JOURNAL ARTICLE
Large-Vocabulary Continuous Speech Recognition of Lhasa Tibetan
Year: 2014 Journal: Applied Mechanics and Materials Vol: 519-520 Pages: 800-804 Publisher: Trans Tech Publications
Abstract
The framework of auto speech recognition of Lhasa dialect was established in this paper. Phoneme was chosen as the basic unit for modeling. Then, phonemes set of Lhasa dialect and their Latin transliteration were designed. There were 5568 frequently used monosyllables in the vocabulary. Hidden Markov Models of triphones were established and trained by use of HTK. Word error rate (WER) was 21.81% under the optimal situation.
Keywords:
Hidden Markov model Speech recognition Vocabulary Transliteration Computer science Word error rate Set (abstract data type) Natural language processing Word (group theory) Artificial intelligence Linguistics
Metrics
0
Cited By
0.00
FWCI (Field Weighted Citation Impact)
0
Refs
0.54
Citation Normalized Percentile
Is in top 1%
Is in top 10%
Topics
Advanced Algorithms and Applications
Physical Sciences → Engineering → Control and Systems Engineering
Advanced Computational Techniques and Applications
Physical Sciences → Computer Science → Artificial Intelligence
China's Ethnic Minorities and Relations
Social Sciences → Social Sciences → Sociology and Political Science
Related Documents
JOURNAL ARTICLE
Large-Vocabulary Continuous Speech Recognition of Lhasa Tibetan
Journal: Applied Mechanics and Materials Year: 2014 Vol: 519-520 Pages: 802-806
JOURNAL ARTICLE
Research in large vocabulary continuous speech recognition
Janet BakerLarry GillickRobert Roth
Year: 1994 Pages: 454-454
JOURNAL ARTICLE
Large Vocabulary Continuous Audio-Visual Speech Recognition
Year: 2018 Pages: 538-541