Use of prosodic information to integrate acoustic and linguistic knowledge in continuous Mandarin speech recognition with very large vocabulary
Resource
Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on
Journal
Fourth International Conference on Spoken Language, 1996. ICSLP 96
Pages
-
Date Issued
1996-10
Date
1996-10
Author(s)
DOI
N/A
Abstract
The paper presents an approach to using prosodic information for the integration of acoustic and linguistic knowledge in continuous Mandarin speech with very large vocabulary. Since the overhead computation incurred from unification of search space is confined to the syllable boundaries, the use of prosodic information to reduce the syllable boundary hypotheses as well as the syllable matching length, is shown to be effective. The inherent complexity with the very large vocabulary is also reduced by the use of phrase boundary hypotheses conjectured via the phrase-final lengthening. Experimental results show a 47.2% recognition time save with only a 5.67% error rate increase using the syllable and phrase boundary hypotheses conjectured from prosodic information.
SDGs
Type
journal article
File(s)![Thumbnail Image]()
Loading...
Name
00607724.pdf
Size
366.18 KB
Format
Adobe PDF
Checksum
(MD5):e48284ee1f6b9321b5b3ff396a3506b5