Paper Info
Title
An Unsupervised Speaker Adaptation Method for Lecture-Style Spontaneous Speech Recognition Using Multiple Recognition Systems
Abstract
This paper describes an accurate unsupervised speaker adaptation method for lecture style spontaneous speech recognition using multiple LVCSR systems. In an unsupervised speaker adaptation framework, the improvement of recognition performance by adapting acoustic models remarkably depends on the accuracy of labels such as phonemes and syllables. Therefore, extraction of the adaptation data guided by confidence measure is effective for unsupervised adaptation. In this paper, we looked for the high confidence portions based on the agreement between two LVCSR systems, adapted acoustic models using the portions attached with high accurate labels, and then improved the recognition accuracy. We applied our method to the Corpus of Spontaneous Japanese (CSJ) and the method improved the recognition rate by about 2.1% in comparison with a traditional method.
Year
DOI
Venue
2005
10.1093/ietisy/e88-d.3.463
IEICE Transactions
Keywords
Field
DocType
adaptation data,traditional method,recognition accuracy,unsupervised adaptation,recognition performance,unsupervised speaker adaptation framework,acoustic model,accurate unsupervised speaker adaptation,confidence measure,unsupervised speaker adaptation method,recognition rate,multiple recognition systems,unsupervised speaker adap- tation,multiple lvcsr models,lvcsr system,traditional method. key words: spontaneous speech recognition,lecture-style spontaneous speech recognition
Pattern recognition,Computer science,Speech recognition,Speaker recognition,Natural language processing,Speaker diarisation,Artificial intelligence,Speaker adaptation
Journal
Volume
Issue
ISSN
E88-D
3
1745-1361
Citations 
PageRank 
References 
2
0.37
8
Authors
4
Name
Order
Citations
PageRank
Seiichi Nakagawa1598104.03
Tomohiro Watanabe2132.20
Hiromitsu Nishizaki316329.49
takehito utsuro445682.76