Hidden Markov model for Mandarin lexical tone recognition

Author

Yang, Wu-ji ; Lee, Jyh-Chyang ; Chang, Yueh-Chin ; Wang, Hsiao-Chuan

Author_Institution

Dept. of Electr. Eng., Nat. Tsing Hua Univ., Hsinchu, Taiwan

Volume

36

Issue

7

fYear

1988

fDate

7/1/1988 12:00:00 AM

Firstpage

988

Lastpage

992

Abstract

A case of lexical tone recognition for Mandarin speech is discussed using a combination of vector quantization and hidden Markov modelling techniques. The observation sequence was a sequence of vectorized parameters consisting of a logarithmic pitch interval and its first derivative. The vector quantization was applied to convert the observation sequence into a symbol sequence for Hidden Markov modeling. The speech database was provided by seven male and seven female college students, with each pronouncing 72 isolated monosyllabic utterances. A probabilistic model for each of the four tones was generated. A series of tonal recognition tests were then conducted to evaluate the effects of pitch reference base, codebook size, and tonal model topology. Future consideration of Mandarin speech recognition is also discussed

Keywords

Markov processes; analogue-digital conversion; speech recognition; Mandarin lexical tone recognition; codebook size; females; hidden Markov modelling; isolated monosyllabic utterances; logarithmic pitch interval; males; observation sequence; pitch reference base; probabilistic model; speech database; symbol sequence; tonal model topology; vector quantization; vectorized parameters; Databases; Delta modulation; Educational institutions; Hidden Markov models; Natural languages; Speech recognition; Testing; Topology; Vector quantization;

fLanguage

English

Journal_Title

Acoustics, Speech and Signal Processing, IEEE Transactions on

Publisher

ieee

ISSN

0096-3518

Type

jour

DOI

10.1109/29.1620

Filename

1620