Une nouvelle architecture de compensation du bruit pour la reconnaissance robuste de la parole - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2004

Une nouvelle architecture de compensation du bruit pour la reconnaissance robuste de la parole

Abstract

We present a novel noise compensation architecture which makes no assumptions on how the noise sources alter the speech data and which do not rely on clean speech models. Rather, this new architecture makes the (realistic) assumption that speech databases recorded under different background noise conditions are available. Its main principle is to process individually each database and to construct a parametric representation which describes the variation of acoustic models w.r.t. noise models. This representation is then used during recognition to estimate the acoustic models in the new environment. We evaluate the performance of this new compensation scheme on a connected digits recognition task and show that it can perform significantly better than multi-conditions training, which is the most widely used technique in these kind of scenarios.
Fichier principal
Vignette du fichier
A04-R-100.pdf (233.19 Ko) Télécharger le fichier
Loading...

Dates and versions

inria-00107784 , version 1 (19-10-2006)

Identifiers

  • HAL Id : inria-00107784 , version 1

Cite

Khalid Daoudi, Murat Deviren. Une nouvelle architecture de compensation du bruit pour la reconnaissance robuste de la parole. XXVes Journées d'Etudes sur la Parole - JEP-TALN-RECITAL 2004, 2004, Fès, Maroc, 4 p. ⟨inria-00107784⟩
68 View
67 Download

Share

Gmail Facebook Twitter LinkedIn More