Study on SAMPA_ST for Lhasa Tibetan and realization of automatic labelling system

Author

Lu, Gao ; Hongzhi Yu ; Yonghong Li ; Ruishan, Zhang

Author_Institution

Key Lab. of Nat. Linguistic Inf. Technol., Northwest Univ. for Nat., Lan Zhou, China

fYear

2010

fDate

9-11 April 2010

Firstpage

133

Lastpage

137

Abstract

SAMPA_ST labeling is a computer-readable labeling system of Tibetan segments based on SAMPA. Through language investigation and phonological induction, the paper sorts out the phonology of Lhasa Tibetan which includes single consonants, consonant clusters, monophthongs, diphthongs , consonant coda of finals and tone of Lhasa Tibetan. According to SAMPA rules, the paper designs SAMPA _ST of Lhasa Tibetan initials, finals and tones, and establishes a set of SAMPA rules suitable for Lhasa Tibetan. The paper designs and realizes SAMPA_ST automatic labeling system of Tibetan monosyllables. This system realizes the true text-speech conversion and offers the basis for prosodic feature analysis, speech recognition and synthesis in engineering.

Keywords

natural language processing; speech processing; Lhasa; SAMPA_ST automatic labeling system; Tibetan monosyllables; computer-readable labeling system; consonant clusters; consonant coda; diphthongs; language investigation; phonological induction; prosodic feature analysis; speech recognition; text-speech conversion; Application software; Information retrieval; Information technology; Keyboards; Labeling; Natural languages; Speech analysis; Speech recognition; Speech synthesis; Standards development; IPA (International Phonetic Alphabet); Lhasa Tibetan; SAMPA_ST; finals; initials;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Analysis and Signal Processing (IASP), 2010 International Conference on

Conference_Location

Zhejiang

Print_ISBN

978-1-4244-5554-6

Electronic_ISBN

978-1-4244-5556-0

Type

conf

DOI

10.1109/IASP.2010.5476147

Filename

5476147