Issues in acoustic modeling of speech for automatic speech recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports (Research Report) Year : 1994

Issues in acoustic modeling of speech for automatic speech recognition

Yifan Gong
  • Function : Author
Jean-Paul Haton
  • Function : Author
  • PersonId : 830987
Jean-François Mari
  • Function : Author
  • PersonId : 1202580

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.

Domains

Other [cs.OH]
Fichier principal
Vignette du fichier
RR-2368.pdf (222.95 Ko) Télécharger le fichier

Dates and versions

inria-00074309 , version 1 (24-05-2006)

Identifiers

  • HAL Id : inria-00074309 , version 1

Cite

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⟩
77 View
119 Download

Share

Gmail Facebook Twitter LinkedIn More