Summary of the invention
The object of the present invention is to provide a kind of data communication system and method based on Application on Voiceprint Recognition, the successful pairing of the vocal print feature by voice, realizes between communication equipment fast, simple data communication.
For addressing the above problem, the invention provides a kind of data communication system based on Application on Voiceprint Recognition, comprise the communication equipment of data receiver and data receiver's communication equipment, wherein,
The communication equipment of described data receiver comprises:
The first voice acquisition module, for gathering voice;
The first vocal print characteristic extracting module, for extracting the vocal print feature of described voice, generates the first vocal print authentication message bag;
The first data communication module, the list of obtaining all data receivers' communication equipment within the scope of a predeterminable range for described data receiver, sends described the first vocal print authentication message bag and target data;
Described data receiver's communication equipment comprises:
The second voice acquisition module, for gathering described voice;
The second vocal print characteristic extracting module, for extracting the vocal print feature of described voice, generates the second vocal print authentication message bag;
Vocal print characteristic matching module, for carrying out the vocal print feature pairing of the voiceprint message bag of described the first vocal print authentication message bag and described second;
The second data communication module for receiving described the first vocal print authentication message bag, and receives described target data after the successful matching of described vocal print feature.
Further, the first vocal print characteristic extracting module and/or described the second vocal print characteristic extracting module are used Mel frequency cepstral coefficient to extract the vocal print feature of described voice.
Further, the process that the first vocal print characteristic extracting module and/or described the second vocal print characteristic extracting module are extracted the vocal print feature of described voice comprises:
First, described voice are processed by a high pass filter, abandoned high-frequency signal, be only the MFCC of low frequency, be convenient to the voiceprint of described voice to analyze;
Then, by Mel frequency filter group, described voice are carried out to smoothing processing;
Then, the voice data of described voice is done to the logarithm process of Mel parameter to compress the dynamic range of the voice data of described voice, and the property the taken advantage of composition in the frequency domain of described voice is become and adds type composition, to remove multiplicative noise;
Afterwards, the voice data after removal multiplicative noise is done to discrete cosine transform and ask cepstrum, its result is as the vocal print feature of described voice.
Further, described the first vocal print authentication message bag comprises: vocal print feature and the acquisition time of the information of the communication equipment of described data receiver and address, described voice.
Further, described the second vocal print authentication message bag comprises: vocal print feature and the acquisition time of the information of described data receiver's communication equipment and address, described voice.
Further, described the first data communication module obtains the list of all data receivers' communication equipment within the scope of predeterminable range by least one in LBS server, WIFI, 3G and bluetooth.
Further, described the first data communication module sends described the first vocal print authentication message bag and target data by least one in WIFI, 3G and bluetooth.
Further, described the second data communication module receives described the first vocal print authentication message bag and described target data by least one in WIFI, 3G and bluetooth.
Accordingly, the present invention also provides a kind of method of applying the above-mentioned data communication system based on Application on Voiceprint Recognition, the operation that comprises data receiver and data receiver's operation, wherein,
The operation of described data receiver comprises:
In the communication equipment of described data receiver selection data receiver, need the target data sending;
Described data receiver is sent voice and is gathered described voice by described the first voice acquisition module;
Described data receiver is extracted the vocal print feature of described voice by described the first vocal print characteristic extracting module, generate the first vocal print authentication message bag;
The list that described data receiver is obtained all data receivers' communication equipment within the scope of described predeterminable range by described the first data communication module, and send described target data and described the first vocal print authentication message bag to the communication equipment of at least one data receiver in described list;
Described data receiver's operation, comprising:
Described data receiver gathers described voice by described the second voice acquisition module when described data receiver is sent voice;
Described data receiver extracts the vocal print feature of described voice by described the second vocal print characteristic extracting module, generate the second vocal print authentication message bag;
Described data receiving receives described the first vocal print authentication message bag by described data communication module;
The vocal print feature that described data receiving is undertaken in described the first vocal print authentication message bag and described the second vocal print authentication message bag by described vocal print characteristic matching module is matched;
If the successful matching of described vocal print feature, the communication connection of described the second data communication module foundation and described the first data communication module, and receive described target data; If described vocal print feature is matched unsuccessfully, the communication connection of described the second data communication module refusal foundation and described the first data communication module, this data communication finishes.
Compared with prior art, data communication system and the method based on Application on Voiceprint Recognition provided by the invention, on the one hand, is used vocal print to authenticate, and more quick than traditional mode authenticating by password, interactive experience is convenient, easy-to-use; On the other hand, a communication equipment once can, simultaneously to many communication equipment transmission data of matching by vocal print, improve the interactive experience of transfer of data further.
Embodiment
The data communication system based on Application on Voiceprint Recognition and the method that the present invention are proposed below in conjunction with the drawings and specific embodiments are described in further detail.
As shown in Figure 1, the invention provides a kind of data communication system based on Application on Voiceprint Recognition, comprise the communication equipment 10 of data receiver and data receiver's communication equipment 20, wherein
The communication equipment 10 of described data receiver comprises:
The first voice acquisition module 11, for gathering voice;
The first vocal print characteristic extracting module 12, for extracting the vocal print feature of described voice, generates the first vocal print authentication message bag;
The first data communication module 13, the list of obtaining all data receivers' communication equipment within the scope of predeterminable range for described data receiver, sends described the first vocal print authentication message bag and target data;
Described data receiver's communication equipment 20 comprises:
The second voice acquisition module 21, for gathering described voice;
The second vocal print characteristic extracting module 22, for extracting the vocal print feature of described voice, generates the second vocal print authentication message bag;
Vocal print characteristic matching module 23, for carrying out the vocal print feature pairing of the voiceprint message bag of described the first vocal print authentication message bag and described second;
The second data communication module 24 for receiving described the first vocal print authentication message bag, and receives described target data after the successful matching of described vocal print feature.
Further, described the first vocal print authentication message bag comprises vocal print feature and the acquisition time of the information of communication equipment of described data receiver and address, described voice; Described the second vocal print authentication message bag comprises vocal print feature and the acquisition time of described data receiver's the information of communication equipment and address, described voice.
Further, described the first data communication module obtains the list of all data receivers' communication equipment within the scope of predeterminable range by least one in LBS server, WIFI, 3G and bluetooth, by least one in WIFI, 3G and bluetooth, sends described the first vocal print authentication message bag and target data; Described the second data communication module receives described the first vocal print authentication message bag and described target data by least one in WIFI, 3G and bluetooth.
Accordingly, the present invention also provides a kind of method of applying the above-mentioned data communication system based on Application on Voiceprint Recognition, the operation that comprises data receiver and data receiver's operation, and wherein, as shown in Figure 2, the operation of described data receiver comprises S10 to S15 step; Described data receiver's operation comprises S20 to S23 step and S24a or S24b step.Below in conjunction with accompanying drawing 1 and accompanying drawing 2, introduce in detail the method for the above-mentioned data communication system based on Application on Voiceprint Recognition of application.
As shown in Figure 2, the operation of described data receiver comprises the following steps:
Step S10, needs the target data sending in the communication equipment of described data receiver selection data receiver.
In this step, the target data in the communication equipment 10 of the data receiver of selection includes but not limited to text, address list, calendar and mail.
Step S11, described data receiver is sent voice.
In this step, the voice that send can be any voice, such as the sound of the voice of speaking, machinery, even clap hands, the sound that the action such as applause is sent.
Step S12, described data receiver gathers described voice by described the first voice acquisition module.
Please refer to Fig. 1, in step S12, described the first voice acquisition module 11 becomes digital signal by described speech conversion.Preferably, by described digital signal unloading in the SRAM storage chip of the communication equipment 10 of data receiver, for subsequent module for processing (seeing step S13 and step S23).
Step S13, described data receiver is extracted the vocal print feature of described voice by described the first vocal print characteristic extracting module, generate the first vocal print authentication message bag.
Please refer to Fig. 1, the voice that described the first vocal print characteristic extracting module 12 gathers described the first voice acquisition module 11 carry out vocal print feature extraction, generate the first vocal print authentication information bag, for vocal print pairing afterwards.
In the present embodiment, described the first vocal print characteristic extracting module 12 is obtained the voice of collection from SRAM storage chip, uses Mel frequency cepstral coefficient, i.e. MFCC (Mel Frequency Cestrum coefficient).MFCC calculates by each frame of voice, and its leaching process is as follows: first, described voice are processed by a high pass filter, abandoned high-frequency signal, be only the MFCC of low frequency, be convenient to the voiceprint of described voice to analyze; Then, by Mel frequency filter group, described voice are carried out to smoothing processing; Then, the voice data of described voice is done to the logarithm process of Mel parameter to compress the dynamic range of the voice data of described voice, and the property the taken advantage of composition in the frequency domain of described voice is become and adds type composition, to remove multiplicative noise; Afterwards, to removing voice data after multiplicative noise, do discrete cosine transform and ask cepstrum, its result is as the vocal print feature of described voice, and for after vocal print pairing.
Step S14, the list that described data receiver is obtained all data receivers' communication equipment within the scope of a predeterminable range by described the first data communication module.
Please refer to Fig. 1, in step S14, the communication equipment that need to carry out data communication puts together while starting, be the communication equipment 10 of data receiver and data receiver's communication equipment 20, spacing distance is between the two unsuitable long, can be a predeterminable range, with this, can guarantee that described the first data communication module 13 can obtain the list of all data receivers' that need to carry out data communication communication equipment.
Step S15, described data receiver selects the communication equipment of at least one data receiver in described list as data receiver, by described the first data communication module, sends described target data and described the first vocal print authentication message bag.
Please refer to Fig. 1, described data receiver can be selected the communication equipment of one or more data receivers in described list, by described the first data communication module 13, sends described target data and described the first vocal print authentication message bag.
As shown in Figure 2, described data receiver's operation comprises:
Step S20, described data receiver gathers described voice by described the second voice acquisition module when described data receiver is sent voice.
Please refer to Fig. 1, in this step, need to carry out the communication equipment of data communication, be the communication equipment 10 of data receiver and data receiver's communication equipment 20, during beginning, put together, spacing distance is unsuitable long, it can be a predeterminable range, the voice acquisition module that can guarantee to carry out in the communication equipment of data communication with this can both collect described voice, though the second voice acquisition module 21 of communication equipment 20 of data receiver also can collect this voice when described data receiver is sent voice.
Step S21, described data receiver extracts the vocal print feature of described voice by described the second vocal print characteristic extracting module, generate the second vocal print authentication message bag.
Please refer to Fig. 1, the voice that described the second vocal print characteristic extracting module 22 gathers described the second voice acquisition module 21 carry out vocal print feature extraction, generate the second vocal print authentication information bag, for vocal print pairing afterwards., described the second vocal print characteristic extracting module 22 also can be used Mel frequency cepstral coefficient to extract the vocal print feature of described voice, and leaching process is with described the first vocal print characteristic extracting module 12.
Step S22, described data receiver receives described the first vocal print authentication message bag by described the second data communication module.
Please refer to Fig. 1, described data receiver receives described the first vocal print authentication message bag by the second data communication module 24.
Step S23, described data receiving matches the vocal print feature in the vocal print feature in described the first vocal print authentication message bag receiving and described the second vocal print authentication message bag by described vocal print characteristic matching module.
Please refer to Fig. 1, the vocal print feature in the second vocal print authentication message bag that described data receiver's vocal print characteristic matching module 23 generates the second vocal print characteristic extracting module 22 according to the acquisition time of described voice and the vocal print feature in described the first vocal print authentication message bag are matched.
Step S24a, if successful matching, the communication connection of described the second data communication module 24 foundation and described the first data communication module 13, receives described target data; Step S24b, if matched unsuccessfully, described the second data communication module 24 refusal set up with the communication connection of the first data communication module 13, this data communication finishes.
In sum, data communication system and the method based on Application on Voiceprint Recognition provided by the invention, on the one hand, is used vocal print to authenticate, and more quick than traditional mode authenticating by password, interactive experience is convenient, easy-to-use; On the other hand, communication equipment needs and when other or many communication equipments transmission data, only these communication equipments need be placed in together, be placed within the scope of predeterminable range, and send voice, after the finger print information of these voice successfully matches in these communication equipments, these communication equipments are connected and will set up with the data communication of data receiver equipment room, target data will send to the communication equipment of all successful matchings afterwards, improves further the interactive experience of transfer of data.
Obviously, those skilled in the art can carry out various changes and modification and not depart from the spirit and scope of the present invention invention.Like this, if within of the present invention these are revised and modification belongs to the scope of the claims in the present invention and equivalent technologies thereof, the present invention is also intended to comprise these changes and modification interior.