System and method for identifying voice prints based on phoneme information

Abstract

The invention relates to a system and a method for identifying voice prints based on phoneme information. The system comprises a phoneme forced aligning module, a phoneme relevance model creating module and a neural network classifier module, wherein the phoneme forced aligning module is based on a Chinese mandarin voice identifier; the neural network classifier module is based on a dropout strategy. The method comprises the following steps of defining sixteen phoneme types of Chinese mandarin numeric string voice prints, and digitally utilizing each piece of pronunciation type information of a numeric string; according to the Chinese mandarin voice identifier, using a viterbi forced aligning algorithm to obtain the phoneme boundary of the text content of each numeric string; using a text irrelevance algorithm to establish a phoneme relevance model; calculating the phoneme relevance model, so as to obtain a fraction vector. The system and the method have the advantages that the functions of division of phoneme information, modeling of phonemes and analysis of distinguishing capability of the phoneme relevance model are realized, the neural network training method based on the dropout strategy is proposed, the problem of phoneme missing of the numeric string is solved, and the performance of a numeric string voice print identifying system is improved.

Description

technical field [0001] The invention relates to the technical field of voiceprint authentication systems, in particular to a voiceprint authentication system and method based on phoneme information. Background technique [0002] Biometric identification is a technology to identify the identity based on the inherent physiological and behavioral characteristics of the human body. With the rapid development of the Internet, traditional identity authentication techniques are increasingly unable to meet the needs of users' experience and security capabilities. The simple and easy-to-use voiceprint recognition technology has attracted widespread attention and great attention from all walks of life due to its broad application prospects, huge social and economic benefits. [0003] Voiceprint recognition, also known as speaker recognition, is a kind of biometric technology. This technology identifies the identity of the speaker through the speech parameters that reflect the speake...

AI Technical Summary

Problems solved by technology

[0013] The purpose of the present invention is to propose a voiceprint authentication system and method based on phoneme information, which can solve the problem of digital cross-phoneme while realizing phoneme information segmentation, phoneme modeling and phoneme-related (Phone-dependent) model discrimination ability analysis. missing issues and improved the performance of the digital serial voiceprint authentication system

Images