L'adaptation thématique d'un modèle de langue fait-elle apparaître des mots thématiques?

Gwénolé Lécorvé 1 Guillaume Gravier 2 Pascale Sébillot 1
1 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
2 METISS - Speech and sound data modeling and processing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : Whereas topic-based adaptation of language models (LM) claims to increase the accuracy of topic-specific words within automatic speech recognition, this paper investigates why this wish is not always verified. After outlining the mechanisms of LM adaptation and automatic speech recognition, diagnosing elements are proposed along with solutions. In addition to a better accuracy on topic-specific words, results show better graph error rates and word error rates on a set of spoken documents with various topics
Complete list of metadatas

Cited literature [7 references]  Display  Hide  Download

https://hal.inria.fr/inria-00555850
Contributor : Valentin Emiya <>
Submitted on : Tuesday, February 15, 2011 - 3:48:29 PM
Last modification on : Friday, November 16, 2018 - 1:23:12 AM
Long-term archiving on : Monday, May 16, 2011 - 2:47:59 AM

File

lecorve10a.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00555850, version 1

Citation

Gwénolé Lécorvé, Guillaume Gravier, Pascale Sébillot. L'adaptation thématique d'un modèle de langue fait-elle apparaître des mots thématiques?. Journées d'Étude sur la Parole, May 2010, Mons, Belgium. ⟨inria-00555850⟩

Share

Metrics

Record views

447

Files downloads

108