Improved speech recognition word lattice translation by confidence measure

Abdulvohid Bozarov, Yoshinori Sagisaka, Ruiqiang Zhang, Genichiro Kikui

Research output: Contribution to conferencePaper

3 Citations (Scopus)

Abstract

In conventional speech translation systems, Automatic Speech Recognition (ASR) produces a single hypothesis which is then translated by the SMT system. The translation results of SMT system are impaired by the word errors of the first best hypothesis in this approach more or less. To improve speech translation, we use a new word lattice translation approach which integrates multiple information sources from the speech recognition word lattice to discount the misrecognition. Furthermore, in order to improve speech translation and to reduce computation, we used N-bests cutoff, merging of identical word ids, and confidence measure. Experiments of Japanese-to-English speech translation showed that the proposed word lattice translation outperforms the conventional single best method.

Original languageEnglish
Pages3197-3200
Number of pages4
Publication statusPublished - 2005 Dec 1
Event9th European Conference on Speech Communication and Technology - Lisbon, Portugal
Duration: 2005 Sep 42005 Sep 8

Conference

Conference9th European Conference on Speech Communication and Technology
CountryPortugal
CityLisbon
Period05/9/405/9/8

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'Improved speech recognition word lattice translation by confidence measure'. Together they form a unique fingerprint.

  • Cite this

    Bozarov, A., Sagisaka, Y., Zhang, R., & Kikui, G. (2005). Improved speech recognition word lattice translation by confidence measure. 3197-3200. Paper presented at 9th European Conference on Speech Communication and Technology, Lisbon, Portugal.