Towards a Global Optimization Scheme for Multi-Band Speech Recognition

Christophe Cerisara 1 Jean-Paul Haton 1 Dominique Fohr 1
1 PAROLE - Analysis, perception and recognition of speech
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [4 references]  Display  Hide  Download

https://hal.inria.fr/inria-00107822
Contributor : Publications Loria <>
Submitted on : Thursday, October 19, 2006 - 9:10:50 AM
Last modification on : Tuesday, September 24, 2019 - 4:00:12 PM
Long-term archiving on : Wednesday, March 29, 2017 - 1:18:42 PM

Identifiers

  • HAL Id : inria-00107822, version 1

Collections

Citation

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⟩

Share

Metrics

Record views

313

Files downloads

65