CN201947339U - Safe mobile phone based on voice analysis, processing and identification - Google Patents
Safe mobile phone based on voice analysis, processing and identification Download PDFInfo
- Publication number
- CN201947339U CN201947339U CN2010205952272U CN201020595227U CN201947339U CN 201947339 U CN201947339 U CN 201947339U CN 2010205952272 U CN2010205952272 U CN 2010205952272U CN 201020595227 U CN201020595227 U CN 201020595227U CN 201947339 U CN201947339 U CN 201947339U
- Authority
- CN
- China
- Prior art keywords
- module
- mobile phone
- identification
- interface module
- man
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Telephone Function (AREA)
Abstract
The utility model relates to a mobile phone, especially a safe mobile phone based on voice analysis, processing and identification. The mobile phone comprises an LCD display, an indicator light and a keyboard for man-machine conversation. The mobile phone still includes a safe burglary-resisting system, and the system includes a core control system module, a GPRS module and a sound identification module, the core control system module is connected with the GPRS module, the sound identification module, the LCD display and the indicator light and the keyboard for man-machine conversation respectively. The GPRS module consists of a radio frequency interface module, a SIM card interface module and an ARM interface module. Using the voice identification technique to identify ID accurately and reliably, the utility model raises the safety and efficiency of man-machine conversation, ensures the user easy to operate and protects info from lost/ revealed after the mobile phone was stolen. The theft-proof system can also be widely used in various ID identification and safety/ secrecy systems.
Description
Technical field
The utility model relates to a kind of mobile phone, especially a kind of safe mobile phone of handling and discerning based on speech analysis.
Background technology
In the information-intensive society of current high speed development, human physics and dummy activity space are in continuous expansion.Social information's safety problem of thereupon bringing also is being on the increase, and one of them pressing issues just is how accurately to identify a people's identity.At present traditional identity authentication methods such as the identity card that widely uses, IC-card, password exist easily lose, vulnerable and problem such as give away secrets.Therefore, living things feature recognition has become the hot issue of information security field research gradually.
The authentication safe practice of feature that traditional with the password is is converted into the things of differentiating some sign personal identifications usually, comprises key, certificate, ATM sheet, the user name and password or the like.There is significant disadvantages in these traditional identity discrimination methods, and the article that the individual has are lost easily or are forged, and individual's password is forgotten easily or misremembered.Even more serious is, system can't distinguish real owner and obtain the jactitator of identify label thing, in case other people have obtained these identify label things, just can have and the real identical power of owner, be difficult to satisfy the requirement of high security and long-term safety.And based on the feature identification identification of audio frequency be people itself because everyone audio frequency characteristics has the uniqueness different with other people, and constant over a period to come stability, be difficult for being forged and palming off.So the audio frequency characteristics recognition technology that possesses uniqueness has more fail safe than password identification.
The research of speaker's audio identification starts from the thirties in 20th century, and speaker's audio identification has entered a new field after the nineties, and a lot of commercial speaker's audio recognition systems products come out.Domestic speaker's audio identification product has the sharp speaker's audio recognition engine of middle section letter, the Application on Voiceprint Recognition software kit that proud sound is logical etc.But also there be not this information security that is used for mobile phone, burglary-resisting system at present both at home and abroad in conjunction with audio frequency characteristics identification.
The utility model content
The purpose of this utility model has been to propose a kind of safe mobile phone of handling and discerning based on speech analysis.
The utility model is to adopt following technical scheme to realize: a kind of safe mobile phone of handling and discerning based on speech analysis, it comprises LCD demonstration and indicator light, keyboard man-machine interface, wherein, this mobile phone also comprises antitheft security system, this system comprises that core control system module, GPRS module and sound identification module, core control system module are connected with GPRS module, sound identification module, LCD demonstration and indicator light and keyboard man-machine interface respectively, the GPRS module comprises radio frequency interface module, the SIM card interface module and with the ARM interface module.
In the utility model, described radio frequency interface module adopts dual-band antenna.
The SIM card of described SIM interface module and outer handset is connected, and this module can detect and adapt to the SIM card type automatically.
Described ARM interface module adopts the RS-232 serial interface, uses AT to order the operation of finishing module by serial interface.
The beneficial effects of the utility model are: the antitheft security system in the utility model adopts speaker's voice to control, speaker's speech parameter has uniqueness and constant over a period to come stability, therefore utilize speech recognition technology to carry out identification, accurately stable, safe and reliable, improve the efficient of man-machine interaction, user-friendly mobile phone strengthens the control to smart mobile phone; Secondly, antitheft security system has increased the fail safe of mobile phone, prevents information dropout and leakage behind the hand-set from stolen; In addition, this antitheft security system also can be widely applied in various identity authentication and the security system.
Description of drawings
Fig. 1 is a structural representation of the present utility model;
Fig. 2 is the fundamental diagram of sound identification module.
Embodiment
As shown in Figure 1, mobile phone of the present utility model comprises LCD demonstration and indicator light, keyboard man-machine interface and antitheft security system, and wherein antitheft security system comprises core control system module, GPRS module, sound identification module.The core control system module is as the core component of mobile phone, be connected with GPRS module, sound identification module, LCD demonstration and indicator light and keyboard man-machine interface respectively, the embedded developping system that is based on ARM9 that core control system adopts, and under flush type LINUX, utilize speech recognition of C language development and Control Software, be mainly used in and realize specific people's speech recognition, voice operating authority and password setting, mobile phone speech dialing and answer function such as control.The user can check cellphone information by LCD demonstration and indicator light.
The GPRS module comprises radio frequency interface module, the SIM card interface module and with the ARM interface module.Wherein radio frequency interface module adopts dual-band antenna.Direct and the outside SIM card of SIM interface module is connected, and this module can detect and adapt to the SIM card type automatically.The GPRS module is carried out transfer of data by ARM interface module and ARM, and the ARM interface module adopts the RS-232 serial interface of standard, uses AT to order the operation of finishing module by serial interface.
Described sound identification module is mainly used in the input and the identification of voice.The fundamental diagram of this module as shown in Figure 2.After the phonetic entry it is carried out preliminary treatment, the pretreated basis of voice signal is the Mathematical Modeling that voice signal generates, preliminary treatment comprises sampling, removes noise, end-point detection, uses transistor with the adaptive cancellation method, it is steps such as AGC (Automatic Gain Control), preemphasis, branch frame, windowing that automatic gain control is made in linear amplifier chip and the design of AGC integration module, carry out feature extraction through pretreated voice signal, feature extraction is the committed step of speaker's audio recognition systems.After the feature extraction, with Mel frequency cepstral coefficient (Mel Frequency Cepstrum Coefficient, be called for short MFCC) and each differential parameter combine and train and discern as a stack features vector, the static characteristic that had both reflected speech parameter, well describe its dynamic characteristic again, improved the noise robustness of system.Simple multi-template training method is adopted in the reference template training, each time pronunciation that is each word forms a template, in when identification, speech characteristic vector sequence to be identified is tried to achieve accumulative total distortion with each template respectively with specific matching algorithm, differentiates it then which kind of belongs to.Pattern matching adopts gauss hybrid models, promptly each individuality in speaker's set is set up a probabilistic model such as gauss hybrid models, and the parameter in this probabilistic model is the decision that distributes of the characteristic parameter by the speaker, has characterized speaker's identity thus.The process of being obtained the parameter in the probabilistic model by speaker's speech characteristic parameter promptly is described training.Therefore, in fact the process of audio identification is exactly a speaker's speech characteristic parameter and the process that the probabilistic model in speaker's set is complementary.
The keyboard man-machine interface is the user I/O interface of using always, all instructions of user can realize by the keyboard man-machine interface, by the keyboard man-machine interface can realize comprising keyboard initialization, make a phone call, answer the call, short-message sending, check short message, and keyboard operation mode commonly used such as wait.
The utility model realizes that by the training of sound identification module this mobile phone can be realized the speech recognition of 5 different people at most at certain special speaker.After the input of user's voice information, by sound identification module voice messaging is discerned, identifying the speaker is machine master, common user or criminal manipulation person, for different users different rights of using are arranged: if the operating right that the machine master of being identified as can the starting hand-set all functions is identified as then function such as an opening section dialing and note of domestic consumer.When speech recognition is the disabled user, can inform that presetting people's mobile phone is illegally used by the note form.In addition, this mobile phone can be realized the identification of telephone number or name, and validated user only need be said the name of contact person in the number that will dial or the phone directory, can realize dialing of phone, also can utilize voice to realize answering for incoming call simultaneously.Say the network address or the Chinese of the website that needs login by phonetic order, can control system land the website, carry out the voice reading of Internet news.
Because adopting speaker's voice controls, speaker's speech parameter has uniqueness and constant over a period to come stability, therefore utilize speech recognition technology to carry out identification, accurately stable, safe and reliable, improve the efficient of man-machine interaction, user-friendly mobile phone strengthens the control to smart mobile phone; In addition, the fail safe of mobile phone be can also increase, information dropout and leakage behind the hand-set from stolen prevented with this technology.
Claims (4)
1. handle based on speech analysis and the safe mobile phone of identification for one kind, it comprises LCD demonstration and indicator light, keyboard man-machine interface, it is characterized in that: this mobile phone also comprises antitheft security system, this system comprises that core control system module, GPRS module and sound identification module, core control system module are connected with GPRS module, sound identification module, LCD demonstration and indicator light and keyboard man-machine interface respectively, the GPRS module comprises radio frequency interface module, the SIM card interface module and with the ARM interface module.
2. the safe mobile phone of handling and discerning based on speech analysis according to claim 1 is characterized in that: described radio frequency interface module adopts dual-band antenna.
3. the safe mobile phone of handling and discerning based on speech analysis according to claim 1, it is characterized in that: the SIM card of described SIM interface module and outer handset is connected.
4. the safe mobile phone of handling and discerning based on speech analysis according to claim 1 is characterized in that: described ARM interface module adopts the RS-232 serial interface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010205952272U CN201947339U (en) | 2010-11-05 | 2010-11-05 | Safe mobile phone based on voice analysis, processing and identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010205952272U CN201947339U (en) | 2010-11-05 | 2010-11-05 | Safe mobile phone based on voice analysis, processing and identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN201947339U true CN201947339U (en) | 2011-08-24 |
Family
ID=44474673
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010205952272U Expired - Fee Related CN201947339U (en) | 2010-11-05 | 2010-11-05 | Safe mobile phone based on voice analysis, processing and identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN201947339U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104168379A (en) * | 2014-08-20 | 2014-11-26 | 南京工程学院 | Mobile phone anti-theft device based on speech recognition |
-
2010
- 2010-11-05 CN CN2010205952272U patent/CN201947339U/en not_active Expired - Fee Related
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104168379A (en) * | 2014-08-20 | 2014-11-26 | 南京工程学院 | Mobile phone anti-theft device based on speech recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107395352B (en) | Personal identification method and device based on vocal print | |
| WO2017012496A1 (en) | User voiceprint model construction method, apparatus, and system | |
| CN103888581B (en) | A kind of communication terminal and its method for recording call-information | |
| CN103747129B (en) | A kind of Bluetooth system unlocking with vocal print and wake up | |
| CN105141768A (en) | Method and device for multi-user identification and mobile terminal | |
| CN105740686A (en) | Application control method and device | |
| CN102142254A (en) | Voiceprint identification and voice identification-based recording and faking resistant identity confirmation method | |
| CN103310142A (en) | Man-machine fusion security authentication method based on wearable equipment | |
| CN104217152A (en) | Implementation method and device for mobile terminal to enter application program under stand-by state | |
| CN102708867A (en) | Method and system for identifying faked identity by preventing faked recordings based on voiceprint and voice | |
| CN104202455A (en) | Intelligent voice dialing method and intelligent voice dialing device | |
| CN104899582A (en) | Fingerprint identification software and fingerprint identification method therefor | |
| CN102930868A (en) | Identity recognition method and device | |
| CN109272991A (en) | Method, apparatus, equipment and the computer readable storage medium of interactive voice | |
| CN110517696A (en) | A kind of offline Voiceprint Recognition System of implantable | |
| CN103888606A (en) | Mobile terminal and unlocking method thereof | |
| CN109510806A (en) | Method for authenticating and device | |
| CN109994118A (en) | Speech cipher verification method, device, storage medium and computer equipment | |
| CN105160732A (en) | Novel voice-based door control system having warning function | |
| CN104793860A (en) | Intelligent wearing equipment unlocking method, device and watch based on voice recognition | |
| CN201947339U (en) | Safe mobile phone based on voice analysis, processing and identification | |
| CN104427125A (en) | Method and mobile terminal for answering call | |
| CN103995996A (en) | Encryption and decryption method and device based on voice and face biometric feature recognition | |
| CN105007365A (en) | Method and apparatus for dialing extension number | |
| CN205540981U (en) | Support sound wave attendance management and access control system of intelligent Mobile Terminal operation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20110824 Termination date: 20111105 |