Speaker-Consistent Parsing for Speaker-Independent Continuous Speech Recognition

Kouichi YAMAGUCHI, Harald SINGER, Shoichi MATSUNAGA, Shigeki SAGAYAMA

Summary :

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 uttered 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.

• Publication: IEICE TRANSACTIONS on Information Vol.E78-D No.6 pp.719-724
• Publication Date: 1995/06/25
• Type of Manuscript: Special Section PAPER (Special Issue on Spoken Language Processing)

Authors

Kouichi YAMAGUCHI
Harald SINGER
Shoichi MATSUNAGA
Shigeki SAGAYAMA

Keyword

speech recognition,  search algorithm,  hidden Markov model,  speaker adaptation