CN105070291A - Sound control door system based on dynamic time warping technology - Google Patents
Sound control door system based on dynamic time warping technology Download PDFInfo
- Publication number
- CN105070291A CN105070291A CN201510429081.1A CN201510429081A CN105070291A CN 105070291 A CN105070291 A CN 105070291A CN 201510429081 A CN201510429081 A CN 201510429081A CN 105070291 A CN105070291 A CN 105070291A
- Authority
- CN
- China
- Prior art keywords
- signal
- door
- time warping
- dynamic time
- sound
- 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
Landscapes
- Operating, Guiding And Securing Of Roll- Type Closing Members (AREA)
- Lock And Its Accessories (AREA)
Abstract
The invention relates to a sound control door system based on dynamic time warping technology. The sound control door system comprises a sound acquisition module for sound acquisition; the sound acquisition module transmits acquired sound signals to a voice recognition system; the voice recognition system sends a recognition result to a digital signal processing system; the digital signal processing system outputs a door opening signal to an unlocking system; and after the unlocking system receives the signal, an electromagnet generates magnetic attraction, power is provided for an electrical door of a door opening and closing system, and the door opening and closing system opens and closes the door. Huge convenience is brought to life of people, and when the person is inconvenient to use a key to unlock the door, the door can be unlocked only via sound, and great effects can be realized for busy white-collar workers, people with mobility impairments and people who forget to bring keys.
Description
Technical field
The invention belongs to acoustic control product technical field, particularly a kind of Acoustic controlled door system based on dynamic time warping technology.
Background technology
People open the door only by manual mode, all there is inconvenient situation under many circumstances, need a kind of switch of aut.eq. control gate, will bring great convenience to the life of people like this.At present, speech recognition technology is through the research of whole world over half a century, develop into the practical stage, utilize speech recognition system that the voice signal of people is become a kind of command transfer in signal processing system, after being converted into electric signal wherein, electric signal is accepted by unlocking apparatus, implement unlocking action to become possibility, particularly based on the isolated-word speech recognition system under dynamic time warping technology (DTW), quite complete, therefore develop a kind of Acoustic controlled door based on dynamic time warping technology and will seem very necessary.
Summary of the invention
The object of the invention is for the deficiencies in the prior art, and propose a kind of Acoustic controlled door system based on dynamic time warping technology.
The present invention solves its technical matters and takes following technical scheme to realize:
A kind of Acoustic controlled door system based on dynamic time warping technology, this system comprises the sound acquisition module for sound collection, the voice signal collected is passed to speech recognition system by sound acquisition module, recognition result is sent to digital information processing system by speech recognition system, digital information processing system exports enabling signal to unlocking system, and after unlocking system receives signal, electromagnet produces magnetic attraction, for the motor of shutter door system powers up, shutter door system completes shutter door action
Wherein, described sound acquisition module adopts conventional acoustic pickup to complete sound collection;
Wherein, described speech recognition system, includes:
(1) pretreatment module: the primary speech signal of input is processed, filters out ground unrest, the end-point detection of lang tone signal of going forward side by side, voice framing and pre-emphasis process;
(2) characteristic extracting module: the acoustical characteristic parameters calculating voice, extracts the key feature vector parameters of reflected signal feature;
(3) training stage: user inputs several times training utterance, after pre-service and feature extraction, obtain character vector, set up or revise the reference model storehouse of training utterance;
(4) cognitive phase: the voice of input extraction character vector is carried out similarity measurement with the pattern in reference model storehouse and compares, and draw final recognition result in conjunction with certain decision rule;
Wherein, described digital information processing system, include further connect successively pre-filtering, A/D converter, digital signal processing unit, D/A converter and smothing filtering, input signal is after pre-filtering, by A/D converter, simulating signal is changed into digital signal, digital signal exports to D/A converter according to after certain algorithm process, then obtains continuous print simulating signal through smothing filtering;
Wherein, unlocking system is conventional electromagnet line system, when digital information processing system exports the signal opened the door, electromagnet circuit will close automatically, for the motor of shutter door system powers up, equally, after digital information processing system exports the signal of closing the door, after door is completely closed, electromagnet circuit will disconnect automatically, thus door is shut;
Wherein, described shutter door system is made up of motor-operated lever group.
And the acoustical characteristic parameters of voice comprises: one or more in linear prediction (PLP) parameter of linear prediction (LPC) parameter, line spectrum pair (LSP) parameter, linear prediction residue error (LPCC), mel cepstrum coefficients (MFCC), the responsive scale coefficient (ASCC) of accent, perceptual weighting, dynamic difference parameter and higher order signal spectrum category feature.
And described decision rule is specially word-building rule and syntax rule.
And wherein, described digital signal is specially DTW algorithm process according to certain algorithm process.
And; this system also includes security system further; security system gathers the current value of motor in shutter door system; judge whether motor transships by the size of current value; once there is current overload security system will send signal; cut off motor power, reaching protected circuit can not by the object of burning.
Advantage of the present invention and good effect are:
The present invention can bring huge convenience for the life of people, from social perspective, the rhythm of life of modern people is more and more faster, when people are not easy to use key to go to realize unblanking, just door lock can be opened by means of only sound, the white collars busy to those, for the people of action obstacle, have huge effect for the situation leaving behind key.
Accompanying drawing explanation
Fig. 1 is the function structure chart of present system;
Fig. 2 is the function structure chart of speech recognition system in the present invention;
Fig. 3 is the function structure chart of digital information processing system in the present invention.
Embodiment
Be further described the invention process below, following examples are descriptive, are not determinate, can not limit protection scope of the present invention with this.
A kind of Acoustic controlled door system based on dynamic time warping technology, as shown in Figure 1, this system comprises the sound acquisition module for sound collection, the voice signal collected is passed to speech recognition system by sound acquisition module, recognition result is sent to digital information processing system by speech recognition system, and digital information processing system is connected with unlocking system, shutter door system and security system respectively, sends digital signal and realizes securely unlocking action, complete shutter door function
Wherein, described sound acquisition module adopts conventional acoustic pickup to complete sound collection;
Wherein, described speech recognition system, as shown in Figure 2, includes:
(1) pretreatment module: the primary speech signal of input is processed, filters out ground unrest, the end-point detection of lang tone signal of going forward side by side, voice framing and pre-emphasis process;
(2) characteristic extracting module: the acoustical characteristic parameters calculating voice, extracts the key feature vector parameters of reflected signal feature;
In specific embodiment of the invention, the acoustical characteristic parameters of voice comprises: one or more in linear prediction (PLP) parameter of linear prediction (LPC) parameter, line spectrum pair (LSP) parameter, linear prediction residue error (LPCC), mel cepstrum coefficients (MFCC), the responsive scale coefficient (ASCC) of accent, perceptual weighting, dynamic difference parameter and higher order signal spectrum category feature;
(3) training stage: user inputs several times training utterance, after pre-service and feature extraction, obtain character vector, set up or revise the reference model storehouse of training utterance;
(4) cognitive phase: the voice of input extraction character vector is carried out similarity measurement with the pattern in reference model storehouse and compares, and draw final recognition result in conjunction with certain decision rule;
Wherein, decision rule is specially word-building rule and syntax rule;
Wherein, described digital information processing system, as shown in Figure 3, include further connect successively pre-filtering, A/D converter, digital signal processing unit, D/A converter and smothing filtering, input signal is after pre-filtering, by A/D converter, simulating signal is changed into digital signal, digital signal exports to D/A converter according to after certain algorithm process, then obtains continuous print simulating signal through smothing filtering;
Wherein, described certain algorithm process is specially DTW algorithm process
Wherein, unlocking system is conventional electromagnet line system, and when digital information processing system exports the signal opened the door, electromagnet circuit will close automatically, produces magnetic force and opens door lock; Equally, after digital information processing system exports the signal of closing the door, after door is completely closed, electromagnet circuit will disconnect automatically, thus door is finally closed;
Wherein, described shutter door system is made up of motor-operated lever group;
Wherein, described security system gathers the current value of motor in shutter door system, judges whether motor transships by the size of current value, once there is current overload security system will send signal; cut off motor power, reaching protected circuit can not by the object of burning.
Claims (5)
1. the Acoustic controlled door system based on dynamic time warping technology, it is characterized in that: this system comprises the sound acquisition module for sound collection, the voice signal collected is passed to speech recognition system by sound acquisition module, recognition result is sent to digital information processing system by speech recognition system, digital information processing system exports enabling signal to unlocking system, after unlocking system receives signal, electromagnet produces magnetic attraction, for the motor of shutter door system powers up, shutter door system completes shutter door action
Wherein, described sound acquisition module adopts conventional acoustic pickup to complete sound collection;
Wherein, described speech recognition system, includes:
(1) pretreatment module: the primary speech signal of input is processed, filters out ground unrest, the end-point detection of lang tone signal of going forward side by side, voice framing and pre-emphasis process;
(2) characteristic extracting module: the acoustical characteristic parameters calculating voice, extracts the key feature vector parameters of reflected signal feature;
(3) training stage: user inputs several times training utterance, after pre-service and feature extraction, obtain character vector, set up or revise the reference model storehouse of training utterance;
(4) cognitive phase: the voice of input extraction character vector is carried out similarity measurement with the pattern in reference model storehouse and compares, and draw final recognition result in conjunction with certain decision rule;
Wherein, described digital information processing system, include further connect successively pre-filtering, A/D converter, digital signal processing unit, D/A converter and smothing filtering, input signal is after pre-filtering, by A/D converter, simulating signal is changed into digital signal, digital signal exports to D/A converter according to after certain algorithm process, then obtains continuous print simulating signal through smothing filtering;
Wherein, unlocking system is conventional electromagnet line system, when digital information processing system exports the signal opened the door, electromagnet circuit will close automatically, for the motor of shutter door system powers up, equally, after digital information processing system exports the signal of closing the door, after door is completely closed, electromagnet circuit will disconnect automatically, thus door is shut;
Wherein, described shutter door system is made up of motor-operated lever group.
2. the Acoustic controlled door system based on dynamic time warping technology according to claim 1, is characterized in that: the acoustical characteristic parameters of voice comprises: one or more in the linear forecasting parameter of linear forecasting parameter, line spectrum pairs parameter, linear prediction residue error, mel cepstrum coefficients, the responsive scale coefficient of accent, perceptual weighting, dynamic difference parameter and higher order signal spectrum category feature.
3. the Acoustic controlled door system based on dynamic time warping technology according to claim 1, is characterized in that: described decision rule is specially word-building rule and syntax rule.
4. the Acoustic controlled door system based on dynamic time warping technology according to claim 1, it is characterized in that: wherein, described digital signal is specially dynamic time warping algorithm process according to certain algorithm process.
5. the Acoustic controlled door system based on dynamic time warping technology according to claim 1; it is characterized in that: this system also includes security system further; security system gathers the current value of motor in shutter door system; judge whether motor transships by the size of current value; once there is current overload security system will send signal; cut off motor power, reaching protected circuit can not by the object of burning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510429081.1A CN105070291A (en) | 2015-07-21 | 2015-07-21 | Sound control door system based on dynamic time warping technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510429081.1A CN105070291A (en) | 2015-07-21 | 2015-07-21 | Sound control door system based on dynamic time warping technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105070291A true CN105070291A (en) | 2015-11-18 |
Family
ID=54499644
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510429081.1A Pending CN105070291A (en) | 2015-07-21 | 2015-07-21 | Sound control door system based on dynamic time warping technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105070291A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105679311A (en) * | 2016-02-03 | 2016-06-15 | 郑州职业技术学院 | Automatic opening single-leaf door |
| CN106639802A (en) * | 2016-06-25 | 2017-05-10 | 佛山市三水金大田门业有限公司 | Voice control door system based on dynamic time warping (DTW) technology |
| CN110379062A (en) * | 2019-07-28 | 2019-10-25 | 李良杰 | Intelligent switch door gear |
| CN111540373A (en) * | 2020-01-12 | 2020-08-14 | 杭州电子科技大学 | City noise identification method based on supercomplex random neural network |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR880002663B1 (en) * | 1985-03-29 | 1988-12-17 | 신석균 | A door system |
| CN2048890U (en) * | 1989-04-22 | 1989-12-06 | 林凯 | Safyty appliance for anti-theft alarm |
| CN1042790A (en) * | 1988-11-16 | 1990-06-06 | 中国科学院声学研究所 | The method and apparatus that the real-time voice of recognizing people and do not recognize people is discerned |
| DE3910879A1 (en) * | 1989-04-04 | 1990-10-11 | Grothe & Soehne Kg A | Door station of a domestic telephone system equipped with voice control |
| CN2067725U (en) * | 1989-04-24 | 1990-12-19 | 山东省惠民县水利水产局 | Automatic opening and closing device for remote-control and-measure of sluice |
| CN104240705A (en) * | 2014-09-24 | 2014-12-24 | 上海伯释信息科技有限公司 | Intelligent voice-recognition locking system for safe box |
-
2015
- 2015-07-21 CN CN201510429081.1A patent/CN105070291A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR880002663B1 (en) * | 1985-03-29 | 1988-12-17 | 신석균 | A door system |
| CN1042790A (en) * | 1988-11-16 | 1990-06-06 | 中国科学院声学研究所 | The method and apparatus that the real-time voice of recognizing people and do not recognize people is discerned |
| DE3910879A1 (en) * | 1989-04-04 | 1990-10-11 | Grothe & Soehne Kg A | Door station of a domestic telephone system equipped with voice control |
| CN2048890U (en) * | 1989-04-22 | 1989-12-06 | 林凯 | Safyty appliance for anti-theft alarm |
| CN2067725U (en) * | 1989-04-24 | 1990-12-19 | 山东省惠民县水利水产局 | Automatic opening and closing device for remote-control and-measure of sluice |
| CN104240705A (en) * | 2014-09-24 | 2014-12-24 | 上海伯释信息科技有限公司 | Intelligent voice-recognition locking system for safe box |
Non-Patent Citations (3)
| Title |
|---|
| 杨明发等: "基于电流与最高温度检测的异步电动机保护研究", 《电力系统保护与控制》 * |
| 罗建锋等: "基于发热-散热积累模型的电动机过载保护研究", 《电力系统保护与控制》 * |
| 胡亚楠: "基于TMS320VC5502的语音门锁系统设计", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105679311A (en) * | 2016-02-03 | 2016-06-15 | 郑州职业技术学院 | Automatic opening single-leaf door |
| CN106639802A (en) * | 2016-06-25 | 2017-05-10 | 佛山市三水金大田门业有限公司 | Voice control door system based on dynamic time warping (DTW) technology |
| CN110379062A (en) * | 2019-07-28 | 2019-10-25 | 李良杰 | Intelligent switch door gear |
| CN111540373A (en) * | 2020-01-12 | 2020-08-14 | 杭州电子科技大学 | City noise identification method based on supercomplex random neural network |
| CN111540373B (en) * | 2020-01-12 | 2022-12-02 | 杭州电子科技大学 | City noise identification method based on supercomplex random neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104123932B (en) | A kind of speech conversion system and method | |
| CN105070291A (en) | Sound control door system based on dynamic time warping technology | |
| Matrouf et al. | Effect of speech transformation on impostor acceptance | |
| CN102324232A (en) | Method for recognizing sound-groove and system based on gauss hybrid models | |
| CN106127896A (en) | A kind of Intelligent door lock control system and method | |
| CN103422764A (en) | Door control system and control method thereof | |
| CN106448654A (en) | Robot speech recognition system and working method thereof | |
| CN103258535A (en) | Identity recognition method and system based on voiceprint recognition | |
| CN103106717A (en) | Intelligent warehouse voice control doorkeeper system based on voiceprint recognition and identity authentication method thereof | |
| CN105845135A (en) | Sound recognition system and method for robot system | |
| CN102509547A (en) | Method and system for voiceprint recognition based on vector quantization based | |
| CN102723078A (en) | Emotion speech recognition method based on natural language comprehension | |
| CN102426835A (en) | Method for identifying local discharge signals of switchboard based on support vector machine model | |
| CN1941080A (en) | Soundwave discriminating unlocking module and unlocking method for interactive device at gate of building | |
| CN110956965A (en) | Personalized intelligent home safety control system and method based on voiceprint recognition | |
| CN109243492A (en) | A kind of speech emotion recognition system and recognition methods | |
| CN107134277A (en) | A kind of voice-activation detecting method based on GMM model | |
| Al-Kaltakchi et al. | Comparison of I-vector and GMM-UBM approaches to speaker identification with TIMIT and NIST 2008 databases in challenging environments | |
| CN205680160U (en) | A kind of Intelligent door lock control system | |
| CN108172220A (en) | A kind of novel voice denoising method | |
| CN105679323A (en) | Number finding method and system | |
| Verma | Multi-feature fusion for closed set text independent speaker identification | |
| CN109544745A (en) | A kind of intelligent door lock control method, apparatus and system | |
| CN105909118A (en) | Acoustic control electrically-operated gate type shower room | |
| CN107393539A (en) | A kind of sound cipher control method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151118 |
|
| RJ01 | Rejection of invention patent application after publication |