A Novel Method For Speech Segmentation Based On Speakers' Characteristics

TL;DR

This paper introduces a fast speech segmentation method based on pitch frequency, achieving comparable accuracy to BIC-based methods but with significantly reduced computational cost, enhancing speaker diarization efficiency.

Contribution

A new pitch-based speech segmentation technique that improves speed while maintaining accuracy, surpassing traditional BIC-based methods in efficiency.

Findings

Approximately 2.4 times faster than BIC-based segmentation

Achieves similar or slightly higher accuracy than BIC methods

Reduces computational cost significantly

Abstract

Speech Segmentation is the process change point detection for partitioning an input audio stream into regions each of which corresponds to only one audio source or one speaker. One application of this system is in Speaker Diarization systems. There are several methods for speaker segmentation; however, most of the Speaker Diarization Systems use BIC-based Segmentation methods. The main goal of this paper is to propose a new method for speaker segmentation with higher speed than the current methods - e.g. BIC - and acceptable accuracy. Our proposed method is based on the pitch frequency of the speech. The accuracy of this method is similar to the accuracy of common speaker segmentation methods. However, its computation cost is much less than theirs. We show that our method is about 2.4 times faster than the BIC-based method, while the average accuracy of pitch-based method is slightly higher than that of the BIC-based method.