Towards a Global Optimization Scheme for Multi-Band Speech Recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 1999

Towards a Global Optimization Scheme for Multi-Band Speech Recognition

Abstract

n this paper, we deal with a new method to globally optimize a Multi-Band Speech Recognition (MBSR) system. We have tested our algorithm with the TIMIT database and obtained a significant improvement in the accuracy over a basic HMM system for clean speech. The goal of this work is not to prove the effectiveness of MBSR, what has yet been done, but to improve the training scheme by introducing a global optimization procedure. A consequence of this method is that the models are no longer phone-models, but define new classes in the phonetic space which might better model the acoustic information carried by each band.
Fichier principal
Vignette du fichier
99-R-326.pdf (50.41 Ko) Télécharger le fichier
Loading...

Dates and versions

inria-00107822 , version 1 (19-10-2006)

Identifiers

  • HAL Id : inria-00107822 , version 1

Cite

Christophe Cerisara, Jean-Paul Haton, Dominique Fohr. Towards a Global Optimization Scheme for Multi-Band Speech Recognition. 6th European Conference on Speech Communication & Technology - EUROSPEECH'99, 1999, Budapest, Hungary, 4 p. ⟨inria-00107822⟩
226 View
60 Download

Share

Gmail Facebook Twitter LinkedIn More