===============================================
Technical Committee on Speech (SP)
Chair: Takao Kobayashi (Tokyo Inst. of Tech.) Vice Chair: Satoru Hayami (Gifu Univ.)
Secretary: Yoshiaki Ito (Iwate Pref. Univ.), Nobuaki Minematsu (Univ. of Tokyo)
Assistant: Takaaki Hori (NTT), Hiroki Matsuzaki (Hokkai Gakuen Univ.)
DATE:
Thu, Mar 20, 2008 09:55 - 16:50
Fri, Mar 21, 2008 10:00 - 17:15
PLACE:
Sanjo Conference Hall (Mar 20) and Faculty of Engineering Bldg.2 (Mar 21), Hongo Campus, the University of Tokyo(7-3-1 Hongo, Bunkyo-ku, Tokyo, Japan. http://www.u-tokyo.ac.jp/campusmap/map01_02_e.html. Assoc. Prof. Nobuaki Minematsu. 04-7136-5488)
TOPICS:
International Workshop (Mar 20), Speech Production, Speech Perception, Hearing and Speech, etc. (Mar 21)
----------------------------------------
Thu, Mar 20 Asian Workshop on Speech Science and Technology (09:55 - 16:50)
----------------------------------------
----- OPENING REMARKS ( 5 min. ) -----
(1) 10:00 - 11:00
[Invited Talk]
Voice-based Information Retrieval
-- How far are we from the text-based retrieval? --
Lin-shan Lee (Nat'l Taiwan Univ.)
(2) 11:00 - 12:00
[Invited Talk]
Robust Speech Recognition Based on Structured Modeling, Irrelevant Variability Normalization and Unsupervised Online Adaptation
Qiang Huo (Microsoft Research Asia)
----- LUNCH BREAK ( 60 min. ) -----
(3) 13:00 - 14:00
[Invited Talk]
Feature Vector Classification based on Likelihood Ratio
Jeong-sik Park, Sang-min Yoon, Yung-Hwan Oh (KAIST)
(4) 14:00 - 15:00
[Invited Talk]
Remaking speech revisited STRAIGHT and TANDEM-STRAIGHT and Their implications
Hideki Kawahara (Wakayama Univ.)
----- Break ( 15 min. ) -----
----- POSTER SESSION ( 90 min. ) -----
(5) 15:15 - 16:45
[Poster Presentation]
A STUDY ON THE LP-BASED BLIND MODEL IN RESTORING BONE-CONDUCTED SPEECH
Thang tat Vu, Masashi Unoki, Masato Akagi (JAIST)
(6) 15:15 - 16:45
[Poster Presentation]
Investigation of usual and unusual articulation based on simulations and observations
Akikazu Nishikido, Jianwu Dang (JAIST)
(7) 15:15 - 16:45
[Poster Presentation]
Perception of Speaker Identity and Its Relation to the Phonological Features
Kanae Amino, Takayuki Arai (Sophia Univ.)
(8) 15:15 - 16:45
[Poster Presentation]
Effects of repetition priming and word familiarity on perception of spectrally degraded spoken words
Mika Murao, Yasunari Sasaki, Hiroshi Riquimaroux (Doshisha Univ.)
(9) 15:15 - 16:45
[Poster Presentation]
Prosody Reconstruction by Rescaling Fundamental Frequency Contours in Order to Synthesize Communicative Speech
Jinfu Ni, Shinsuke Sakai, Satoshi Nakamura (NICT/ATR)
(10) 15:15 - 16:45
[Poster Presentation]
A Context Clustering Technique for Improvement of Tone Intelligibility of Average-voice-based Thai Speech Synthesis
Suphattharachai Chomphan, Takao Kobayashi (Tokyo Inst. of Tech.)
(11) 15:15 - 16:45
[Poster Presentation]
Robust noise suppression algorithm using the only Kalman filter theory for white and colored noises
Nari Tanabe (Tokyo Univ. of Science, Suwa), Toshihiro Furukawa (Tokyo Univ. of Science), Shigeo Tsujii (Inst. of Information Security)
(12) 15:15 - 16:45
[Poster Presentation]
Improvement of robustness using selective sound segregation for automatic speech recognition systems in noisy environments
Atsushi Haniu, Masashi Unoki, Masato Akagi (JAIST)
(13) 15:15 - 16:45
[Poster Presentation]
Robust Distant Speech Recognition by Combining Variable-term spectrum Based Position-dependent CMN with Conventional CMN
Longbiao Wang, Seiichi Nakagawa (Toyohashi Univ. of Tech.), Norihide Kitaoka (Nagoya Univ.)
(14) 15:15 - 16:45
[Poster Presentation]
Unsupervised Phoneme Segmentation Using Mahalanobis Distance
Yu Qiao, Nobuaki Minematsu (Univ. of Tokyo)
(15) 15:15 - 16:45
[Poster Presentation]
A Fast Sequence Kernel for Sequential Data Classification
Makoto Yamada (SOKENDAI/Yamaha Corp.), Tomoko Matsui (Inst. of Statistical Mathematics)
(16) 15:15 - 16:45
[Poster Presentation]
LVCSR based on Context-Dependent Syllable Acoustic Models
Jian Zhang, Longbiao Wang, Seiichi Nakagawa (Toyohashi Univ. of Tech.)
(17) 15:15 - 16:45
[Poster Presentation]
Accent Analysis for Mandarin Large Vocabulary Continuous Speech Recognition
Dong Yang, Koji Iwano, Sadaoki Furui (Tokyo Inst. of Tech.)
(18) 15:15 - 16:45
[Poster Presentation]
Initial Evaluation of the Drivers' Japanese Speech Corpus in a Car Environment
Kousuke Hiraki, Takahiro Shinozaki, Koji Iwano, Agnieszka Betkowska, Koichi Shinoda, Sadaoki Furui (Tokyo Inst. of Tech.)
(19) 15:15 - 16:45
[Poster Presentation]
Efficient Discriminative Training of Error Corrective Models Using High-WER Competitors
Takanobu Oba, Takaaki Hori, Atsushi Nakamura (NTT)
----- CLOSING REMARKS ( 5 min. ) -----
----------------------------------------
Fri, Mar 21 SP/H March Workshop (10:00 - 17:15)
----------------------------------------
(1) 10:00 - 10:30
Vowel Epenthesis in Consonant Clusters by Japanese Speakers
Masako Fujimoto (NIJLA), Seiya Funatsu (The Prefectural University of Hiroshima)
(2) 10:30 - 11:00
Attention Effects on Auditory Brainstem Responses During Contralateral Noise Masking
Kazunari Ikeda, Takahiro Sekiguchi, Akiko Hayashi (Tokyo Gakugei Univ.)
(3) 11:00 - 11:30
Acoustic features contributing to gender perception in continuously uttered speech signals
Takeshi Shibata, Masato Akagi (JAIST)
----- LUNCH BREAK ( 90 min. ) -----
(4) 13:00 - 13:30
A study on perceptual naturalness and spectrum features of a phoneme replaced with other speaker's one in short sentence.
Reiko Takou, Hiroyuki Segi (NHK Sci. & Tech. Res.), Nobumasa Seiyama (NHK Eng. Serv., Inc.), Tohru Takagi (NHK Sci. & Tech. Res.)
(5) 13:30 - 14:00
Study of Word Perception using abnomal speech sounds of a Glossectomized Patient
-- I. Working of Top-Down Process --
Yoshio Miki, Kanji Nohara, Kentarou Okuno (Osaka Univ.)
(6) 14:00 - 14:30
Study of Word Perception using abnormal speech sounds of a Glossectomized Patient
-- II. Factors and influence on word perception --
Yoshio Miki, Kanji Nohara, Kentarou Okuno (Osaka Univ.)
(7) 14:30 - 15:00
Numerical study of vocal nodules-induced dysphonia
Shinji Deguchi (Tohoku Univ.), Yuki Kawahara (Okayama Univ.)
----- BREAK ( 15 min. ) -----
(8) 15:15 - 15:45
On-line Discrimination of Speakers without prior Learning
Shinji Kutomi, Tetsuya Matsumoto, Yoshinori Takeuchi, Hiroaki Kudo, Noboru Ohnishi (Nagoya Univ.)
(9) 15:45 - 16:15
Automatic scoring of language learners' utterances generated through shadowing based on bottom-up clustering
Naoya Shimomura, Nobuaki Minematsu (Univ. of Tokyo), Yutaka Yamauchi (Tokyo International Univ.), Keikichi Hirose (Univ. of Tokyo)
(10) 16:15 - 16:45
Improvement of real-time STRAIGHT and implementation of STRAIGHT library
Hideki Banno (Meijo Univ.), Masanori Morise, Toru Takahashi, Ryuichi Nisimura, Toshio Irino, Hideki Kawahara (Wakayama Univ.)
(11) 16:45 - 17:15
A Band Extension Technique of Narrow Band Telephony Speech Based on Full Wave Rectification
Naofumi Aoki (Hokkaido Univ.)
# CONFERENCE SPONSORS:
- Co-organized by the Speech Committee and the Psychological and Physiological Acoustics Committee of the Acoustical Society of Japan. Co-sponsored by the IEEE Signal Processing Society Japan Chapter
=== Technical Committee on Speech (SP) ===
# FUTURE SCHEDULE:
Apr, 2008: Recess
Thu, May 29, 2008 - Fri, May 30, 2008: Kobe University [Fri, Mar 14], Topics: Welfare and Speech Processing, etc.
Fri, Jun 27, 2008 - Sat, Jun 28, 2008: [Wed, Apr 16], Topics: Speech Production, Speech Perception, Hearing and Speech, etc.
Last modified: 2008-01-26 15:48:27
|
Notification: Mail addresses are partially hidden against SPAM.
|