Speaker-Consistent Parsing for Speaker-Independent Continuous Speech Recognition

Kouichi YAMAGUCHI  Harald SINGER  Shoichi MATSUNAGA  Shigeki SAGAYAMA  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E78-D   No.6   pp.719-724
Publication Date: 1995/06/25
Online ISSN: 
DOI: 
Print ISSN: 0916-8532
Type of Manuscript: Special Section PAPER (Special Issue on Spoken Language Processing)
Category: 
Keyword: 
speech recognition,  search algorithm,  hidden Markov model,  speaker adaptation,  

Full Text: PDF(558.2KB)
>>Buy this Article


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.