CN107170455A - A kind of simple speech identifying device - Google Patents
A kind of simple speech identifying device Download PDFInfo
- Publication number
- CN107170455A CN107170455A CN201710401510.3A CN201710401510A CN107170455A CN 107170455 A CN107170455 A CN 107170455A CN 201710401510 A CN201710401510 A CN 201710401510A CN 107170455 A CN107170455 A CN 107170455A
- Authority
- CN
- China
- Prior art keywords
- module
- voice
- unit
- acquisition module
- voice signal
- 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
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000006243 chemical reaction Methods 0.000 claims abstract description 8
- 230000009467 reduction Effects 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 8
- 238000013461 design Methods 0.000 claims description 3
- 238000000034 method Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000010276 construction Methods 0.000 abstract description 2
- 230000002618 waking effect Effects 0.000 abstract 1
- 230000008859 change Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000241 respiratory effect Effects 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
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Machine Translation (AREA)
Abstract
The present invention relates to identification technology field, specially a kind of simple speech identifying device, including starting module, voice acquisition module, speech processing module, sound identification module and output module；The starting module is for detecting whether having the signal for starting the voice acquisition module and waking up voice acquisition module；The voice acquisition module is used to gather voice signal；The speech processing module is used to receive the voice signal that the voice acquisition module is collected, and analog-to-digital conversion is carried out to the voice signal, and the sound identification module is used to recognize the voice signal Jing Guo analog-to-digital conversion；The output module is used to export the result that the sound identification module is identified.The success rate of speech recognition equipment identification simple in construction of the present invention is high.
Description
【Technical field】
The present invention relates to identification technology field, specially a kind of simple speech identifying device.
【Background technology】
The application of speech recognition in modern society is more and more frequent, and people can also be commonly used in life and carry voice
The sci-tech product of identification function.For example voice is made a phone call, and voice writes short message, Voice command TV etc..Classify by articulation type,
Isolated word recognition can be divided into, connection string and continuous speech recognition etc., the algorithm of identification have dynamic time warping, vector quantity
Change, hidden Markov model, artificial neural network etc..Under continuous research, speech recognition obtains considerable progress, identification
Rate and identification range are greatly improved, but the identifying system of these algorithms is more complicated, to the requirement of chip computing capability
Higher, have or even needs, which are networked, to be realized.
【The content of the invention】
For the above, the present invention is by a kind of simple speech identifying device, and its is simple in construction, and discrimination is high, to hardware system
System requires low.
The purpose of the present invention is achieved through the following technical solutions：
A kind of simple speech identifying device, it is characterised in that at including starting module, voice acquisition module, voice
Manage module, sound identification module and output module；
The starting module is connected with the voice acquisition module, the voice acquisition module and speech processing module phase
Even, the speech processing module is connected with the sound identification module, and the sound identification module is connected with the output module；
The starting module is used to detect voice signal and starts voice acquisition module；
The voice acquisition module is used to gather voice signal；
The speech processing module includes converting unit and noise reduction unit, and the converting unit is adopted for receiving the voice
The voice signal that collection module is collected, and analog-to-digital conversion is carried out to the voice signal, the noise reduction unit is used to reduce described
The noise of voice signal；
The sound identification module includes the first recognition unit, the second recognition unit, memory cell, weighting processing unit,
First recognition unit is used for the formatted file of the default voice of the voice signal after analog-to-digital conversion and noise reduction and storage
Similarity system design is carried out, the default phonetic matrix file similar to voice signal is drawn；Second recognition unit is used to receive
Voice signal after described similar default phonetic matrix file and noise reduction, and by the voice signal after the noise reduction to it is similar
Default phonetic matrix file is compared, and obtains both difference values；It is all pre- that the memory cell is compared for storing
If the set of voice；The difference value that the weighting processing unit is drawn to the second voice recognition unit is folded with weight variable
Plus, draw success value；
The output module is used to export the result that the sound identification module is identified.
Further, the difference value is compared with default threshold value, if the difference value is less than default threshold value,
Then enter weighting processing unit, otherwise, indicate that the first recognition unit, the second recognition unit re-start and compare identification, Zhi Daoshi
Untill other difference value is less than default threshold value.
Further, the voice acquisition module converts voice signals into electric signal using microphone.
Further, starting module includes detection unit and wakeup unit, and the detection unit and wakeup unit are mutually interconnected
Connect, the detection unit is for detecting whether there is the signal for starting the voice acquisition module, and wakeup unit is used to wake up voice
Acquisition module.
The beneficial effects of the invention are as follows：By being controlled to starting module to whole system, no signal is that system is quiet
It is silent, reduce energy consumption.Speech processing module carries out the interference that processing reduces external noise, respiratory air flow, electric current to voice.Voice is known
Other module carries out similitude, diversity identifying processing to voice respectively, obtains the recognition result with voice signal, improves voice
The success rate of identification.
Brief description of the drawings
Fig. 1 is simple speech identifying device structured flowchart of the present invention；
【Embodiment】
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
It should be noted that when component is referred to as " being fixed on " another component, it can be directly on another component
Or can also have component placed in the middle.When a component is considered as " connection " another component, it can be directly connected to
To another component or it may be simultaneously present component placed in the middle.When a component is considered as " being arranged at " another component, it
Can be set directly on another component or may be simultaneously present component placed in the middle.Term as used herein is " vertical
", " level ", "left", "right" and similar statement for illustrative purposes only.
Unless otherwise defined, all of technologies and scientific terms used here by the article is with belonging to technical field of the invention
The implication that technical staff is generally understood that is identical.Term used in the description of the invention herein is intended merely to description tool
The purpose of the embodiment of body, it is not intended that in the limitation present invention.Term as used herein " and/or " include one or more phases
The arbitrary and all combination of the Listed Items of pass.
Refer to accompanying drawing
A kind of simple speech identifying device, including including starting module 1, voice acquisition module 2, speech processing module 3, language
Sound identification module 4 and output module 5.Starting module 1 is connected with voice acquisition module 2, voice acquisition module 2 and speech processes mould
Block 3 is connected, and speech processing module 3 is connected with sound identification module 4, and sound identification module 4 is connected with output module 5.Start mould
Block 1 is used to detect voice signal and starts voice acquisition module 2；Voice acquisition module 2 is used to gather voice signal.Speech processes
Module 3 includes converting unit 31 and noise reduction unit 32, and converting unit 31 is used to receive the voice letter that voice acquisition module 2 is collected
Number, and analog-to-digital conversion is carried out to the voice signal, noise reduction unit 32 is used to reduce the noise of the voice signal.Speech recognition
Module 4 includes the first recognition unit 42, the second recognition unit 43, memory cell 41, weighting processing unit 44, the first recognition unit
41 are used to the formatted file of the default voice of the voice signal after analog-to-digital conversion and noise reduction and storage carrying out similarity system design,
Draw the default phonetic matrix file similar to voice signal；Second recognition unit 43 is used to receive described similar default voice
Voice signal after formatted file and noise reduction, and the voice signal after the noise reduction is entered to similar default phonetic matrix file
Row compares, and obtains both difference values；Memory cell 41 is used for the set for storing all default voices being compared；Weighting is handled
The difference value that 44 pair of second voice recognition unit of unit is drawn is overlapped with weight variable, draws success value.Output module 5 is used
The result identified in the output sound identification module.
Further, the difference value is compared with default threshold value, if the difference value is less than default threshold value,
Then enter weighting processing unit, otherwise, indicate that the first recognition unit 42, the second recognition unit 43 re-start and compare identification, directly
Untill the difference value of identification is less than default threshold value.The voice acquisition module 3 is converted voice signals into using microphone
Electric signal.Starting module 1 includes detection unit 11 and wakeup unit 12, and detection unit 11 and wakeup unit 12 are connected with each other, and examines
Unit 11 is surveyed for detecting whether there is the signal for starting the voice acquisition module, wakeup unit 12 is used to wake up voice collecting mould
Block.
Described above is the detailed description for the present invention preferably possible embodiments, but embodiment is not limited to this hair
The equal change or modification change completed under bright patent claim, the technical spirit suggested by all present invention, all should belong to
Cover the scope of the claims in the present invention.
Claims (4)
1. a kind of simple speech identifying device, it is characterised in that including including starting module, voice acquisition module, speech processes
Module, sound identification module and output module；
The starting module is connected with the voice acquisition module, and the voice acquisition module is connected with speech processing module, institute
State speech processing module to be connected with the sound identification module, the sound identification module is connected with the output module；
The starting module is used to detect voice signal and starts voice acquisition module；
The voice acquisition module is used to gather voice signal；
The speech processing module includes converting unit and noise reduction unit, and the converting unit is used to receive the voice collecting mould
The voice signal that block is collected, and analog-to-digital conversion is carried out to the voice signal, the noise reduction unit is used to reduce the voice
The noise of signal；
The sound identification module includes the first recognition unit, the second recognition unit, memory cell, weighting processing unit, described
First recognition unit is used to carry out the formatted file of the default voice of the voice signal after analog-to-digital conversion and noise reduction and storage
Similarity system design, draws the default phonetic matrix file similar to voice signal；Second recognition unit is used to receive described
Similar default phonetic matrix file and noise reduction after voice signal, and by the voice signal after the noise reduction to it is similar default
Phonetic matrix file is compared, and obtains both difference values；The memory cell is used to store all default languages being compared
The set of sound；The weighting processing unit is overlapped to the difference value that the second voice recognition unit is drawn with weight variable, is obtained
Go out success value；
The output module is used to export the result that the sound identification module is identified.
2. simple speech identifying device according to claim 1, it is characterised in that the difference value is carried out with default threshold value
Compare, if the difference value is less than default threshold value, into weighting processing unit, otherwise, indicate the first recognition unit, the
Two recognition units, which are re-started, compares identification, untill the difference value of identification is less than default threshold value.
3. simple speech identifying device according to claim 1, it is characterised in that the voice acquisition module uses microphone
Convert voice signals into electric signal.
4. simple speech identifying device according to claim 1, it is characterised in that starting module includes detection unit and wake-up
Unit, the detection unit and wakeup unit are connected with each other, and the detection unit is for detecting whether there is the startup voice to adopt
Collect the signal of module, wakeup unit is used to wake up voice acquisition module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710401510.3A CN107170455A (en) | 2017-05-31 | 2017-05-31 | A kind of simple speech identifying device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710401510.3A CN107170455A (en) | 2017-05-31 | 2017-05-31 | A kind of simple speech identifying device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107170455A true CN107170455A (en) | 2017-09-15 |
Family
ID=59821401
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710401510.3A Pending CN107170455A (en) | 2017-05-31 | 2017-05-31 | A kind of simple speech identifying device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107170455A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3456444B2 (en) * | 1999-05-10 | 2003-10-14 | 日本電気株式会社 | Voice determination apparatus and method, and recording medium |
| CN101256769A (en) * | 2008-03-21 | 2008-09-03 | 广州汉音电子科技有限公司 | Speech recognition devices and methods thereof |
| CN201233718Y (en) * | 2008-03-21 | 2009-05-06 | 广州汉音电子科技有限公司 | Speech recognition apparatus |
| CN103956164A (en) * | 2014-05-20 | 2014-07-30 | 苏州思必驰信息科技有限公司 | Voice awakening method and system |
-
2017
- 2017-05-31 CN CN201710401510.3A patent/CN107170455A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3456444B2 (en) * | 1999-05-10 | 2003-10-14 | 日本電気株式会社 | Voice determination apparatus and method, and recording medium |
| CN101256769A (en) * | 2008-03-21 | 2008-09-03 | 广州汉音电子科技有限公司 | Speech recognition devices and methods thereof |
| CN201233718Y (en) * | 2008-03-21 | 2009-05-06 | 广州汉音电子科技有限公司 | Speech recognition apparatus |
| CN103956164A (en) * | 2014-05-20 | 2014-07-30 | 苏州思必驰信息科技有限公司 | Voice awakening method and system |
Non-Patent Citations (2)
| Title |
|---|
| 周小东: "《录音工程师手册（第二版）》", 30 April 2015, 中国广播电视出版社 * |
| 李征宇，付杨，吕双: "《人工智能导论》", 31 December 2016, 哈尔滨工程大学出版社 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3522153B1 (en) | Voice control system, wakeup method and wakeup apparatus therefor, electrical appliance and co-processor | |
| CN105704300A (en) | Voice wakeup detecting device with digital microphone and associated method | |
| CN106971741A (en) | The method and system for the voice de-noising that voice is separated in real time | |
| CN107767863A (en) | voice awakening method, system and intelligent terminal | |
| CN103021411A (en) | Speech control device and speech control method | |
| CN107680229B (en) | The control method of access control system based on phonetic feature and recognition of face | |
| CN103956164A (en) | Voice awakening method and system | |
| CN107452375A (en) | Bluetooth earphone | |
| CN106155621A (en) | The key word voice of recognizable sound source position wakes up system and method and mobile terminal up | |
| CN105182763A (en) | Intelligent remote controller based on voice recognition and realization method thereof | |
| CN108877127B (en) | Forest fire detection method based on image processing | |
| CN111429901A (en) | IoT chip-oriented multi-stage voice intelligent awakening method and system | |
| CN106683676A (en) | Voice recognition system for robot control | |
| CN108447483A (en) | Speech recognition system | |
| CN106612367A (en) | Speech wake method based on microphone and mobile terminal | |
| CN107293299A (en) | It is a kind of to improve the speech recognition alignment system that dispatcher searches drawing efficiency | |
| CN113571053A (en) | Voice wake-up method and device | |
| CN107170455A (en) | A kind of simple speech identifying device | |
| CN116386676B (en) | Voice awakening method, voice awakening device and storage medium | |
| CN208362737U (en) | A kind of electric clothes hanger with voice control system | |
| CN105336330A (en) | Simple voice recognizing system | |
| CN209625783U (en) | Intelligent sound box and smart home system | |
| CN107643908A (en) | Voice application trigger control method, device and terminal | |
| CN206574069U (en) | Intelligent computer main frame | |
| CN205492959U (en) | Adopt fingerprint identification and dual sensor's multi -functional theftproof schoolbag |
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 |
Application publication date: 20170915 |
|
| RJ01 | Rejection of invention patent application after publication |