Browse by author
Lookup NU author(s): Tao Chen
Full text for this publication is not currently held within this repository. Alternative links are provided below where available.
This paper addresses accent1 issues in large vocabulary continuous speech recognition. Cross-accent experiments show that the accent problem is very dominant in speech recognition. Analysis based on multivariate statistical tools (principal component analysis and independent component analysis) confirms that accent is one of the key factors in speaker variability. Considering different applications, we proposed two methods for accent adaptation. When a certain amount of adaptation data was available, pronunciation dictionary modeling was adopted to reduce recognition errors caused by pronunciation mistakes. When a large corpus was collected for each accent type, accent-dependent models were trained and a Gaussian mixture model-based accent identification system was developed for model selection. We report experimental results for the two schemes and verify their efficiency in each situation.
Author(s): Huang C, Chen T, Chang E
Publication type: Article
Publication status: Published
Journal: International Journal of Speech Technology
Year: 2004
Volume: 7
Issue: 2-3
Pages: 141-153
Print publication date: 01/04/2004
ISSN (print): 1381-2416
ISSN (electronic): 1572-8110
Publisher: Springer New York LLC
URL: http://dx.doi.org/10.1023/B:IJST.0000017014.52972.1d
DOI: 10.1023/B:IJST.0000017014.52972.1d
Altmetrics provided by Altmetric
