Oriental-COCOSDA Workshop 2003

 

Final Program, Singapore Oct 1-3, 2003

 

Oct 1, 2003 Wednesday (First Day)

 

0830-0930                     Registration

0930-1000               Opening and welcome speeches

1000-1030                        Tea

1030-1200                        Keynote 1

Overview of the East-Asian Activities on Speech Corpora and

Assessment

Shuichi ITAHASHI, University oh Tsukuba, Japan

Keynote 2

Focus-Marking in Chinese and Malay: A Comparative Perspective

Jie XU, Department of Chinese Studies, National University of Singapore

1230-1330                          Lunch

1330-1530   AST O-COCOSDA       Chair: Haizhou Li

Error Identification and Correction in Chinese Speech Input Post-processing, L.Y.L. Cheung, B.K.Tsou, T.B.Y.Lai, LISRC, City University of Hong Kong

 

Learning of Word Boundaries In Continuous Speech Using Time Delay Neural Networks, Colin Keng-Yan TAN, Kim-Teng LUA, School of Computing, National University of Singapore

 

Dialog Input Assessment in a Diverse-Task Environment Using Belief Functions, Hong-I Ng, Kim-Teng Lua, School of Computing, National University of Singapore

 

            Use of Linguistic Information of Accent Phrases for Automatic

            Extraction of Fo Contour Generation Process Model Parameters,

Keikichi Hirose*, Yusuke Furuyama*, Shuichi Narusawa**, Nobuaki Minematsu**, Hiroya Fujusak***,

*Dept. of Frontier Informatics, School of Frontier Sciences, University of Tokyo, **Dept. of Information and Communication Enguneering, School of Information Science and Technology, University of Tokyo

***Prof. Emeritus, University of Tokyo

 

Duration Rules For Vowels In Telugu, P. N. Girija and Sridevi, Department of Computer & Information Sciences, Artificial Intelligence Lab, University of Hyderabad

 

1530-1600                       Tea

1600-1800   SDC-1 O-COCOSDA       Chair: P N Girija

TAICAR - A Collection of In-Car Mandorin Speech Database in Taiwan, Jhing-Fa Wang, Hsien-Chang Wang and Chung-Hsien Yang, Department of Electrical Engineering, Department of Computer Science and Information Science, National Cheng Kung University, Tainan

 

Thai Speech Coupus for Speech Recognition, Sawit Kasuriya, Virach Sornlertlamvanich, Patcharika CotsomrongSupphanat Kanokphara, and Nattanun, Information Research and Development, National Electronics and Computer Technology Center (NECTEC), Thailand

 

            Construction of Large-Scale Shanghai Putonghua

Speech Corpus for Chinese Speech Recognition, Jing Li, Fang Zheng, Zhenyu Xiong, and Wenuhu Wu, Tsinghua University, China

 

DIMSU: A Speech Database with Pitch Marks, RenZyun Cheng, MingJie Tian, Yuang-Chin Chiang, Ren-yuan Lyu, Chamg Gung University, Tao Yuan

 

Databases of Expressive Speech, Nick Campbell, ATR Human Information Science Laboratories, JST/CREST Expressive Speech Processing Project

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Oct, 2003 Thursday (Second Day)

 

0900-1020                      Keynote 3

Making Full Use of Speech Corpora

Thomas Fang Zheng, Tsinghua University

1020-1050                       Tea

1050-1210                      Keynote 4

Virtual Linked Lexical Knowledge Base for Causality Reasoning

Choi, Key-Sun, KAIST, Korterm

 

1210-1330                       Lunch

1330-1530   SIO-1 O-COCOSDA       Chair: Nick Campbell

An In-Car Speech Corpus for Singapore English, Cuntai Guan, Thomas Choy, Bin Ma, Jun Xu, Haizhou Li, Min Zhang, Infotalk Technology, Republic, of Singapore

 

            Thai Tagged Speech Corpus for Speech Synthesis, Chatchawarn

            Hansakunbuntheung, Virongrong Tesprasit, Virach Sornlertlamvanich,

Information R&D Division, National Electronics and Computer Technology Center, 112 Thailand Science Park, Phahon Yothin Road, Klong 1, Klong Luang, Pathumthani 12120 Thailand.

 

1530-1600                       Tea

1600-1800   SIO-2 O-COCOSDA       Chair: Thomas Fang Zheng

Thai Speech Database for Speech Recognition (NECTEC-ATR Thai Speech Database), Sawit Kasuriya, Virach Sornlertlamvanich, Patcharika Cotsomrong, Takatoshi Jitsuhiro, Genichiro Kikui and Yoshinori Sagisaka

 

Prosody Model For Indonesian TTS Using “Contour Pitch Theory” and “Fujidako Model”, Arry Akhmad Arman, Hammam Riza, Electrical Engineering Dept. Instittut Tecknologi Bandung Bandung 40132, Indonesia; Language Technology Center BPPT, Jakarta, Indonesia

 

Data-Driven Construction of Distance Tables for Cantonese Unit Selection Synththesis, Jin-Hui Yang Zhi-Wei Shuang Ren-Hua Wang, iFly Speech Laboratory, China

 

1900                          Banquet

Oct 3, 2003 Friday (Third Day)

 

0900-1020    SIO-3 O-COCOSDA       Chair: Shuichi ITAHASHI

            MLP-Based Utterance Verification For In-Car Speech Recognition,

Shih-Chieh Chien, Tai-Hwei Hwang, and Sen-Chang, Industrial Technology Research Institute, HsinChu

 

Reducing Language Model Size By Importance-Based Pruning And Rank-Based Quantization, Genquing WU and Fang ZHENG, Tsinghua University, China

 

1020-1050                         Tea

1050-1210    PSOL O-COCOSDA       Chair: Jianhua Tao

            A collection of onomatopoeias in Japanese sports, Yoshitaka Fujino

Masao Kikkawa, Yoshinori Sagisaka, Graduate School of Global Information and Telecommunication Studies, Waseda University, Tokyo

 

Intonation Patterns in Thai Questions with and without Final Particles, Auyeung Puangpen, Tumtavitikul, Apiluck, Department of Linguistics, Faculty of Humanities, Kasetsart University, Bangkok, Thailand

 

Analysis of pronunciation errors in Japanese speech uttered by Korean towards development of Japanese CALL system, Oh Pyo Kweon, Motoyuki Suzuji, Akinori Ito and Shozo Makino, Tohoku University, Japan

 

Intonation Knowledge for Declarative Telugu Sentences, P. N, Girija and M.Neeraja, University of Hyderabad

 

1210-1330                       Lunch

 

 

 

 

 

 

 

 

 

 

1330-1530    SDC-2-COCOSDA       Chair: Keikichi Hirose

            An evaluation of J-TOBI on the Japanese multext prosodic corpus,

Shigeyoshi KITAZAWA, Shinya KIRIYAMA, Toshihiko ITOH, Nick CAMPBELL, Faculty of Information, Shizuoka University, 3-5-1

Johoku, Hamamatsu, 432-8011, Japan, ATR Human Information Science Research Labs. Seika-cho, Hikari-dai, Kyoto 619-02, Japan

 

An Advanced Japanese Speech Corpus for In-car Spoken Dialogue Research, Yuki Irie, Nobuko Kawaguchi, Shigeki Matsubara, Itsuki

            Kishida, Yukiko Yamaguchi, Kazuya Takeda, Fumitada Itakura, and

            Yasuyoshi Inagaki, Center for Integrated Acoustic Information Research,

            Nagoya University, Japan

 

            Bilingual Speech Dialogue Corpus for Simultaneous Machine

Interpretation Research, Koichiro Ryu, Shigeki Matsubara, Nobuo Kawaguchi and Yasuyoshi Inagaki, Nagoya University, Prefectual University, Japan

 

            Collecting Mandarin Speech Databases for Prosody Investigations,

            Ciu-yu Tseng, Yun-Ching Cheng, Wei-Sha Lee and Feng-Lan Huang,

            Academia Sinica, Taipei

 

Statisitcal Analysis of Text and Speech Sounds from Parallel Corpus of Indian Languages, Sunita Arora, Karunesh Kr. Arora, Aman Suneja, S S Agrawal

 

1530-1600                        Tea

1600-1615                    Closing Ceremony

 

 

One-day City Tour (Saturday, 4-10-2003)

Details to be announced.