Communication method, apparatus and system based on voiceprint

Patent metadata

Field	Value
Publication number	US-9865267-B2
Application number	US-201514962711-A
Country	US
Kind code	B2
Filing date	Dec 8, 2015
Priority date	Jun 30, 2015
Publication date	Jan 9, 2018
Grant date	Jan 9, 2018

Abstract

The present disclosure relates to a communication method, apparatus and system based on a voiceprint. The communication method based on the voiceprint includes: sending first information to a sever and receiving identification information sent from the server, in which the identification information is generated after the server receives the first information and the first information is one of user account information and speech information; and sending second information and the identification information to the server, in which the second information is the other one of the user account information and the speech information.

First claim

What is claimed is:

1. A communication method based on a voiceprint, comprising:
sending first information to a sever and receiving identification information sent from the server, the identification information being generated after the server receives the first information and the first information is speech information; and
sending second information and the identification information to the server, the second information being user account information, and the second information being different from the first information,
performing, by the server, a registration or verification based on an association between the first and second information according to the identification information.

2. The method according to claim 1 , the identification information being generated randomly.

3. A communication method based on a voiceprint, comprising:
receiving first information sent from a client, generating identification information and sending the identification information to the client, the first information being speech information; and
receiving second information and the identification information sent from the client, the second information being user account information, and the second information being different from the first information; associating the first information with the second information according to the identification; and,
performing a registration or verification according to the associated first and second information.

4. The method according to claim 3 , when registering, the speech information being speech data configured as a training sample and the training sample being configured for a voiceprint training to obtain voiceprint characteristic information, and the method further comprises:
training the speech data configured as the training sample to obtain the voiceprint characteristic information after receiving the speech data configured as the training sample;
storing the identification information and the voiceprint characteristic information in correspondence to each other; and
finding the voiceprint characteristic information corresponding to the identification information from pre-stored data after receiving the user account information and the identification information, and storing the received user account information and the found voiceprint characteristic information in correspondence to each other to obtain a registration result.

5. The method according to claim 3 , when verifying, the speech information being speech data to be verified, and the method further comprises:
storing the identification information and the speech data to be verified in correspondence to each other after receiving the speech data to be verified and generating the identification information; and
finding the speech data to be verified corresponding to the identification information from pre-stored data after receiving the user account information and the identification information, and obtaining a verification result according to the received user account information, the found speech data to be verified as well as the user account information and the voiceprint characteristic information obtained when registering.

6. The method according to claim 3 , generating identification information comprising:
generating the identification information randomly.

7. A communication apparatus based on a voiceprint, comprising:
a processor; and
a memory for storing instructions executable by the processor;
the processor being configured to:
send first information to a sever and receive identification information sent from the server, the identification information being generated after the server receives the first information and the first information being speech information; and
send second information and the identification information to the server, the second information being user account information, and the second information being different from the first information;
the first information being associated with the second information according to the identification information in the server, and the associated first and second information being used by the server to perform a registration or verification.

8. The apparatus according to claim 7 , the identification information being generated randomly.

9. A communication apparatus based on a voiceprint, comprising:
a processor; and
a memory for storing instructions executable by the processor;
the processor being configured to:
receive first information sent from a client, generate identification information and send the identification information to the client, the first information being speech information; and
receive second information and the identification information sent from the client, the second information being user account information, and the second information being different from the first information;
associate the first information with the second information according to the identification; and,
perform a registration or verification according to the associated first and second information.

10. The apparatus according to claim 9 , when registering, the speech information being speech data configured as a training sample and the training sample being configured for a voiceprint training to obtain voiceprint characteristic information, and the processor being further configured to:
train the speech data configured as the training sample to obtain the voiceprint characteristic information after receiving the speech data configured as the training sample;
store the identification information and the voiceprint characteristic information in correspondence to each other; and
find the voiceprint characteristic information corresponding to the identification information from pre-stored data after receiving the user account information and the identification information, and store the received user account information and the found voiceprint characteristic information in correspondence to each other to obtain a registration result.

11. The apparatus according to claim 9 , when verifying, the speech information being speech data to be verified, and the processor being further configured to:
store the identification information and the speech data to be verified in correspondence to each other after receiving the speech data to be verified and generating the identification information; and
find the speech data to be verified corresponding to the identification information from pre-stored data after receiving the user account information and the identification information, and obtain a verification result according to the received user account information, the found speech data to be verified as well as the user account information and the voiceprint characteristic information obtained when registering.

12. The apparatus according to claim 9 , the processor generating identification information by:
generating the identification information randomly.

Assignees

• Baidu online network technology beijing co ltd

Inventors

• Du Niandong
• Li Chao
• Xie Yan

Classifications

• G06F21/31

  User authentication · CPC title

• G10L17/24 Primary

  the user being prompted to utter a password or a predefined phrase · CPC title

• G06F21/32

  using biometric data, e.g. fingerprints, iris scans or voiceprints · CPC title

• H04L63/0861 Primary

  using biometrical features, e.g. fingerprint, retina-scan (cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231) · CPC title

• H04L63/083

  using passwords (cryptographic mechanisms or cryptographic arrangements for entity authentication using a predetermined code H04L9/3226) · CPC title