A LARAGE-VOCABULARY TAIWANESE (MIN-NAN) MULTI-SYLLABIC WORD RECOGNITION SYSTEM BASED UPON RIGHT-CONTEXT-DEPENDENT PHONES WITH STATE CLUSTERING BY ACOUSTIC DECISION TREE

Ren Yuan Lyu; Yuang Jin Chiang; Wen Ping Hsieh

A LARAGE-VOCABULARY TAIWANESE (MIN-NAN) MULTI-SYLLABIC WORD RECOGNITION SYSTEM BASED UPON RIGHT-CONTEXT-DEPENDENT PHONES WITH STATE CLUSTERING BY ACOUSTIC DECISION TREE

Ren Yuan Lyu
, Yuang Jin Chiang^*
, Wen Ping Hsieh

^*此作品的通信作者

資訊工程學系(含學碩博士班)

National Tsing Hua University

研究成果: 會議稿件的類型 › 論文 › 同行評審

6 引文斯高帕斯（Scopus）

摘要

In this paper, we apply context dependent phonetic modeling on the task of large vocabulary (with 20 thousand words) Taiwanese multi-syllabic word recognition. Considering the phonetic characteristics of Taiwanese, the right context dependent (RCD) phones instead of the general tri-phones are used. The RCDs are further clustered at the sub-phone or state level using a decision tree with a set of context-split questions specially designed for Taiwanese speech according to the acoustic/phonetic knowledge. For the speaker dependent case, 7.18% word error rate is achieved. A real-time prototype system implemented on a Pentium-II personal computer running MSWindows95/NT is also shown to validate the approaches proposed here.

原文	英語
出版狀態	已出版 - 1998
事件	5th International Conference on Spoken Language Processing, ICSLP 1998 - Sydney, 澳大利亞持續時間: 30 11 1998 → 04 12 1998

Conference

Conference	5th International Conference on Spoken Language Processing, ICSLP 1998
國家/地區	澳大利亞
城市	Sydney
期間	30/11/98 → 04/12/98

文獻附註

Publisher Copyright:
© 1998. 5th International Conference on Spoken Language Processing, ICSLP 1998. All rights reserved.

其它文件與鏈接

Link to publication in Scopus

引用此

@conference{eac65b7968b149ca9ae0851c8cf8d0a0,

title = "A LARAGE-VOCABULARY TAIWANESE (MIN-NAN) MULTI-SYLLABIC WORD RECOGNITION SYSTEM BASED UPON RIGHT-CONTEXT-DEPENDENT PHONES WITH STATE CLUSTERING BY ACOUSTIC DECISION TREE",

abstract = "In this paper, we apply context dependent phonetic modeling on the task of large vocabulary (with 20 thousand words) Taiwanese multi-syllabic word recognition. Considering the phonetic characteristics of Taiwanese, the right context dependent (RCD) phones instead of the general tri-phones are used. The RCDs are further clustered at the sub-phone or state level using a decision tree with a set of context-split questions specially designed for Taiwanese speech according to the acoustic/phonetic knowledge. For the speaker dependent case, 7.18\% word error rate is achieved. A real-time prototype system implemented on a Pentium-II personal computer running MSWindows95/NT is also shown to validate the approaches proposed here.",

author = "Lyu, \{Ren Yuan\} and Chiang, \{Yuang Jin\} and Hsieh, \{Wen Ping\}",

note = "Publisher Copyright: {\textcopyright} 1998. 5th International Conference on Spoken Language Processing, ICSLP 1998. All rights reserved.; 5th International Conference on Spoken Language Processing, ICSLP 1998 ; Conference date: 30-11-1998 Through 04-12-1998",

year = "1998",

language = "英语",

}

A LARAGE-VOCABULARY TAIWANESE (MIN-NAN) MULTI-SYLLABIC WORD RECOGNITION SYSTEM BASED UPON RIGHT-CONTEXT-DEPENDENT PHONES WITH STATE CLUSTERING BY ACOUSTIC DECISION TREE. / Lyu, Ren Yuan; Chiang, Yuang Jin; Hsieh, Wen Ping.
1998. 論文發表於 5th International Conference on Spoken Language Processing, ICSLP 1998, Sydney, 澳大利亞.

研究成果: 會議稿件的類型 › 論文 › 同行評審

TY - CONF

T1 - A LARAGE-VOCABULARY TAIWANESE (MIN-NAN) MULTI-SYLLABIC WORD RECOGNITION SYSTEM BASED UPON RIGHT-CONTEXT-DEPENDENT PHONES WITH STATE CLUSTERING BY ACOUSTIC DECISION TREE

AU - Lyu, Ren Yuan

AU - Chiang, Yuang Jin

AU - Hsieh, Wen Ping

PY - 1998

Y1 - 1998

N2 - In this paper, we apply context dependent phonetic modeling on the task of large vocabulary (with 20 thousand words) Taiwanese multi-syllabic word recognition. Considering the phonetic characteristics of Taiwanese, the right context dependent (RCD) phones instead of the general tri-phones are used. The RCDs are further clustered at the sub-phone or state level using a decision tree with a set of context-split questions specially designed for Taiwanese speech according to the acoustic/phonetic knowledge. For the speaker dependent case, 7.18% word error rate is achieved. A real-time prototype system implemented on a Pentium-II personal computer running MSWindows95/NT is also shown to validate the approaches proposed here.

AB - In this paper, we apply context dependent phonetic modeling on the task of large vocabulary (with 20 thousand words) Taiwanese multi-syllabic word recognition. Considering the phonetic characteristics of Taiwanese, the right context dependent (RCD) phones instead of the general tri-phones are used. The RCDs are further clustered at the sub-phone or state level using a decision tree with a set of context-split questions specially designed for Taiwanese speech according to the acoustic/phonetic knowledge. For the speaker dependent case, 7.18% word error rate is achieved. A real-time prototype system implemented on a Pentium-II personal computer running MSWindows95/NT is also shown to validate the approaches proposed here.

UR - https://www.scopus.com/pages/publications/51849098063

M3 - 论文

AN - SCOPUS:51849098063

T2 - 5th International Conference on Spoken Language Processing, ICSLP 1998

Y2 - 30 November 1998 through 4 December 1998

ER -

A LARAGE-VOCABULARY TAIWANESE (MIN-NAN) MULTI-SYLLABIC WORD RECOGNITION SYSTEM BASED UPON RIGHT-CONTEXT-DEPENDENT PHONES WITH STATE CLUSTERING BY ACOUSTIC DECISION TREE

摘要

Conference

文獻附註

其它文件與鏈接

指紋

引用此