Voiceprint recognition method and system based on communication system

Abstract

The invention provides a method for identifying the voiceprint based on the communication system. The steps are following: (a) receiving the voice information of the user; (b) automatically collecting the voice information of the user to extract the user voiceprint information and storing the user voiceprint information as the valid confirmed information of the user; (c) comparing the received voice information of the user to the valid confirmed information of the user and making a evaluating value for the comparing result and storing the evaluating value; (d) comparing the evaluating value to the set threshold value to obtain a result whether the user is valid; (e) processing the authorized service for the valid user. The invention uses the voiceprint mould program to extract the user model; the method for identifying the voiceprint is simple and precise, which can effectively stop the influence by the noise with different channel and different background in different communication way. The invention also discloses a system for identifying the voiceprint based on the communication system.

Description

technical field [0001] The invention relates to the technology of using voice signal as identification, in particular to a technology of voiceprint recognition based on communication system. Background technique [0002] In the telecommunications industry, it is required to provide 24-hour telephone customer service, and provide various authorization services such as business suspension, business recovery, fee inquiry, account transfer, and credit card authorization to customers in need at any time. The current service mode is generally that the customer service personnel ask the user's name, ID number, reserved password and other information on the phone as the basis for confirming the legal identity of the user. However, such information is often easily understood or deciphered by people (including relatives, colleagues, friends, etc.) Institutions have caused commercial disputes and loss of reputation. [0003] At present, most of the mobile phone voiceprint cryptograph...

AI Technical Summary

Problems solved by technology

[0005] (1) The influence of noise is not considered

The input speech is usually accompanied by a certain amount of environmental noise, and the types of noise in different speaking places are also different, which adds difficulty to speaker recognition

[0006] (2) Does not consider the impact of cross-channel

The user must say a paragraph according to the specified text content, which will bring some inconvenience to the user and easily lead to password leakage

[0008] (4) The implementation system is relatively complex, and has high requirements for hardware performance, which is basically in the laboratory stage

[0009] (5) The function of providing various services at any time according to the needs of customers has not yet been realized, such as the functions of business suspension, business recovery, fee inquiry, account transfer, credit card authorization, etc.

[0010] (6) Only a single communication method is realized, such as a mobile phone or a fixed telephone, etc., and all the communication methods used are not combined to achieve

Images