Previous [1] [2] [3] [4] [5] [6] [7] [8] [9] [10]

Journal of Inforamtion Science and Engineering, Vol.12 No.3, pp.365-379 (September 1996)
A Vowel-Driven Connected Mandarin
Digit Recognition System

Ruey-Ching Shyu, Jhing-Fa Wang*, Chaug-Ching Huang,
Chung-Hsien Wu* and Jau-Yien Lee#
Department of Electrical Engineering
National Cheng Kung University
Tainan, Taiwan 701, R.O.C.
*Institute of Information Engineering
National Cheng-Kung University
Tainan, Taiwan 701, R.O.C.
#Department of Electrical Engineering
Chang Gung College of Medicine and Technology
Taiwan, R.O.C.

A vowel-driven connected Mandarin digit recognition system is presented in this paper. Since Mandarin is a monosyllabic language, each syllable has a consonant (which may be null) and a vowel. Hence, a concatenated digit string is composed of a series of consonants and vowels. A segmentation algorithm is proposed to segment a connected digit string into its consonant and stable-region parts, where a stable region may contain more than one vowel. The stable-region parts are recognized first. Mandarin digits, except (1, 7) and (6, 9), can be recognized just by their vowel parts. The digit pairs (1, 7) and (6, 9), which have the same vowel parts, are further distinguished by the special acoustic characteristic of the consonant part. The recognition system has been tested in a speaker-dependent mode under two different cases; known string length and unknown string length. String error rates of 5.3% and 7.4% were achieved in the known-length and unknown-length cases, respectively.

Keywords: connected Mandarin digit recognition; vowel-driven; consonant/stable-region segmentation; Bayesian template; speaker-dependent; known string length; unknown string length

Received October 9, 1995; revised March 4, 1996.
Communicated by Zen Chen.