Skip to Main content Skip to Navigation
Reports

Issues in acoustic modeling of speech for automatic speech recognition

Abstract : Stochastic modeling is a flexible method for handling the large variability in speech for recognition applications. In contrast to dynamic time warping where heuristic training methods for estimating word templates are used, stochastic modeling allows a probabilistic and automatic training for estimating models. This paper deals with the improvement of stochastic techniques, especially for a better representation of time varying phenomena.
Complete list of metadatas

https://hal.inria.fr/inria-00074309
Contributor : Rapport de Recherche Inria <>
Submitted on : Wednesday, May 24, 2006 - 3:01:40 PM
Last modification on : Saturday, September 17, 2016 - 1:06:53 AM
Document(s) archivé(s) le : Sunday, April 4, 2010 - 9:45:07 PM

Identifiers

  • HAL Id : inria-00074309, version 1

Collections

Citation

Yifan Gong, Jean-Paul Haton, Jean-François Mari. Issues in acoustic modeling of speech for automatic speech recognition. [Research Report] RR-2368, INRIA. 1994. ⟨inria-00074309⟩

Share

Metrics

Record views

181

Files downloads

220