Speaker recognition method based on semantic cell mixing model

Abstract

The invention discloses a speaker recognition method based on a semantic cell mixing model. The method comprises the following steps: (1) establishing a voice library, wherein the voice library comprises multiple voice signals of multiple speakers; (2) preprocessing each voice signal in the voice library, extracting the voice characteristics, thereby obtaining each feature vector of each person; (3) performing dimensionality reduction on the feature vector so as to obtain a dimensionality reduction feature vector based on a semantic cell feature selection method, and training the semantic cell mixing model; (4) constructing an SVM classifier of each speaker by using a kernel function based on the semantic cell mixing model, and training a recognition model of the SVM classifier; and (5) recognizing the unknown speaker by utilizing the recognition model. According to the method disclosed by the invention, the problem that the kernel function of the conventional SVM model does not perform targeted optimization on a specific speaker, and when voice features used for a training classifier are selected, the method has high targeting property compared with the conventional common method, and the needed space for storing the model can be reduced.

Description

technical field [0001] The invention relates to the fields of signal processing and pattern recognition, in particular to a speaker recognition method based on a semantic cell mixed model. Background technique [0002] Speaker Recognition, also known as speaker recognition, refers to the process of automatically determining whether the speaker is in the registered speaker set and identifying the specific speaker by performing feature extraction and other analysis on the speech signal generated by the unknown speaker. . Since the shape and size of individual vocal tracts, larynx, and other generating organs vary, the speech characteristics of any two individuals are different (see Kinnunen T, Li H. An overview of text-independent speaker recognition: from features to supervectors. Speech communication, 2010, 52(1):12-40.). This technology can be used in processes that need to identify operators, such as telephone banking, voice access control, and telephone shopping. [00...

AI Technical Summary

Problems solved by technology

The disadvantage of this invention is that the dimensionality reduction of the feature vectors is carried out from the statistical point of view by using the principal component analysis method, and the pertinence is not strong

In addition, this invention uses the semantic cell mixture model as the recognition model of the classifier, and the accuracy of the method is limited when it is used for speaker recognition

Images