ISCA Archive ICSLP 1994
ISCA Archive ICSLP 1994

Speaker-consistent parsing for speaker-independent continuous speech recognition

Kouichi Yamaguchi, Harald Singer, Shoichi Matsunaga, Shigeki Sagayama

This paper describes a novel speaker-independent speech recognition method, called "speaker-consistent parsing", which is based on an intra-speaker correlation called the speaker-consistency principle. We focus on the fact that a sentence or a string of words is tittered by an individual speaker even in a speaker-independent task. Thus, the proposed method searches through speaker variations in addition to the contents of utterances. As a result of the recognition process, an appropriate standard speaker is selected for speaker adaptation. This new method is experimentally compared with a conventional speaker-independent speech recognition method. Since the speaker-consistency principle best demonstrates its effect with a large number of training and test speakers, a small-scale experiment may not fully exploit this principle. Nevertheless, even the results of our small-scale experiment show that the new method significantly outperforms the conventional method. In addition, this framework's speaker selection mechanism can drastically reduce the likelihood map computation.


Cite as: Yamaguchi, K., Singer, H., Matsunaga, S., Sagayama, S. (1994) Speaker-consistent parsing for speaker-independent continuous speech recognition. Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994), 791-794

@inproceedings{yamaguchi94_icslp,
  author={Kouichi Yamaguchi and Harald Singer and Shoichi Matsunaga and Shigeki Sagayama},
  title={{Speaker-consistent parsing for speaker-independent continuous speech recognition}},
  year=1994,
  booktitle={Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994)},
  pages={791--794}
}