Title :
Tone recognition for Thai
Author :
Tungthangthum, Apichat
Author_Institution :
Asian Univ. of Sci. & Technol., Chonburi, Thailand
Abstract :
This paper describes the tone recognition for Thai language. The autocorrelation method is used to extract the pitch or fundamental frequency (FO) from a speech signal. Hidden Markov models (HMMs) are then used to recognize these pitch contours to determine the tones. Though the tone information is superimposed on the vowel portion of a syllable, recognition experiments show that tones and vowels are independent from each other. Tone information extracted from one vowel can be used on another different vowel
Keywords :
correlation methods; hidden Markov models; speech recognition; Thai language; autocorrelation method; fundamental frequency; hidden Markov models; pitch contours; pitch extraction; speech signal; tone recognition; vowel portion; Autocorrelation; Cities and towns; Data mining; Databases; Frequency; Hidden Markov models; Pattern recognition; Sampling methods; Speech recognition; Testing;
Conference_Titel :
Circuits and Systems, 1998. IEEE APCCAS 1998. The 1998 IEEE Asia-Pacific Conference on
Conference_Location :
Chiangmai
Print_ISBN :
0-7803-5146-0
DOI :
10.1109/APCCAS.1998.743692
