E-HMM approach for learning and adapting sound models for speaker indexing

Sylvain Meignier (1) , Jean-François Bonastre (1) , S. Igounet (1)

1 LIA - Laboratoire Informatique d'Avignon

This paper presents an iterative process for blind speaker indexing based on a HMM. This process detects and adds speakers one after the other to the evolutive HMM (E-HMM).The use of this HMM approach takes advantage of the different components of AMIRAL automatic speaker recognition system (ASR system: frontend processing, learning, loglikelihood ratio computing) from LIA. The proposed solution reduces the miss detection of short utterances by exploiting all the information (detected speakers) as soon as it is available. The proposed system was tested on N-speaker segmentation task of NIST 2001 evaluation campaign. Experiments were carried out to validate thoce speakers detection. Moreover, these tests measure the influence of parameters used for speaker models learning.

Domaines: Informatique et langage [cs.CL]

Sylvain Meignier, Jean-François Bonastre, S. Igounet. E-HMM approach for learning and adapting sound models for speaker indexing. ISCA, A Speaker Odyssey, The Speaker Recognition Workshop, 2001, Chiana (Crete), Greece. pp.5. ⟨hal-01434656⟩