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)

1 TEXMEX - Multimedia content-based indexing
2 METISS - Speech and sound data modeling and processing

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.

Domains: Sound [cs.SD]

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⟩