Dynamic Gaussian Selection Technique for Speeding Up HMM-Based Continuous Speech Recognition

Jun Cai 1 Ghazi Bouselmi 1 Dominique Fohr 1 Yves Laprie 1
1 PAROLE - Analysis, perception and recognition of speech
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : A fast likelihood computation approach called dynamic Gaussian selection (DGS) is proposed for HMM-based continuous speech recognition. DGS approach is a one-pass search technique which generates a dynamic shortlist of Gaussians for each state during the procedure of likelihood computation. The shortlist consists of the Gaussians which make prominent contribution to the likelihood. In principle, DGS is an extension of the technique of Partial Distance Elimination, and it requires almost no additional memory for the storage of Gaussian shortlists. DGS algorithm has been implemented by modifying the likelihood computation module in HTK 3.4 system. Results from experiments on TIMIT and HIWIRE corpora indicate that this approach can speed up the likelihood computation significantly without introducing apparent additional recognition error.
Complete list of metadatas

https://hal.inria.fr/inria-00327703
Contributor : Dominique Fohr <>
Submitted on : Thursday, October 9, 2008 - 11:46:27 AM
Last modification on : Thursday, January 11, 2018 - 6:19:56 AM

Identifiers

  • HAL Id : inria-00327703, version 1

Collections

Citation

Jun Cai, Ghazi Bouselmi, Dominique Fohr, Yves Laprie. Dynamic Gaussian Selection Technique for Speeding Up HMM-Based Continuous Speech Recognition. ICASSP, Apr 2008, Las Vegas, United States. ⟨inria-00327703⟩

Share

Metrics

Record views

267