A new approach for multi-band speech recognition based on probabilistic graphical models

Khalid Daoudi 1 Dominique Fohr 1 Christophe Antoine
1 PAROLE - Analysis, perception and recognition of speech
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : In this paper, we introduce a new approach for multi-band speech recognition which allows interaction between sub-bands and does not require a recombination step. Moreover, this approach is a natural generalization of the HMMs paradigm and leads to fast learning and recognition algorithms.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/inria-00099058
Contributor : Publications Loria <>
Submitted on : Tuesday, September 26, 2006 - 8:49:06 AM
Last modification on : Thursday, January 11, 2018 - 6:19:57 AM
Long-term archiving on: Wednesday, March 29, 2017 - 12:42:57 PM

Identifiers

  • HAL Id : inria-00099058, version 1

Collections

Citation

Khalid Daoudi, Dominique Fohr, Christophe Antoine. A new approach for multi-band speech recognition based on probabilistic graphical models. ICSLP, Oct 2000, Beijing, China, 4 p. ⟨inria-00099058⟩

Share

Metrics

Record views

261

Files downloads

107