CN102034473B - Personal positioning indicator and information sending method thereof - Google Patents
Personal positioning indicator and information sending method thereof Download PDFInfo
- Publication number
- CN102034473B CN102034473B CN2010106038818A CN201010603881A CN102034473B CN 102034473 B CN102034473 B CN 102034473B CN 2010106038818 A CN2010106038818 A CN 2010106038818A CN 201010603881 A CN201010603881 A CN 201010603881A CN 102034473 B CN102034473 B CN 102034473B
- Authority
- CN
- China
- Prior art keywords
- voice
- module
- information
- orientator
- speaker
- 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.)
- Active
Links
Images
Abstract
The invention relates to a personal positioning indicator, which comprises a microprocessor, a positioning module, a communication module and a voice recognition module. The microprocessor is used for the global control of the positioning indicator. The positioning module is used for determining the position information of the positioning indicator. The communication module is used for allowing the positioning indicator to communicate with the outside. The voice recognition module is used for recognizing voice and sending the position information and other information by the communication module in a preset mode according to according to a voice information and comprises a data storage module, a voice information extraction module and a functional module, wherein the data storage module is used for storing voice vocabularies, voice recognition models and a functional relation table corresponding to the voice state; the voice information extraction module is used for extracting voice characteristics, comparing the voice recognition models in the data storage module, and returning speaker information, voice vocabulary information, voice state information and the functional relation table stored by the data storage module which correspond to voice; and the functional module is used for executing corresponding functions in the table according to the speaker information, the voice vocabulary information, the voice state information and the functional relation table stored by the data storage module which are returned by the voice information extraction module. By adopting the technical scheme, the personal positioning indicator can perform authentication and recognize the voice state automatically by utilizing voice frequency spectra to perform corresponding operation, so the emergency time is reduced; and hardware resources can be saved, the cost can be reduced, and the volume of the personal positioning indicator can be reduced.
Description
Technical field
The present invention relates to a kind of individual orientator and method for sending information thereof, especially utilize speech recognition to realize the individual orientator of operation.
Background technology
Present in the market existing individual orientator, all be to send warning information ﹑ calling, running under accident or the crisis situation, do not have time enough to send and report to the police and the location through button through button.Owing to individual orientator is also found on volume easily, in use all possibly give and prevent simultaneously, so it is more hidden with the minimizing volume how to shorten time of fire alarming, and the economize on hardware resource.
Summary of the invention
The purpose of this invention is to provide a kind of individual orientator that can discern user's identity and can operate according to its relevant voice state.
The present invention is achieved in that a kind of individual orientator, and said orientator comprises, microprocessor is used for the overall situation control of said orientator; Locating module is used for confirming said orientator position information; Communication module is used for said orientator and outside and carries out communication; Said orientator also comprises, sound identification module is used for recognizing voice, and according to voice messaging said positional information and other information is sent through communication module according to preset mode; Said sound identification module comprises, data memory module is used to preserve the pairing functional relationship table of voice vocabulary, speech recognition model and voice status; The voice messaging extraction module is used for phonetic feature and extracts, and compares with the speech recognition model in the said data memory module, returns said voice corresponding speaker information, voice vocabulary information and voice status information; Functional module, the functional relationship table of the speaker information of returning according to said voice messaging extraction module, voice vocabulary information, voice status information and the storage of said data memory module, pairing function in the execution list.
Further, said voice messaging extraction module comprises, pre-processing module and characteristic extracting module, said characteristic extracting module comprise and add form and get sound frame module, pitch characteristic extracting module, resonance peak feature calculation and Mei Er scramble coefficient calculations.
Further, said orientator also comprises voice status identification model training module, through SVMs, trains urgent and normal two kinds of voice status identification models, and stores said identification model to data memory module.
Further, said voice messaging extraction module passes through to extract the amplitude and the frequency of voice, and discerns said voice status information through the amplitude and the frequency of voice.
Further, the threshold value of said amplitude and frequency is respectively 60 decibels and 1850HZ.
Further, said locating module comprises Beidou satellite navigation system receiving module.
The present invention also provides a kind of method for sending information that is used for individual orientator, and said method comprises, pre-treatment step receives voice, extracts said phonetic feature and carries out pre-service; The identification step, identification speaker's identity; The vocabulary identification step, identification speaker's voice vocabulary; The state recognition step, identification speaker's voice status; The information forwarding step is searched pairing function according to above-mentioned recognition result in functional relationship table table, send information to the take over party of setting according to function setting.
After the technical scheme above adopting, individual orientator can utilize sound spectrum to carry out individual orientator authentication, automatically the recognizing voice state; Carry out corresponding operating, reduce the crash time, can save hardware resource simultaneously; Reduce cost, and reduce individual orientator volume, more hidden.This orientator goes for GPS, Beidou satellite navigation system, GLONASS satellite navigation system and other satellite navigation systems.
Description of drawings
Fig. 1 is individual orientator system diagram;
Fig. 2 is the speech processes block diagram;
Fig. 3 implementing procedure of the present invention.
Embodiment
In order to make the object of the invention, technical scheme and advantage clearer,, the present invention is further elaborated below in conjunction with accompanying drawing and embodiment.Should be appreciated that specific embodiment described herein only in order to explanation the present invention, and be not used in qualification the present invention.
Table one is the basic function relation table with individual orientator of speech identifying function of the present invention.Individual's orientator is carried out different functions through identification speaker's identity, voice vocabulary and voice mood grade.
Table part of functions relation table
Specify realization of the present invention below.
Fig. 1 is individual orientator system diagram.Mainly comprise:
Locating module 105 is used for confirming the speaker position, and when orientator receives positioning request signal, locating module carries out position calculation with GPS or Big Dipper mode, and the position data is sent to number or alarm center are set;
Fig. 2 is the speech processes block diagram, method one: mainly be that mood grade separation model set up in speaker's voice, because speaker's phonetic feature has time variation under condition of different, the different voice mood be divided into normal, urgent two kinds of grades record.Speaker's voice signal 201 is received by voice receiver 202, and speech sound signal is done pre-treatment 203, will not have voice or non-voice (noise) part to remove.Carry out feature extraction 204 then; Because phonetic feature has a lot, this device mainly extracts through four aspects, at first adds to look frame and get the discrete-time signal of sound frame 205 with one section voice; Delimit the range of signal of handling with the regular length form; Signal to this scope is done computing, calculates phonetic feature, and form length is generally got 15 ~ 30ms.Secondly; Select for use automatic calibration function (Auto-correction Function, method ACF) is carried out fundamental frequency and is calculated, with selected form translation N point; Then two sound frame laps are done inner product; Find out the maximum point except first point, and be converted into respective frequencies, be pitch 206 phonetic features.Once more, on the frequency spectrum that the fundamental resonance peak value is arranged, get its envelope and draw a spectrum curve, in looking frame, obtain the frequency location of concentration of energy, draw its resonance peak 207.At last, in frequency domain,, obtain frequency band intensity, become cepstrum, be Mei Er scramble coefficient 208 through discrete cosine transform with the Mei Er divided band.(Support Vector Machine SVM) trains normal, urgent two kinds of voice mood identification models 210, and model is carried out the mood grade separation for urgent and normal through SVMs 209 with above four characteristics.
Method two: need not carry out model training to the speaker; Also can pick out mood through voice size (amplitude) and voice height (frequency), the mood grade separation via the boundary value of finding out general and speaker's voice size in emergency circumstances and height after the tone testing repeatedly as distinguishing generalized case and emergency condition.Usually the voice amplitude is 20 ~ 100 decibels and 300 ~ 3400HZ with the scope of frequency.In case of emergency voice size and voice height is high under than normal condition as the speaker; Therefore speech processing module can be set between the two average as the resume module threshold value, also is that the sound amplitude is 60 decibels, and frequency is that 1850HZ is as the software processes boundary; When speech processing module receives speaker's voice; The numerical values recited of extracting amplitude in 5S (judgment standard) voice and frequency height are in addition average again, and the numerical value after average and the boundary value of above setting are done and relatively judged, distinguish speaker's mood grade urgent with normally; But the method can only be distinguished the mood grade roughly, can't discern speaker ' s identity.
Fig. 3 is an implementing procedure of the present invention, and the practical implementation flow process is following:
Speaker's phonetic feature has time variation under different moods, the condition of different mood is divided into normally, and urgent two kinds of grades are recorded.Speaker's voice are preserved in the data module with identification model in emergency circumstances through normal based on speaker's sound after the voice pre-service.Commonly used and individual orientator relative words, in vocabulary such as " help ", " location " preservation data module.With corresponding general calling number under normal, the urgent two kinds of class voices of speaker; Emergency numbers relation table and corresponding difference in functionality operation (like table one); As: " help " carried out with emergency numbers according to the corresponding general number of mood grade and dialed function, and the corresponding transmission of " location " different mood grades locating short message extremely generally relation tables such as number or alarm center deposits data module in.
When voice reception 301 received speaker's voice, voice module extracted phonetic feature in the same way and carries out pre-service 302, and identification model carries out model comparison 303 in the extraction data module, and the speaker is carried out identification 304.
After identification is passed through, obtain the speaker's voice vocabulary 305 and the mood grade 306 of speaking, do function corresponding according to mapping table.Example: when voice receiver receives speaker's voice; Extract carrying out speaker's phonetic feature according to the voice preprocess method, extract data module preservation identification model and compare, carry out identification; Extract vocabulary " help "; Judge that grade is urgent, functional module is obtained emergency numbers according to mapping table and is carried out feature operation 307, dials emergency numbers and reports to the police.
Outgoing call perhaps sends alarming short message, and can set the response time is 5 ~ 10ms.
The locating module of this orientator can be single mode, bimodulus or a multimode positioning system of supporting GPS, Beidou satellite navigation system, GLONASS satellite navigation system and other satellite navigation systems.
The above is merely preferred embodiment of the present invention, not in order to restriction the present invention, all any modifications of within spirit of the present invention and principle, being done, is equal to and replaces and improvement etc., all should be included within protection scope of the present invention.
Claims (4)
1. individual orientator, said orientator comprises, microprocessor is used for the overall situation control of said orientator; Locating module is used for confirming said orientator position information; Communication module is used for said orientator and outside and carries out communication; Sound identification module; Be used for recognizing voice; And according to voice messaging said positional information is passed through communication module with other information according to preset mode and send; Said sound identification module comprises, data memory module is used to preserve the pairing functional relationship table of voice vocabulary, speech recognition model and voice status; Functional module; The functional relationship table of the speaker information of returning according to said voice messaging extraction module, voice vocabulary information, voice status information and the storage of said data memory module, pairing function is characterized in that in the execution list; Said sound identification module also comprises; The voice messaging extraction module through extracting the amplitude and the frequency of voice, and is discerned said voice status information through the amplitude and the frequency of voice; And compare with the speech recognition model in the said data memory module, return said voice corresponding voice vocabulary information and voice status information.
2. orientator as claimed in claim 1 is characterized in that, the threshold value of said amplitude and frequency is respectively 60 decibels and 1850HZ.
3. like claim 1 and 2 described orientators, it is characterized in that said locating module comprises Beidou satellite navigation system receiving module.
4. a method for sending information that is used for individual orientator is characterized in that, said method comprises,
Pre-treatment step receives voice, extracts said phonetic feature and carries out pre-service;
The vocabulary identification step, identification speaker's voice vocabulary;
The state recognition step, the voice status of discerning the speaker through the amplitude and the frequency of voice;
The information forwarding step is searched pairing function according to above-mentioned recognition result in the functional relationship table, send information to the take over party of setting according to function setting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010106038818A CN102034473B (en) | 2010-12-24 | 2010-12-24 | Personal positioning indicator and information sending method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010106038818A CN102034473B (en) | 2010-12-24 | 2010-12-24 | Personal positioning indicator and information sending method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102034473A CN102034473A (en) | 2011-04-27 |
| CN102034473B true CN102034473B (en) | 2012-07-04 |
Family
ID=43887278
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010106038818A Active CN102034473B (en) | 2010-12-24 | 2010-12-24 | Personal positioning indicator and information sending method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102034473B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103281447A (en) * | 2013-05-10 | 2013-09-04 | 金硕澳门离岸商业服务有限公司 | Mobile terminal and mobile terminal positioning method |
| CN106531191A (en) * | 2015-09-10 | 2017-03-22 | 百度在线网络技术（北京）有限公司 | Method and device for providing danger report information |
| CN107888774A (en) * | 2017-11-13 | 2018-04-06 | 平安科技（深圳）有限公司 | A kind of method for seeking help, device, equipment and computer-readable recording medium |
| CN109275132A (en) * | 2018-09-03 | 2019-01-25 | 深圳市物语智联科技有限公司 | The alarm of dress intelligent emergent and rescue system and method after a kind of vehicle |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101004846A (en) * | 2006-01-16 | 2007-07-25 | 中国科学院半导体研究所 | Alarm system and method triggered by specific voice |
| CN1975856B (en) * | 2006-10-30 | 2011-11-09 | 邹采荣 | Speech emotion identifying method based on supporting vector machine |
| CN201431057Y (en) * | 2009-06-26 | 2010-03-31 | 鲍继怀 | Positioning schoolbag dedicated for children |
| CN201553126U (en) * | 2009-07-24 | 2010-08-18 | 谭汉卿 | GPS+GPRS vehicle alarming management system with voice identifying function |
-
2010
- 2010-12-24 CN CN2010106038818A patent/CN102034473B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN102034473A (en) | 2011-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11704397B2 (en) | Detection of replay attack | |
| RU2714805C2 (en) | Method and system of vehicle for performing secret call of an operator of rescue services (embodiments) | |
| CN103095911B (en) | Method and system for finding mobile phone through voice awakening | |
| CN106663430B (en) | Keyword detection for speaker-independent keyword models using user-specified keywords | |
| US9847096B2 (en) | Environment sensing intelligent apparatus | |
| CN107240405B (en) | Sound box and alarm method | |
| US9646610B2 (en) | Method and apparatus for activating a particular wireless communication device to accept speech and/or voice commands using identification data consisting of speech, voice, image recognition | |
| CN104834847B (en) | Auth method and device | |
| US9626962B2 (en) | Method and apparatus for recognizing speech, and method and apparatus for generating noise-speech recognition model | |
| WO2019002831A1 (en) | Detection of replay attack | |
| US8145274B2 (en) | Automatic setting of reminders in telephony using speech recognition | |
| CN102034473B (en) | Personal positioning indicator and information sending method thereof | |
| CN101569093A (en) | Dynamically learning a user's response via user-preferred audio settings in response to different noise environments | |
| CA2635959A1 (en) | Method, system and apparatus for locating a mobile communications device | |
| CN101004846A (en) | Alarm system and method triggered by specific voice | |
| CN103002425A (en) | Method and system for automatically triggering emergency calls and mobile terminal | |
| EP2647189A1 (en) | Method and apparatus for determining location of mobile device | |
| CN101997978A (en) | Mobile terminal operating mode processing method and mobile terminal | |
| CN111028834B (en) | Voice message reminding method and device, server and voice message reminding equipment | |
| CN103514876A (en) | Method and device for eliminating noise and mobile terminal | |
| CN111081275A (en) | Terminal processing method and device based on sound analysis, storage medium and terminal | |
| CN100396133C (en) | Mobile telephone with identity recognition and self-start by listening the environment and its implementation method | |
| US20140162613A1 (en) | Audio Sample | |
| US20110071831A1 (en) | Method and System for Localizing and Authenticating a Person | |
| JP2007172423A (en) | Speech state detecting device and 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 | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C56 | Change in the name or address of the patentee |
Owner name: TAIDOU MICROELECTRONICS TECHNOLOGY CO., LTD. Free format text: FORMER NAME: DONGGUAN TECHTOP MICROELECTRONICS CO., LTD. |
|
| CP01 | Change in the name or title of a patent holder |
Address after: 523070 Dongguan City, Guangdong province south of the New District of the United States on the eastern side of the road east of Dongguan city commercial center, block C, 1212 Patentee after: TECHTOTOP MICROELECTRONICS CO.LTD Address before: 523070 Dongguan City, Guangdong province south of the New District of the United States on the eastern side of the road east of Dongguan city commercial center, block C, 1212 Patentee before: Dongguan Techtop Microelectronics Co., Ltd. |
|
| CB03 | Change of inventor or designer information |
Inventor after: Hu Yaoguang Inventor after: Gao Feng Inventor after: Xu Xiangbin Inventor before: Hu Yaoguang |
|
| CB03 | Change of inventor or designer information | ||
| CP02 | Change in the address of a patent holder |
Address after: 510530 Room 301 and 401, No. 42 Dongzhong Road, East District, Guangzhou Economic and Technological Development Zone, Guangzhou, Guangdong Province Patentee after: TECHTOTOP MICROELECTRONICS CO.LTD Address before: Room A701, No. 11 Color Frequency Road, Science City, Guangzhou High-tech Development Zone Patentee before: TECHTOTOP MICROELECTRONICS CO.LTD |
|
| CP02 | Change in the address of a patent holder |