Séminaire de M. Sethserey Sam, doctorant en co-tutelle du Centre MICA - Date : 25 mars 2010, 14h00 - Lieu : Centre MICA

Intervenant :
Sethserey SAM, jeune enseignant de l'ITC du Cambodge, doctorant en co-tutelle entre le Centre MICA (Hanoi) et le LIG (Grenoble)

Date : 25 mars 2010, 14h00
Lieu : Salle polyvalente du Centre MICA, bat C10, IP de Hanoi, 1 dai co viet.
Interprète traducteur : le séminaire a eu lieu en français

Résumé/Abstract:
We found several challenges in automatic speech transcription system for multilingual meetings. Firstly, the dialog occurs between native and non-native speakers. Secondly, the non-native speakers come from different parts of the world (e.g., English spoken by native French speakers or English spoken by native Vietnamese speakers, etc.). Thirdly, no data or a limited amount of data is available to bootstrap the acoustic modeling.

This seminar presents some autonomous online and offline acoustic model adaptation approaches, which required no additional data in the adaptation process, to deal with above challenges as well as to improve the performance of the phone recognizers used for automatic transcription purpose. To the best of our knowledge, the observer-based approach that we propose has not been studied yet for acoustic model adaptation in multilingual ASR.