This article tackles the problem of transcribing English words using Thai phonological system. The problem exists in Thai, where modern writing often composes of English orthography, and transcribing using English phonology results unnatural. The proposed model is totally data-driven, starting by automatic grapheme-phoneme alignment, modeling transduction rules and predicting Thai syllabictones using learning machines. Three specific issues are addresses. The first one is involving English transcription information in transduction once the input English word appears in an English pronunciation dictionary. Second, more precise transduction rules can be obtained by a constraint of Thai syllable-structure. Lastly, the ambiguity in assigning tones to Thai pronunciations of English words is alleviated by introducing a learning machine. The proposed model achieves acceptable results in both objective and text-tospeech synthesis subjective tests.
[1]
Alan W. Black,et al.
Letter to sound rules for accented lexicon compression
,
1998,
ICSLP.
[2]
Virach Sornlertlamvanich,et al.
Thai grapheme-to-phoneme using probabilistic GLR parser
,
2001,
INTERSPEECH.
[3]
Walter Daelemans,et al.
Language-Independent Data-Oriented Grapheme-to-Phoneme Conversion
,
1996
.
[4]
Sudaporn Luksaneeyanawin,et al.
GENERATING THAI TRANSCRIPTIONS FOR ENGLISH WORDS
,
2008
.
[5]
Alan W. Black,et al.
Statistically trained orthographic to sound models for Thai
,
2000,
INTERSPEECH.
[6]
Kenneth Ward Church,et al.
Morphology and rhyming: two powerful alternatives to letter-to-sound rules for speech synthesis
,
1990,
SSW.
[7]
Walter Daelemans,et al.
Data-Oriented Methods for Grapheme-to-Phoneme Conversion
,
1993,
EACL.