Speaker recognition method based on multi-coordinate sequence kernel and system thereof

Abstract

The invention provides a speaker recognition method based on a multi-coordinate sequence kernel, comprising a training stage and a recognition stage. The method comprises the following steps: in the training stage, preprocessing training voice; extracting a characteristic vector sequence from the preprocessed training voice; selecting an origin of a multi-coordinate system in a characteristic vector space, and mapping the characteristic vector sequence in each coordinate system; selecting an algorithm according to the coordinate system and splicing the vector sequence of each coordinate systeminto a super-vector; determining a super-vector space and a kernel function of a support vector machine (SVM), and training with the SVM algorithm to obtain a trained speaker model; and in the recognition stage, testing the super-vector by the trained model and outputting a decision mark. In the invention, by effective modeling on the voice signal characteristic sequence, the speaker recognitionmethod helps utilize the information contained in high dimensional statistics, reduce computational complexity of an integrated circuit, and improve speaker recognition accuracy and recognition speed.

Description

technical field [0001] The invention relates to the technical fields of speech recognition and pattern recognition, in particular to a speaker recognition method and system based on a support vector machine model of a multi-coordinate sequence kernel. Background technique [0002] Speaker recognition refers to the technology of using machines to determine the identity of the speaker of a given speech signal. According to different recognition tasks, speaker recognition can be divided into two types: speaker confirmation and speaker identification. Speaker confirmation is to judge whether a given voice comes from a given speaker; speaker identification is to use a given voice to find a given speaker in the test library. Speaker recognition technology is mainly used in systems such as security services and humanized services. [0003] Such as figure 1 As shown, it is a basic flowchart of the speaker recognition system based on the spectrum layer in the prior art, including ...

AI Technical Summary

Problems solved by technology

However, the GMM-SVM system does not solve the following two problems: 1) it does not use the information implied by the high-order statistics of the feature sequence; 2) it does not solve the "imbalance" of each dimension of the input space vector of SVM

Images