Online speaking people cluster analysis method based on bayesian information criterion

Abstract

The invention relates to the online speaking people cluster analysis and particularly relates to the online speaking people cluster analysis based on bayesian information criterion. The method comprises steps of collecting original audio signals and dividing the original audio signals into audio segments with boundaries through the bayesian information criterion, performing audio characteristic extraction on the audio segments, clustering the segments with audio characteristics through the bayesian information criterion, and forming a plurality of clustering groups like the clustering group 1, clustering group 2....clustering group n. An online speaking people cluster analysis system comprises two modules which are an audio signal segmentation module and a segment cluster analysis module, which greatly improve the accuracy of segmentation, guarantee high efficiency of clustering, realize high efficient parallel transcription, segmentation, classification and clustering of signals of the online speaking people on a premise that the audio materials of the original speaking people are not required and realize high efficiency transcription, segmentation, classification and clustering of the signals of online speaker.

Description

technical field [0001] The invention relates to online speaker cluster analysis, in particular to an online speaker cluster analysis method based on Bayesian information criterion. Background technique [0002] Online speaker clustering analysis is the process of dividing and clustering the pronunciations of multiple speakers in scenes such as podcast news, conference calls, and movie clips. Sounds are given the same label, and it does not focus on the semantic content in the speech signal, but needs to mine the personality differences between speakers from the pronunciation of each speaker. Throughout the analysis process, the continuous audio signal is segmented as a preprocessing process for further speaker recognition, authentication, noise removal and background sound separation. In systems such as automatic transcription applications, this segmentation process allows the use of acoustic models of speakers, channels, or specific environments to improve the system's rec...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to address the defects and insufficiencies of the prior art, and provide an online speaking system based on Bayesian information criteria that can solve the problems of dynamic segmentation and efficient classification and aggregation of audio signals in the speaker clustering analysis process.

Images