Open AccessResearch on Tibetan Speech Recognition Speech Dictionary and Acoustic Model Algorithm
Author(s) -
Chunwei Gong,
Guanyu Li,
Lisai Luo
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1570/1/012003
Subject(s) - pronunciation , speech recognition , computer science , acoustic model , speech synthesis , natural language processing , artificial intelligence , speech processing , linguistics , philosophy
This paper mainly conducts related research on the algorithm of the Tibetan acoustic model. Firstly, a Tibetan Lhasa pronunciation dictionary is constructed based on words and monossssyllables, and then compared. The experimental results show that the phonetic dictionary constructed by words is superior to the phonetic dictionary constructed by monosyllables. At the same time, taking phonemes and single syllables as the modeling unit of the acoustic model, the modeling unit of the acoustic model was studied and a comparative experiment was carried out. Experimental results show that phonemes are better than single syllables as acoustic model modeling units.