Summary of the invention
Technology of the present invention is dealt with problems and is: overcome the deficiencies in the prior art, a kind of Bluetooth system unlocking with vocal print and wake up is provided, by Application on Voiceprint Recognition, the speech recognition system in Bluetooth system is unlocked and waken up, the function with voice waken system can be realized, handled easily, Application on Voiceprint Recognition also can realize identity confirmation simultaneously, thus prevents other people usurping and false wake-up as coded lock.
The technology of the present invention solution: a kind ofly to unlock and the Bluetooth system that wakes up with vocal print, comprising: audio frequency net gate way (AG) and hands-free kits (HF) containing two modules, i.e. AG module and HF module; HF module comprises wake module and sound identification module;
The effect of described wake module allows user wake speech identifying function up by phonetic order, carries out bluetooth connection by phonetic order, realizes calling, operating address book function; Described wake module comprises main control unit 1, for gathering the voice collecting unit 2 of user speech, A/D converter 3 and vocal print recognition unit 4; Voice collecting unit 2 output one tunnel is directly connected with an input of the main control unit 1 treating Rouser, and another road is connected with another input of main control unit 1 by A/D converter 3, Application on Voiceprint Recognition unit 4 successively; The output of main control unit 1 is connected with sound identification module input respectively, the analoging sound signal of input is converted to digital signal by A/D converter 3, Application on Voiceprint Recognition unit mates the digital signal received, and matching result is sent to main control unit 1;
Described main control unit 1 receives the wake-up signal of voice collecting unit and vocal print recognition unit, can wake sound identification module up after receiving the wake-up signal of two unit at the same time, carries out speech recognition process;
Described Application on Voiceprint Recognition unit 4 carries out training and identify two processes; Namely training process collects the voice of specifying user, and extracts the voiceprint in its voice, as password; Namely identifying receives the voice of speaker, extracts the voiceprint in voice, voiceprint and the voiceprint as password is compared, if the match is successful, exports wake-up signal;
Sound identification module is after system is waken up, and receives the phonetic order of user, and the Word message identified is sent to AG module by bluetooth;
AG module performs corresponding instruction after receiving Word message.
Described voice collecting unit 2 is made up of the microphone for gathering user speech, audio frequency amplifier and comparator; The output of microphone is connected with the input of audio frequency amplifier, and the output of audio frequency amplifier is connected with the output of comparator with A/D converter 3 respectively; The audio signal that microphone exports is amplified by audio frequency amplifier; Comparator has the threshold values of setting, this threshold values regulates according to distinct device, varying environment, when the input voltage of comparator and the voice signal of microphone conversion are higher than threshold values, then the output of comparator exports wake-up signal, Application on Voiceprint Recognition unit can identify the audio signal received and identity validation simultaneously, if by authentication, then also export wake-up signal, main control unit 1 is waken up after receiving the wake-up signal of comparator and voiceprint identification module simultaneously.
The present invention's advantage is compared with prior art:
(1) can realize being with the voice of speech recognition Bluetooth system to wake up, do not need key wakeup, full voice operates, easily.
(2) Application on Voiceprint Recognition can be carried out authentication thus be avoided being usurped or false wake-up by other people.
Embodiment
As shown in Figure 1, the present invention includes: audio frequency net gate way (AG) and hands-free kits (HF) containing two modules, i.e. AG module and HF module; HF module comprises wake module and sound identification module;
The effect of wake module allows user wake speech identifying function up by phonetic order, carries out bluetooth connection, realizes calling, operating address book function by phonetic order; Wake module comprises main control unit 1, for gathering the voice collecting unit 2 of user speech, A/D converter 3 and vocal print recognition unit 4; For gathering the voice collecting unit 2 of user speech, its output one tunnel is directly connected with the input of the main control unit 1 treating Rouser, another road is connected with the input of main control unit 1 by A/D converter 3, Application on Voiceprint Recognition unit 4 successively, the input of the output sound identification module 3 of main control unit 1 is connected, as shown in Figure 1.The analoging sound signal of input is converted to digital signal by AD converter 3, and outputs to main control unit 1 by Application on Voiceprint Recognition unit 4.
As shown in Figure 1, main control unit 1 is waken up after receiving the wake-up signal of comparator and voiceprint identification module simultaneously.Can carry out after waking up operating with sound identification module.
As shown in Figure 2, wake module implementation procedure of the present invention is as follows:
(1) voice collecting unit 2 is made up of the microphone for gathering user speech, audio frequency amplifier and comparator, the output of microphone is connected with the input of audio frequency amplifier, and the output of audio frequency amplifier is connected with the output of comparator with A/D converter 3 respectively.
(2) audio signal that microphone exports is amplified by audio frequency amplifier.
(3) comparator has specific threshold values, and this threshold values can regulate according to distinct device, varying environment, and when the input voltage of comparator and the voice signal of microphone conversion are higher than threshold values, then the output of comparator exports wake-up signal.
(4) Application on Voiceprint Recognition unit can identify the audio signal received and identity validation simultaneously, if by authentication, then also export wake-up signal.
(5) main control unit 1 is waken up after receiving the wake-up signal of comparator and vocal print recognition unit simultaneously.Can carry out after waking up operating with sound identification module.
As shown in Figure 3, Application on Voiceprint Recognition unit implementation procedure of the present invention is as follows: Application on Voiceprint Recognition need in advance in identification module stored in the voiceprint of nominator as key, this process is called training process.It the process nature identified is the process that the voiceprint of the voice received by input is compared with the voiceprint prestored and mated.
Training process:
(1) specify speaker to speak to voice collecting unit, content of speaking is random, and voice signal can be sent to voiceprint identification module by voice collecting unit.
(2) voiceprint identification module extracts the voiceprint of voice signal, preserves as key.
Identifying:
(1) speaker speaks facing to voice collecting unit, and content of speaking is random, and voice signal is sent to voiceprint identification module by voice collecting unit;
(2) voiceprint identification module extracts the voiceprint of voice signal, and compares with the vocal print key preserved in advance;
(3) and if cipher key match, then by Application on Voiceprint Recognition, export wake-up signal;
(4) if do not mated with key, then wake-up signal is not exported.
As shown in Figure 4, for voice dial telephony feature, illustrate that sound identification module of the present invention realizes as follows:
(1) user is by after vocal print waken system (vocal print wakeup process describes in detail later), and system can carry out bluetooth connection to HF and AG.
(2) after connection completes, it is synchronous that system can carry out telephone directory, by Bluetooth transmission, the telephone directory that AG holds downloaded to HF end.The object done like this is to build contact identification network.
(3) speech recognition network is built.Speech recognition network is divided into two parts: contact identification network and everyday words recognition network.Everyday words identification is the identification of order word, comprising: call, hangs up, answer, rejection etc.Speech recognition process is the extraction characteristic information of voice and compares with the information in recognition network, mates and the process of obtaining a result.
(4) after speech recognition network struction completes, the recording of phonetic order user sent is sent into speech recognition network and is identified.Such as user says " phoning XXX ", and system can identify order word and " phone " in everyday words recognition network, and in contact identification network, identify name of contact person " XXX ", thus obtains complete recognition result and " phone XXX ".
Step (3) and step (4) complete by sound identification module.
(5) Word message identified is connected by the bluetooth set up and is sent to AG end by HF, and it is corresponding command information that AG end receives transcription after Word message, and performs instruction, calls to XXX.
Can realize answering of incoming call in the same way, rejection, hangs up.
In a word, the present invention is unlocked by Application on Voiceprint Recognition the speech recognition system in Bluetooth system and wakes up, can realize the function with voice waken system, handled easily, Application on Voiceprint Recognition also can realize identity confirmation simultaneously, thus prevents other people usurping and false wake-up as coded lock.