THE CU-MFEC CORPUS FOR THAI AND ENGLISH SPELLING SPEECH RECOGNITION

被引：0

作者：

Kertkeidkachorn, Natthawut ^{[1
]}

Chanjaradwichai, Supadaech ^{[1
]}

Suri, Teera ^{[1
]}

Likitsupin, Krerksak ^{[1
]}

Vorapatratorn, Surapol ^{[1
]}

Hirankan, Pawanrat ^{[1
]}

Limpanadusadee, Worasa ^{[1
]}

Chuetanapinyo, Supakit ^{[1
]}

Pitakpawatkul, Kitanan ^{[1
]}

Puangsri, Natnarong ^{[1
]}

Tangsirirat, Nathacha ^{[1
]}

Trakulsuk, Konlawachara ^{[1
]}

Punyabukkana, Proadpran ^{[1
]}

Suchato, Atiwong ^{[1
]}

机构：

[1] Chulalongkorn Univ, Fac Engn, Dept Comp Engn, Spoken Language Syst Res Grp, Bangkok, Thailand

来源：

2012 INTERNATIONAL CONFERENCE ON SPEECH DATABASE AND ASSESSMENTS | 2012年

关键词：

Speech corpus; Thai spelling corpus; Automatic speech recognition;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Much of the efficiency of any Automatic Speech Recognition (ASR) system depends on its speech corpus. This is even more so for recognizers designed for specific tasks. Naturally, an ASR for spelling recognition performs better if it is trained with a spelling speech corpus rather than a generic one. Although several speech corpora are available in Thai, we are still lack of Thai spelling speech corpora. This paper reports collection of experiences gained from constructing CU-MFEC, a Thai spelling speech corpus designed for form filling or other applications of similar nature. CU-MFEC corpus employed 100 speakers and encompassed 58 hours and 10 minutes of speech. There are four sets of the corpus; Alphabets with short pauses, Continuous free spelling, Sentences, and Numbers and commands. We evaluated its efficiency by utilizing CU-MFEC with speech recognition tasks and found the accuracy rate of 79.37% for spelling task and 54.92% for connected spelling task.

引用

页码：18 / 23

页数：6

共 10 条

[1]

[Anonymous], ORIENTAL COCOSDA 200

[2]

BHURIYAKORN P, 2008, SNPD 08 AUG, P475, DOI DOI 10.1109/SNPD.2008.73

[3]

Boersma P., 2012, WEENINK PRAAT 5 3 11

[4]

Chotimongkol A., 2010, P OR COCOSDA 10 KATH

[5]

Chotimongkol A., 2010, ECTI CON THAIL, P1080

[6] LOTUS-BN: A Thai Broadcast News Corpus and Its Research Applications [J].

Chotimongkol, Ananlada ;

Saykhum, Kwanchiva ;

Chootrakool, Patcharika ;

Thatphithakkul, Nattanun ;

Wutiwiwatchai, Chai .

ORIENTAL COCOSDA 2009 - INTERNATIONAL CONFERENCE ON SPEECH DATABASE AND ASSESSMENTS, 2009, :44-50

[7]

Kasuriya S., 2003, Proceedings of the Oriental COCOSDA 2003. International Coordinating Committee on Speech Databases and Speech I/O System Assessment, P105

[8]

Kosawat K., 2009, P SNLP 2009 BANGK TH

[9] An HMM-based method for Thai spelling speech recognition [J].

Pisarn, C. ;

Theeramunkong, T. .

COMPUTERS & MATHEMATICS WITH APPLICATIONS, 2007, 54 (01) :76-95

[10] Automatic selection of phonetically distributed sentence sets for speaker adaptation with application to large vocabulary Mandarin speech recognition [J].

Shen, JL ;

Wang, HM ;

Lyu, RY ;

Lee, LS .

COMPUTER SPEECH AND LANGUAGE, 1999, 13 (01) :79-97

← 1 →