论文信息 - The ELISA consortium approaches in speaker segmentation during the NIST 2002 speaker recognition evaluation

The ELISA consortium approaches in speaker segmentation during the NIST 2002 speaker recognition evaluation

This paper presents the ELISA consortium activities in automatic speaker segmentation during last NIST 2002 evaluation: two different approaches from CLIPS and LIA laboratories are presented and the possibility of combining them either by applying them consecutively, or by fusing the decisions made by each of them, is investigated. Various types of data were available for NIST 2002. The ELISA systems obtained the lower error rates for two corpora: the CLIPS system obtained the best performance on the Meeting data, the LIA system obtained the best performance on the Switchboard data. The combining strategies proposed in this paper allowed us to improve the performance of the best single system on both data types (up to 30 % of error rate reduction).

[1] Douglas A. Reynolds,et al. Blind clustering of speech utterances based on speaker and language characteristics , 1998, ICSLP.

[2] Christian Wellekens,et al. DISTBIC: A speaker-based segmentation for audio data indexing , 2000, Speech Commun..

[3] Jean-François Bonastre,et al. AMIRAL: A Block-Segmental Multirecognizer Architecture for Automatic Speaker Recognition , 2000, Digit. Signal Process..

[4] Guillaume Gravier,et al. Overview of the 2000-2001 ELISA Consortium research activities , 2001, Odyssey.

[5] Jean-François Bonastre,et al. E-HMM approach for learning and adapting sound models for speaker indexing , 2001, Odyssey.

[6] Sylvain Meignier,et al. Speaker utterances tying among speaker segmented audio documents using hierarchical classification: towards speaker indexing of audio databases , 2002, INTERSPEECH.