Third International Conference on Spoken Language Processing (ICSLP 94)

Yokohama, Japan
September 18-22, 1994

Speaker-Consistent Parsing for Speaker-Independent Continuous Speech Recognition

Kouichi Yamaguchi (1), Harald Singer (2), Shoichi Matsunaga (2), Shigeki Sagayama (3)

(1) SHARP Corporation, Information Technology Research Labs., Nara, Japan
(2) ATR Interpreting Telecommunications Research Labs., Kyoto, Japan
(3) NTT Human Interface Labs., Yokosuka-shi, Kariagawa, Japan

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.

Full Paper

Bibliographic reference.  Yamaguchi, Kouichi / Singer, Harald / Matsunaga, Shoichi / Sagayama, Shigeki (1994): "Speaker-consistent parsing for speaker-independent continuous speech recognition", In ICSLP-1994, 791-794.