Hybrid Approach for Unsupervised Audio Speaker SegmentationReport as inadecuate

Hybrid Approach for Unsupervised Audio Speaker Segmentation - Download this document for free, or read online. Document in PDF available to download.

1 Unité de Recherche Signal, Image et Reconnaissance de Formes

Abstract : This paper deals with a new technique, DIS T2 BIC, for audio speaker segmentation when no prior knowledge of speakers is assumed. This technique is based on a hybrid concept which is organized in two steps: the detection of the most probable speaker turns and the validation of turns already detected. For the detection our new technique uses a new distance measure algorithm based on the Hotelling-s T2-Statistic criterion. The validation is obtained by applying the Bayesian Information Criterion BIC segmentation algorithm to the detected speaker turns. For measuring the performance we compare the segmentation results of the proposed method versus recent hybrid techniques. Results show that DIS T2 BIC method has the advantage of high accuracy speaker change detection with a low computation cost.

Author: Hachem Kadri - Zied Lachiri - Noureddine Ellouze -

Source: https://hal.archives-ouvertes.fr/


Related documents