Tangerine: a large vocabulary Mandarin dictation system

Author

Gao, Yuqing ; Hon, Hsiao-Wuen ; Lin, Zhiwei ; Loudon, Gareth ; Yogananthan, S. ; Yuan, Baosheng

Author_Institution

Inst. of Syst. Sci., Nat. Univ. of Singapore, Singapore

Volume

1

fYear

1995

fDate

9-12 May 1995

Firstpage

77

Abstract

The text input for non-alphabetic languages, such as Chinese, has been a decades-long problem. Chinese dictation using large vocabulary speech recognition provides a convenient mode of text entry. In contrast to a character based dictation system, a word-based Mandarin dictation system has been designed (based on Apple´s PlainTalk speech recognition technology for efficient entry of Chinese characters into a computer. New features and improvements to the dictation system are presented. The new features and improvements have produced an overall reduction in recognition error of 50-80%. The vocabulary has also been increased from 5000 words to over 11000 words

Keywords

Apple computers; dictation; natural languages; speech recognition; Apple PlainTalk speech recognition technology; Chinese dictation; Tangerine; large vocabulary Mandarin dictation system; large vocabulary speech recognition; nonalphabetic languages; recognition error; text entry; text input; word-based Mandarin dictation system; Background noise; Cables; Cepstral analysis; Hidden Markov models; Mel frequency cepstral coefficient; Microphones; Natural languages; Noise reduction; Speech analysis; Speech recognition; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., 1995 International Conference on

Conference_Location

Detroit, MI

ISSN

1520-6149

Print_ISBN

0-7803-2431-5

Type

conf

DOI

10.1109/ICASSP.1995.479277

Filename

479277