vocal print in preset vocal print library
Right, preset vocal print library includes the second vocal print of at least one user of typing, therefore obtains at least one matching value.
208, judge whether matching value is higher than preset matching threshold, when determining that matching value is higher than preset matching threshold, hair
Location information is sent to early warning platform and responds early warning platform；
It should be noted that judging whether the matching value obtained is higher than preset matching threshold, that is, judge the audio listened to
In whether have the corresponding vocal print of user of typing in preset vocal print library, if so, sending location information to early warning platform and sound
Answer early warning platform.
209, when matching value is less than preset matching threshold, the first vocal print in the audio listened to is added to preset sound
In line library, and respond early warning platform；
It should be noted that when matching value is less than preset matching threshold, illustrate related without preserving in preset vocal print library
Second vocal print, but there are preset keyword in the audio due to listening to, need corresponding first vocal print of the audio that will be listened to
It preserves into preset vocal print library, and responds early warning platform.
It is saying to a kind of another embodiment progress of the monitoring method based on Application on Voiceprint Recognition provided by the invention above
It is bright, a kind of one embodiment of the monitoring device based on Application on Voiceprint Recognition provided by the invention will be illustrated below.
Referring to Fig. 3, the present invention provides a kind of one embodiment of the monitoring device based on Application on Voiceprint Recognition, including：
First acquisition unit 301, for obtaining the audio listened to；
Voice recognition unit 302, for carrying out speech recognition to the audio listened to, when the audio listened to includes pre-
When setting keyword, vocal print comparing unit 33 is jumped to；
Vocal print comparing unit 303, for carrying out Application on Voiceprint Recognition to the audio listened to, and the audio listened to is corresponding
First vocal print is compared with the second vocal print in preset vocal print library, if being matched to identical vocal print, sends location information extremely
Early warning platform simultaneously responds early warning platform.
It is the explanation carried out to a kind of one embodiment of the monitoring device based on Application on Voiceprint Recognition provided by the invention above,
A kind of another embodiment of the monitoring device based on Application on Voiceprint Recognition provided by the invention will be illustrated below.
Referring to Fig. 4, the present invention provides a kind of another embodiments of the monitoring device based on Application on Voiceprint Recognition, including：
Second acquisition unit 401, the audio for obtaining typing；
Voice quality detection unit 402, for carrying out voice quality detection in the audio of typing；
Voice quality detection unit 402 includes：
Judgment sub-unit 4021, the content type in audio for judging typing, content type include random digit, with
Machine phrase, random long sentence and fixed phrase；
Threshold value determination subelement 4022 determines the first efficient voice duration for the content type in the audio according to typing
Corresponding first preset threshold value；
Computation subunit 4023, the first signal-to-noise ratio, first the average energy value and first of the audio for calculating typing have
Imitate voice duration；
Comparison subunit 4024, for successively by the first signal-to-noise ratio of the audio of typing, first the average energy value and first
Efficient voice duration is compared with corresponding first preset threshold value, if the first signal-to-noise ratio, first the average energy value and first have
Effect voice duration is above corresponding first predetermined threshold value, it is determined that the voice quality of the audio of typing is qualified, and executes next
Otherwise step prompts user to re-type audio and returns to the audio for reacquiring typing；
Voiceprint extraction unit 403, the second vocal print in audio for extracting typing are simultaneously preserved into preset vocal print library；
First acquisition unit 404, for obtaining the audio listened to；
Voice recognition unit 405, for carrying out speech recognition to the audio listened to, when the audio listened to includes pre-
When setting keyword, vocal print comparing unit 406 is jumped to；
Vocal print comparing unit 406, for carrying out Application on Voiceprint Recognition to the audio listened to, and the audio listened to is corresponding
First vocal print is compared with the second vocal print in preset vocal print library, if being matched to identical vocal print, sends location information extremely
Early warning platform simultaneously responds early warning platform；
Vocal print comparing unit 406 specifically includes：
Subelement 4061 is extracted, for carrying out Application on Voiceprint Recognition to the audio that listens to, extracts the in the audio listened to
One vocal print；
Comparison subunit 4062, for by the second vocal print in the first vocal print and the preset vocal print library in the audio listened to
It is compared, obtains matching value；
Coupling subelement 4063, for judging whether matching value is higher than preset matching threshold, when determining matching value higher than pre-
When setting matching threshold, sends location information and to early warning platform and respond early warning platform；
Coupling subelement 4063 is additionally operable to when matching value is less than preset matching threshold, by first in the audio listened to
Vocal print is added in preset vocal print library, and responds early warning platform.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided herein, it should be understood that disclosed system, device and method can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only a kind of division of logic function, formula that in actual implementation, there may be another division manner, such as multiple units or component
It can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown or
The mutual coupling, direct-coupling or communication connection discussed can be the indirect coupling by some interfaces, device or unit
It closes or communicates to connect, can be electrical, machinery or other forms.
The unit illustrated as separating component may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, you can be located at a place, or may be distributed over multiple
In network element.Some or all of unit therein can be selected according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it can also
It is that each unit physically exists alone, it can also be during two or more units be integrated in one unit.Above-mentioned integrated list
The form that hardware had both may be used in member is realized, can also be realized in the form of SFU software functional unit.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can be stored in a computer read/write memory medium.Based on this understanding, technical scheme of the present invention is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server or the network equipment etc.) executes the complete of each embodiment the method for the present invention
Portion or part steps.And storage medium above-mentioned includes：USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can store journey
The medium of sequence code.
The above, the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although with reference to before
Stating embodiment, invention is explained in detail, it will be understood by those of ordinary skill in the art that：It still can be to preceding
The technical solution recorded in each embodiment is stated to modify or equivalent replacement of some of the technical features；And these
Modification or replacement, the spirit and scope for various embodiments of the present invention technical solution that it does not separate the essence of the corresponding technical solution.
Claims (10)
1. a kind of monitoring method based on Application on Voiceprint Recognition, which is characterized in that including：
The audio that S1, acquisition listen to；
S2, the audio progress speech recognition listened to is held when the audio listened to includes preset keyword
Row step S3；
S3, Application on Voiceprint Recognition is carried out to the audio listened to, and by corresponding first vocal print of the audio listened to and in advance
The second vocal print set in vocal print library is compared, if being matched to identical vocal print, sends location information to early warning platform and sound
Answer the early warning platform.
2. the monitoring method according to claim 1 based on Application on Voiceprint Recognition, which is characterized in that also wrapped before the step S1
It includes：
S01, the audio for obtaining typing；
S02, the extraction typing audio in the second vocal print and preserve into preset vocal print library.
3. the monitoring method according to claim 2 based on Application on Voiceprint Recognition, which is characterized in that after the step S01, institute
Further include before stating step S02：
To progress voice quality detection in the audio of the typing, including：
Calculate the first signal-to-noise ratio, first the average energy value and the first efficient voice duration of the audio of the typing；
Successively by the first signal-to-noise ratio of the audio of the typing, first the average energy value and the first efficient voice duration with it is corresponding
First preset threshold value is compared, if the first signal-to-noise ratio, first the average energy value and the first efficient voice duration are above correspondence
The first predetermined threshold value, it is determined that the voice quality of the audio of the typing is qualified, and executes next step, otherwise user is prompted to weigh
New inputting audio simultaneously returns to the audio for reacquiring typing.
4. the monitoring method according to claim 3 based on Application on Voiceprint Recognition, which is characterized in that the calculating typing
Further include before the first signal-to-noise ratio, first the average energy value and the first efficient voice duration of audio：
Judge that the content type in the audio of the typing, content type include random digit, random phrase, random long sentence and consolidate
Determine phrase；
Corresponding first preset threshold value of the first efficient voice duration is determined according to the content type in the audio of the typing.
5. the monitoring method according to claim 1 based on Application on Voiceprint Recognition, which is characterized in that the step S3 is specifically wrapped
It includes：
Application on Voiceprint Recognition, the first vocal print in the audio listened to described in extraction are carried out to the audio listened to；
The first vocal print in the audio listened to is compared with the second vocal print in preset vocal print library, is matched
Value；
Judge whether matching value is higher than preset matching threshold, when determining that matching value is higher than preset matching threshold, sends positioning letter
Breath is to early warning platform and responds the early warning platform.
6. the monitoring method according to claim 5 based on Application on Voiceprint Recognition, which is characterized in that when matching value is less than preset
When with threshold value, the first vocal print in the audio listened to is added in the preset vocal print library, and respond early warning platform.
7. a kind of monitoring device based on Application on Voiceprint Recognition, which is characterized in that including：
First acquisition unit, for obtaining the audio listened to；
Voice recognition unit, for carrying out speech recognition to the audio listened to, when the audio listened to includes
When preset keyword, vocal print comparing unit is jumped to；
Vocal print comparing unit for carrying out Application on Voiceprint Recognition to the audio listened to, and the audio listened to is corresponded to
The first vocal print be compared with the second vocal print in preset vocal print library, if being matched to identical vocal print, send location information
To early warning platform and respond the early warning platform.
8. the monitoring device according to claim 7 based on Application on Voiceprint Recognition, which is characterized in that further include：
Second acquisition unit, the audio for obtaining typing；
Voiceprint extraction unit, the second vocal print in audio for extracting the typing are simultaneously preserved into preset vocal print library.
9. the monitoring device according to claim 8 based on Application on Voiceprint Recognition, which is characterized in that further include：
Voice quality detection unit, for carrying out voice quality detection in the audio of the typing；
Institute's Voice Quality detection unit includes：
Computation subunit, the first signal-to-noise ratio, first the average energy value and the first effective language of the audio for calculating the typing
Sound duration；
Comparison subunit, for successively that the first signal-to-noise ratio of the audio of the typing, first the average energy value and first is effective
Voice duration is compared with corresponding first preset threshold value, if the first signal-to-noise ratio, first the average energy value and first effective language
Sound duration is above corresponding first predetermined threshold value, it is determined that the voice quality of the audio of the typing is qualified, and executes next
Otherwise step prompts user to re-type audio and returns to the audio for reacquiring typing.
10. the monitoring device according to claim 9 based on Application on Voiceprint Recognition, which is characterized in that voice quality detection unit
Further include：
Judgment sub-unit, the content type in audio for judging the typing, content type includes random digit, random short
Language, random long sentence and fixed phrase；
Threshold value determination subelement determines that the first efficient voice duration corresponds to for the content type in the audio according to the typing
The first preset threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810394740.6A CN108766439A (en) | 2018-04-27 | 2018-04-27 | A kind of monitoring method and device based on Application on Voiceprint Recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810394740.6A CN108766439A (en) | 2018-04-27 | 2018-04-27 | A kind of monitoring method and device based on Application on Voiceprint Recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108766439A true CN108766439A (en) | 2018-11-06 |
Family
ID=64012425
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810394740.6A Pending CN108766439A (en) | 2018-04-27 | 2018-04-27 | A kind of monitoring method and device based on Application on Voiceprint Recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108766439A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109448722A (en) * | 2018-12-28 | 2019-03-08 | 合肥凯捷技术有限公司 | A kind of speech analysis system |
| CN109616125A (en) * | 2018-12-13 | 2019-04-12 | 苏州思必驰信息科技有限公司 | Monitoring method and system based on Application on Voiceprint Recognition |
| CN109634554A (en) * | 2018-12-18 | 2019-04-16 | 三星电子（中国）研发中心 | Method and apparatus for output information |
| CN109754811A (en) * | 2018-12-10 | 2019-05-14 | 平安科技（深圳）有限公司 | Sound-source follow-up method, apparatus, equipment and storage medium based on biological characteristic |
| CN109817224A (en) * | 2019-02-22 | 2019-05-28 | 深圳云游四海信息科技有限公司 | A kind of voice sensitive word monitor system and method |
| CN110830771A (en) * | 2019-11-11 | 2020-02-21 | 广州国音智能科技有限公司 | Intelligent monitoring method, device, equipment and computer readable storage medium |
| CN110827829A (en) * | 2019-10-24 | 2020-02-21 | 秒针信息技术有限公司 | Passenger flow analysis method and system based on voice recognition |
| CN111128199A (en) * | 2019-12-27 | 2020-05-08 | 中国人民解放军陆军工程大学 | Sensitive speaker monitoring and recording control method and system based on deep learning |
| CN111275909A (en) * | 2018-12-04 | 2020-06-12 | 阿里巴巴集团控股有限公司 | Security early warning method and device |
| CN111768789A (en) * | 2020-08-03 | 2020-10-13 | 上海依图信息技术有限公司 | Electronic equipment and method, device and medium for determining identity of voice sender thereof |
| CN112992154A (en) * | 2021-05-08 | 2021-06-18 | 北京远鉴信息技术有限公司 | Voice identity determination method and system based on enhanced voiceprint library |
| WO2021133504A1 (en) * | 2019-12-23 | 2021-07-01 | Motorola Solutions, Inc. | Using a sensor hub to generate a tracking profile for tracking an object |
| CN113593581A (en) * | 2021-07-12 | 2021-11-02 | 西安讯飞超脑信息科技有限公司 | Voiceprint distinguishing method and device, computer equipment and storage medium |
| WO2024197594A1 (en) * | 2023-03-28 | 2024-10-03 | 京东方科技集团股份有限公司 | Audio monitoring method, system and device, and computer storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101833843A (en) * | 2009-03-13 | 2010-09-15 | 新奥特硅谷视频技术有限责任公司 | Monitoring system based on voiceprint authentication |
| CN103646481A (en) * | 2013-11-27 | 2014-03-19 | 大连创达技术交易市场有限公司 | Ward calling system |
| CN104065836A (en) * | 2014-05-30 | 2014-09-24 | 小米科技有限责任公司 | Method and device for monitoring calls |
| CN104269016A (en) * | 2014-09-22 | 2015-01-07 | 北京奇艺世纪科技有限公司 | Alarm method and device |
| US20150131788A1 (en) * | 2010-09-07 | 2015-05-14 | Securus Technologies | Multi-party conversation analyzer & logger |
| CN104954429A (en) * | 2015-04-26 | 2015-09-30 | 安徽味唯网络科技有限公司 | Method of automatic help seeking system in danger |
| CN105321514A (en) * | 2014-05-28 | 2016-02-10 | 西安中兴新软件有限责任公司 | Alarm method and terminal |
| CN105679313A (en) * | 2016-04-15 | 2016-06-15 | 福建新恒通智能科技有限公司 | Audio recognition alarm system and method |
| CN107886958A (en) * | 2017-11-10 | 2018-04-06 | 广州势必可赢网络科技有限公司 | Express cabinet pickup method and device based on voiceprint |
-
2018
- 2018-04-27 CN CN201810394740.6A patent/CN108766439A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101833843A (en) * | 2009-03-13 | 2010-09-15 | 新奥特硅谷视频技术有限责任公司 | Monitoring system based on voiceprint authentication |
| US20150131788A1 (en) * | 2010-09-07 | 2015-05-14 | Securus Technologies | Multi-party conversation analyzer & logger |
| CN103646481A (en) * | 2013-11-27 | 2014-03-19 | 大连创达技术交易市场有限公司 | Ward calling system |
| CN105321514A (en) * | 2014-05-28 | 2016-02-10 | 西安中兴新软件有限责任公司 | Alarm method and terminal |
| CN104065836A (en) * | 2014-05-30 | 2014-09-24 | 小米科技有限责任公司 | Method and device for monitoring calls |
| CN104269016A (en) * | 2014-09-22 | 2015-01-07 | 北京奇艺世纪科技有限公司 | Alarm method and device |
| CN104954429A (en) * | 2015-04-26 | 2015-09-30 | 安徽味唯网络科技有限公司 | Method of automatic help seeking system in danger |
| CN105679313A (en) * | 2016-04-15 | 2016-06-15 | 福建新恒通智能科技有限公司 | Audio recognition alarm system and method |
| CN107886958A (en) * | 2017-11-10 | 2018-04-06 | 广州势必可赢网络科技有限公司 | Express cabinet pickup method and device based on voiceprint |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111275909A (en) * | 2018-12-04 | 2020-06-12 | 阿里巴巴集团控股有限公司 | Security early warning method and device |
| CN111275909B (en) * | 2018-12-04 | 2021-12-28 | 阿里巴巴集团控股有限公司 | Security early warning method and device |
| CN109754811A (en) * | 2018-12-10 | 2019-05-14 | 平安科技（深圳）有限公司 | Sound-source follow-up method, apparatus, equipment and storage medium based on biological characteristic |
| CN109754811B (en) * | 2018-12-10 | 2023-06-02 | 平安科技（深圳）有限公司 | Sound source tracking method, device, equipment and storage medium based on biological characteristics |
| CN109616125A (en) * | 2018-12-13 | 2019-04-12 | 苏州思必驰信息科技有限公司 | Monitoring method and system based on Application on Voiceprint Recognition |
| CN109634554A (en) * | 2018-12-18 | 2019-04-16 | 三星电子（中国）研发中心 | Method and apparatus for output information |
| CN109448722A (en) * | 2018-12-28 | 2019-03-08 | 合肥凯捷技术有限公司 | A kind of speech analysis system |
| CN109817224A (en) * | 2019-02-22 | 2019-05-28 | 深圳云游四海信息科技有限公司 | A kind of voice sensitive word monitor system and method |
| CN110827829A (en) * | 2019-10-24 | 2020-02-21 | 秒针信息技术有限公司 | Passenger flow analysis method and system based on voice recognition |
| CN110830771A (en) * | 2019-11-11 | 2020-02-21 | 广州国音智能科技有限公司 | Intelligent monitoring method, device, equipment and computer readable storage medium |
| WO2021133504A1 (en) * | 2019-12-23 | 2021-07-01 | Motorola Solutions, Inc. | Using a sensor hub to generate a tracking profile for tracking an object |
| US11188775B2 (en) | 2019-12-23 | 2021-11-30 | Motorola Solutions, Inc. | Using a sensor hub to generate a tracking profile for tracking an object |
| CN111128199A (en) * | 2019-12-27 | 2020-05-08 | 中国人民解放军陆军工程大学 | Sensitive speaker monitoring and recording control method and system based on deep learning |
| CN111768789A (en) * | 2020-08-03 | 2020-10-13 | 上海依图信息技术有限公司 | Electronic equipment and method, device and medium for determining identity of voice sender thereof |
| CN111768789B (en) * | 2020-08-03 | 2024-02-23 | 上海依图信息技术有限公司 | Electronic equipment, and method, device and medium for determining identity of voice generator of electronic equipment |
| CN112992154A (en) * | 2021-05-08 | 2021-06-18 | 北京远鉴信息技术有限公司 | Voice identity determination method and system based on enhanced voiceprint library |
| CN113593581A (en) * | 2021-07-12 | 2021-11-02 | 西安讯飞超脑信息科技有限公司 | Voiceprint distinguishing method and device, computer equipment and storage medium |
| CN113593581B (en) * | 2021-07-12 | 2024-04-19 | 西安讯飞超脑信息科技有限公司 | Voiceprint discrimination method, voiceprint discrimination device, computer device and storage medium |
| WO2024197594A1 (en) * | 2023-03-28 | 2024-10-03 | 京东方科技集团股份有限公司 | Audio monitoring method, system and device, and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108766439A (en) | A kind of monitoring method and device based on Application on Voiceprint Recognition | |
| CN109769099B (en) | Method and device for detecting abnormality of call person | |
| CN105139858B (en) | A kind of information processing method and electronic equipment | |
| CN105869645B (en) | Voice data processing method and device | |
| CN108039176A (en) | Voiceprint authentication method and device for preventing recording attack and access control system | |
| US9142210B2 (en) | Method and device for speaker recognition | |
| CN105976815A (en) | Vehicle voice recognition method and vehicle voice recognition device | |
| CN108564948A (en) | A kind of audio recognition method and electronic equipment | |
| CN109346055A (en) | Active denoising method, device, earphone and computer storage medium | |
| CN108615537A (en) | A kind of multichannel way of recording, apparatus and system | |
| Kiktova et al. | Gun type recognition from gunshot audio recordings | |
| CN110767214A (en) | Speech recognition method and device and speech recognition system | |
| CN111816185A (en) | Method and device for identifying speaker in mixed voice | |
| CN107871236A (en) | Electronic equipment voiceprint payment method and device | |
| CN106330915A (en) | Voice verification processing method and device | |
| WO2001024163A1 (en) | Speaker verification using hidden markov models with clusters and score thresholding | |
| JP2008145988A (en) | Noise detecting device and noise detecting method | |
| CN107680592A (en) | A kind of mobile terminal sound recognition methods and mobile terminal and storage medium | |
| CN110599751A (en) | Danger alarm method and device, computer equipment and storage medium | |
| CN106971715A (en) | A kind of speech recognition equipment applied to robot | |
| CN113270112A (en) | Electronic camouflage voice automatic distinguishing and restoring method and system | |
| CN110060682B (en) | Sound box control method and device | |
| CN108806693A (en) | Method and device for preventing Internet from refreshing list | |
| US20230274377A1 (en) | An end-to-end proctoring system and method for conducting a secure online examination | |
| CN116013255A (en) | High-security voice recognition method, system, equipment and medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181106 |