Method for identifying speaker unrelated to text based on weighted Bayes mixture model

Abstract

The invention discloses a method for identifying a speaker unrelated to text based on a weighted Bayes mixture model. The method comprises that a voice signal set used for training is pre-processed and feature of the voice signal set is extracted, the training set is described via the weighted Bayes mixture model in the training process, parameter values and random variable distribution in the weighted Bayes mixture model are estimated via training, and thus, the weighted Bayes mixture model corresponding to each speaker is obtained. During identification, the marginal likelihood values of the trained weighted Bayes mixture models corresponding to the speakers are calculated via identification voices after preprocessing and feature extraction, and the maximal marginal likelihood corresponding to the speaker is used as an identification result. The method can effectively improve the correct identification rate of a text-related speaker identification system, avoids the problems of over-fitting and under-fitting that tend to occur in a traditional method, and enable that the relative weight of prior information and training data is easier and more flexible to control.

Description

technical field [0001] The invention relates to a text-independent speaker recognition method based on a weighted Bayesian mixture model, which belongs to the technical field of speech signal processing. Background technique [0002] Speaker recognition plays an increasingly important role in access control, credit card transactions, and court evidence. Its goal is to correctly determine the speech to be recognized as belonging to one of the multiple reference persons in the speech library. [0003] Currently, in the text-independent speaker recognition methods, the method based on Gaussian mixture model (ie: GMM) is the most widely used. Because of its advantages of high recognition rate, simple training, and small requirement for training data, it has become the mainstream method for speaker recognition that has nothing to do with text. Since GMM has a good ability to represent the distribution of data, as long as there are enough states and enough training data, GMM can ...

AI Technical Summary

Problems solved by technology

First of all, the traditional GMM training process is based on the maximum likelihood criterion, which is prone to overfitting or underfitting to the training data.

Second, traditional GMM-based text-independent speaker recognition only considers observational data without introducing prior information

The above problems often make the recognition accuracy of the traditional GMM-based text-independent speaker recognition system low

Images