Large-Vocabulary Continuous Speech Recognition of Lhasa Tibetan

Guan Yu Li; Hong Zhi Yu

doi:10.4028/www.scientific.net/AMM.519-520.802

Paper Titles

Research on Automatic Tagging of Parts of Speech for Tibetan Texts Based on the Condition of Random Fields
p.784

Fast and Effective Algorithm of Iris Localization Based on Hough Transform
p.788

On Fuzzy Abundant Semigroups
p.794

Improved Self-Adaptive Glowworm Swarm Optimization Algorithm
p.798

Large-Vocabulary Continuous Speech Recognition of Lhasa Tibetan
p.802

Text Classification Using SVM with Exponential Kernel
p.807

Fractal Analysis of the Optimal Objective Function
p.811

Application of EEG Analysis in Cognitive Science
p.816

Approaches of Ontological Concept Mapping Based on Multi-Strategy
p.820

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 519-520Large-Vocabulary Continuous Speech Recognition of...

Large-Vocabulary Continuous Speech Recognition of Lhasa Tibetan

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.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 519-520)

Pages:

802-806

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.519-520.802

Citation:

Cite this paper

Online since:

February 2014

Authors:

Guan Yu Li, Hong Zhi Yu

Keywords:

HMM, HTK, Lhasa Dialect, LVCSR, Tibetan

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

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

Google Scholar

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

Google Scholar

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

Google Scholar

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

Google Scholar

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

Google Scholar

[6] Website: http: /htk. eng. cam. ac. uk.

Google Scholar

[7] L awrence Rabiner, Biing-Hwang Juang. Fundamentals of Speech Recognition, Tsinghua University Press Copy.

Google Scholar

[8] Nichong Jia, Liu Wen Ju, Xu Bo. Chinese large vocabulary continuous speech recognition system progress. Chinese Information. Volume 23 No. 1 January (2009).

Google Scholar

[9] Li Yonghong, Kong Jiangping, Yu Hongzhi. Automatically convert Tibetan language audio and its implementation. Tsinghua University (Natural Science) . 2008 Volume 48 of the S1.

Google Scholar

[10] Zheng Fang, Wen Hu Wu, Fang Ditang. Recognition Keyword Research of Continuous stream voice. Fourth National Conference on Human Machine Speech Communication Proceedings, (1996).

Google Scholar

[11] Gao Sheng, XU Bo, HUANG Taiyi. Chinese triphone model Based on Acoustics Decision Tree. Vol 25 No. 6 November (2000).

Google Scholar

[12] Julian James Odell. The Use of Context in Large Vocabulary Speech Recognition. University of Cambridge. March (1995).

Google Scholar