A fast, accurate and stream-based speaker segmentation and clustering algorithm

Abstract

In this paper a new pre-processor for a free speech transcription system is described. It performs a speech/non-speech partition, a segmentation of the speech parts into speaker turns, and a clusteringofthespeakerturns. Itworksinastream-basedmode, and it is aiming for a high accuracy with a low delay and processing time. Experiments on the Hub4 Broadcast News corpus show thatthenewlyproposedpre-processoriscompetitivewithandin some respects better than the best systems published so far. The paper also describes attempts to raise the system performance by supplementing the standard MFCC features with prosodic features such as pitch and voicing evidence.