Interchange Format-based Language Model for Automatic Speech Recognition in Speech-to-Speech Translation

Abstract : This paper relates a methodology to include some semantic information early in the statistical language model for Automatic Speech Recognition (ASR). This work is done in the framework of a global speech-to-speech translation project. An Interchange Format (IF) based approach, representing the meaning of phrases independently of languages, is adopted. The methodology consists in introducing semantic information by using a class-based statistical language model for which classes directly correspond to IF entries. With this new Language Model, the ASR module can analyze into IF an important amount of dialogue data: 35% dialogue words; 58% speaker turns. Among these 58% turns directly analyzed, 84% are properly analyzed.
Keywords : Speech ASR
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01392520
Contributor : Brigitte Bigi <>
Submitted on : Thursday, November 24, 2016 - 6:28:24 PM
Last modification on : Monday, July 8, 2019 - 3:10:52 PM
Long-term archiving on : Tuesday, March 14, 2017 - 6:00:18 PM

File

bigi2004rivf.pdf
Files produced by the author(s)

Licence


Public Domain

Identifiers

  • HAL Id : hal-01392520, version 1

Citation

Minh Quang Vu, Laurent Besacier, Eric Castelli, Brigitte Bigi, Hervé Blanchon. Interchange Format-based Language Model for Automatic Speech Recognition in Speech-to-Speech Translation. Second international Conference RIVF, 2004, Hanoi, Vietnam. pp.47-50. ⟨hal-01392520⟩

Share

Metrics

Record views

362

Files downloads

66