Consolidation based speech translation

Chiori Hori, Bing Zhao, Stephan Vogel, Alex Waibel

Research output: Contribution to conferencePaper

1 Citation (Scopus)

Abstract

To alleviate the degradation of the performance of speech translation, this paper proposes a new approach to translate ASR results through consolidation which extracts meaningful phrases and remove redundant and irrelevant information caused by speaker's disfluency and recognition errors. The speech translation results via consolidation are partial translation and can not be directly compared with gold standards in which all words are translated. We would like to propose a new evaluation framework for partial translation by comparing with the most similar set of words extracted from a word network created by merging gradual summarization of the gold standard translation. Chinese broadcast news speech in RT04 were recognized, consolidated and then translated. The performance of MT results was evaluated using BLEU. We propose Information Preservation Accuracy (IPAccy) and Meaning Preservation Accuracy (MPAccy) for consolidation and consolidation-based MT.

Original languageEnglish
Pages380-385
Number of pages6
Publication statusPublished - 1 Dec 2007
Event2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007 - Kyoto, Japan
Duration: 9 Dec 200713 Dec 2007

Other

Other2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007
CountryJapan
CityKyoto
Period9/12/0713/12/07

    Fingerprint

Keywords

  • Chinese broadcast news speech
  • Chinese-English translation
  • Machine translation
  • Speech consolidation

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Software
  • Artificial Intelligence

Cite this

Hori, C., Zhao, B., Vogel, S., & Waibel, A. (2007). Consolidation based speech translation. 380-385. Paper presented at 2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007, Kyoto, Japan.