CRF-based Combination of Contextual Features to Improve A Posteriori Word-level Confidence Measures

Julien Fayolle 1 Fabienne Moreau 1, * Christian Raymond 1 Guillaume Gravier 2 Patrick Gros 1
* Corresponding author
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 : This paper addresses the issue of confidence measure reliability provided by automatic speech recognition systems for use in various spoken language processing applications. We propose a method based on conditional random field to combine contextual features to improve word-level confidence measures. The method consists in combining various knowledge sources (acoustic, lexical, linguistic, phonetic and morphosyntactic) to enhance confidence measures, explicitly exploiting context information. Experiments were conducted on a large French broadcast news corpus from the ESTER benchmark. Results demonstrate the added-value of our method with a significant improvement of the normalized cross entropy and of the equal error rate.
Document type :
Conference papers
Complete list of metadatas
https://hal.inria.fr/inria-00561051
Contributor : Patrick Gros <>
Submitted on : Monday, January 31, 2011 - 3:25:32 PM
Last modification on : Friday, November 16, 2018 - 1:23:10 AM

Identifiers

  • HAL Id : inria-00561051, version 1

Collections

CNRS | INRIA | UNIV-RENNES1 | INSA-RENNES | IRISA | IRISA-INSA-R | IRISA-D5 | IRISA-D6 | UR1-UFR-ISTIC | UNIV-RENNES | INSA-GROUPE

Citation

Julien Fayolle, Fabienne Moreau, Christian Raymond, Guillaume Gravier, Patrick Gros. CRF-based Combination of Contextual Features to Improve A Posteriori Word-level Confidence Measures. 11th Annual Conference of the International Speech Communication Association, Interspeech'2010, International Speech Communication Association, Sep 2010, Makuhari, Chiba, Japan. ⟨inria-00561051⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

329

Contact

CCSD