Tone variation modeling for fluent Mandarin tone recognition based on clustering
Resource
Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on
Journal
Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on
Pages
-
Date Issued
2004-05
Date
2004-05
Author(s)
Lin, Wan-Yi
DOI
1520-6149
Abstract
Tone recognition for fluent Mandarin speech has always been a very difficult problem, because the complicated tone behavior is difficult to analyze. In this paper, a new method of modeling tone variation for fluent Mandarin tone recognition by clustering training data into few subsets and weighting the likelihood computed by inter-syllabic features (Lin et al. (2003)) is proposed. Experimental results indicate that the tone recognition accuracy can be improved significantly by this method and one modification of the method is robust and has less computation. Our tone variation modeling method is shown to improve the recognition rate from 91.3% to 95.2%.
SDGs
Type
journal article
File(s)![Thumbnail Image]()
Loading...
Name
01326140.pdf
Size
262.95 KB
Format
Adobe PDF
Checksum
(MD5):8959797f60ebd445815204a0b3286ba6