Audio-visual speech translation with automatic LIP synchronization and face tracking based on 3-D head model

Shigeo Morishima, Shin Ogata, Kazumasa Murai, Satoshi Nakamura

Research output: Contribution to journalConference article

9 Citations (Scopus)

Abstract

Speech-to-speech translation has been studied to realize natural human communication beyond language barriers. Toward further multi-modal natural communication, visual information such as face and lip movements will be necessary. In this paper, we introduce a multi-modal English-to-Japanese and Japanese-to-English translation system that also translates the speaker's speech motion while synchronizing it to the translated speech. To retain the speaker's facial expression, we substitute only the speech organ's image with the synthesized one, which is made by a three-dimensional wire-frame model that is adaptable to any speaker. Our approach enables image synthesis and translation with an extremely small database. We conduct subjective evaluation by connected digit discrimination using data with and without audio-visual lip-synchronicity. The results confirm the sufficient quality of the proposed audio-visual translation system.

Original languageEnglish
Pages (from-to)II/2117-II/2120
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2
Publication statusPublished - 2002 Jul 11
Event2002 IEEE International Conference on Acoustic, Speech and Signal Processing - Orlando, FL, United States
Duration: 2002 May 132002 May 17

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Audio-visual speech translation with automatic LIP synchronization and face tracking based on 3-D head model'. Together they form a unique fingerprint.

  • Cite this