1st International ICST Conference on Communications and Networking in China

Research Article

Mouth Shape Sequence Recognition Based on Speech Phoneme Recognition

  • @INPROCEEDINGS{10.1109/CHINACOM.2006.344672,
        author={Ming  Xu and Ruimin  Hu},
        title={Mouth Shape Sequence Recognition Based on Speech Phoneme Recognition},
        proceedings={1st International ICST Conference on Communications and Networking in China},
        publisher={IEEE},
        proceedings_a={CHINACOM},
        year={2007},
        month={4},
        keywords={Mouth shape recognition Speech recognition Triphone modeling Viseme},
        doi={10.1109/CHINACOM.2006.344672}
    }
    
  • Ming Xu
    Ruimin Hu
    Year: 2007
    Mouth Shape Sequence Recognition Based on Speech Phoneme Recognition
    CHINACOM
    IEEE
    DOI: 10.1109/CHINACOM.2006.344672
Ming Xu1,2,*, Ruimin Hu3,4,*
  • 1: Information Center of Shenzhen University, Shenzhen,
  • 2: Guangdong Province,China
  • 3: Computer Science Institute of Wuhan University, Wuhan,
  • 4: Hubei Province,China
*Contact email: xuming@szu.edu.cn, hrm@public.wh.hb.cn

Abstract

As part of the effort to realize human face cartoon automatic synthesization, we explored the mouth shape sequence recognition techniques for continuous natural speech. In this paper we introduce such a method based on speech phoneme recognition. The method consists of five major parts, namely, triphone modeling, search space organization, Viterbi searching, speech phoneme recognition, and path tracking back. At the end of this paper, outputs of such a system are illustrated.