Title :
Classification of Thai tone sequences in syllable-segmented speech using the analysis-by-synthesis method
Author :
Potisuk, Siripong ; Harper, Mary P. ; Gandour, Jack
Author_Institution :
Sch. of Electr. & Comput. Eng., Purdue Univ., West Lafayette, IN, USA
fDate :
1/1/1999 12:00:00 AM
Abstract :
Tone classification is important for Thai speech recognition because tone affects the lexical identification of words. An analysis-by-synthesis algorithm for classifying Thai tones in syllable-segmented speech is presented that uses an extension to Fujisaki´s (1983) model for tone languages that incorporates tonal assimilation and declination. The classifier correctly identifies all of the tones in 89.1% of the test utterances
Keywords :
natural languages; pattern classification; speech processing; speech recognition; speech synthesis; Fujisaki´s model; Thai tone sequences classification; analysis-by-synthesis algorithm; lexical identification; speech recognition; syllable-segmented speech; test utterances; tonal assimilation; tonal declination; tone languages; Algorithm design and analysis; Classification algorithms; Lifting equipment; Natural languages; Pattern matching; Shape; Speech analysis; Speech processing; Speech recognition; Testing;
Journal_Title :
Speech and Audio Processing, IEEE Transactions on
