Large-Vocabulary Continuous Speech Recognition of Lhasa Tibetan-Reference-Cited by-同舟云学术

Large-Vocabulary Continuous Speech Recognition of Lhasa Tibetan

Published:2014-02 Issue: Volume:519-520 Page:802-806
ISSN:1662-7482
Container-title:Applied Mechanics and Materials
language:
Short-container-title:AMM

Author:

Li Guan Yu¹,Yu Hong Zhi¹

Affiliation:

1. Northwest University for Nationalities

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.

Publisher

Trans Tech Publications, Ltd.

Link

https://www.scientific.net/AMM.519-520.802.pdf

Reference12 articles.

1. Gongque Jiangcuo, Theory of Tibetan, Tibetan Studies . 1997 III.

2. Kelsang Jumian, Practical Tibetan grammar course. Sichuan minorities press. November 2004 edition.

3. Han Qinghua, Yu Hongzhi. Anduo Tibetan speaker-independent isolated words speech recognition based on HMMs. Software Guide . 2010 07.

4. Pei Chun Bao. The Tibetan language speech recognition technology based on the standard Lhasa, Master Thesis in Tibet University , (2009).

5. The HTK Book(for HTK Version 3. 4). Cambridge University Engineering Department. (2009).

Cited by 2 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Lhasa Dialect Recognition of Different Phonemes Based on TDNN Method;Lecture Notes in Computer Science;2022

2. A Tibetan Language Model That Considers the Relationship Between Suffixes and Functional Words;IEEE Signal Processing Letters;2021