Tue, Dec 9 AM
10:00 - 12:05 |
| (1) |
10:00-10:25 |
Two-channel input speech recognition using sparsness-based blind source separation |
Kenta Nishiki, Yosuke Izumi (Univ. of Tokyo), Shinji Watanabe (NTT), Takuya Nishimoto, Nobutaka Ono, Shigeki Sagayama (Univ. of Tokyo) |
| (2) |
10:25-10:50 |
Hands-free speech recognition system for robot |
Kosuke Hosoya, Tetsuji Ogawa, Shinya Fujie, Daichi Watanabe, Yuhi Ichikawa, Hikaru Taniyama, Tetsunori Kobayashi (Waseda Univ.) |
| (3) |
10:50-11:15 |
Noisy speech recognition using integrated method of statistical model-based voice activity detection and noise suppression |
Masakiyo Fujimoto, Kentaro Ishizuka, Tomohiro Nakatani (NTT Corporation) |
| (4) |
11:15-11:40 |
Music suppression method for single channel speech mixed with BGM using Bayesian networks |
Hiroaki Itou, Takanori Nishino, Norihide Kitaoka, Kazuya Takeda (Nagoya Univ.) |
| (5) |
11:40-12:05 |
Speaker diarization of multi-party conversations based on audio and visual information integration |
Kentaro Ishizuka, Shoko Araki, Kazuhiro Otsuka, Masakiyo Fujimoto, Tomohiro Nakatani (NTT) |
| |
12:05-13:10 |
Lunch Break ( 65 min. ) |
Tue, Dec 9 PM
13:10 - 14:00 |
| (6) |
13:10-14:00 |
[Invited Talk]
Cognitive competence required for spoken language performance and computational competence realized by spoken language engineering |
Nobuaki Minematsu (Univ. of Tokyo) |
| |
14:00-14:10 |
Break ( 10 min. ) |
Tue, Dec 9 PM
14:10 - 15:00 |
| (7) |
14:10-14:35 |
Acoustic Model Training Technique for Speech Recognition using Style Estimation with Multiple-Regression HMM |
Yusuke Ijima, Makoto Tachibana, Takashi Nose, Takao Kobayashi (Tokyo Tech) |
| (8) |
14:35-15:00 |
Speech Feature Extraction Using Constrained Nonnegative Matrix Factorization |
Hyunsin Park, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) |
| |
15:00-15:10 |
Break ( 10 min. ) |
Tue, Dec 9 PM
15:10 - 16:25 |
| (9) |
15:10-15:35 |
Evaluation of annealing schadule for PLSA language model adaptaion |
Masaharu Kato, Tetsuo Kosaka (Yamagata Univ.), Akinori Ito, Shozo Makino (Tohoku Univ.) |
| (10) |
15:35-16:00 |
Speech Recognition by Topic Models with Continuous/Discontinuous Topic Changes |
Atsushi Sako, Yasuo Ariki (Kobe Univ.), Tomoharu Iwata, Shinji Watanabe, Takaaki Hori (NTT) |
| (11) |
16:00-16:25 |
User modeling for a satisfaction evaluation of a speech recognition system |
Sunao Hara, Norihide Kitaoka, Kazuya Takeda (Nagoya Univ.) |
| |
16:25-16:40 |
Break ( 15 min. ) |
Tue, Dec 9 PM
16:40 - 18:10 |
| |
- |
|
Wed, Dec 10 AM
09:30 - 11:10 |
| (12) |
09:30-09:55 |
Segmentation of Spoken Language into unit of Utterance Fragment using Acoustics Features |
Katsuyoshi Setoyama (Nara Institute of Science and Technology), Hideki Kashioka, Nick Campbell (Nara Institute of Science and Technology/National Institute of I) |
| (13) |
09:55-10:20 |
Bayesian Context Clustering Using Cross Validation for HMM-Based Speech Synthesis |
Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda (Nagoya Institute of Technology) |
| (14) |
10:20-10:45 |
Simultaneous Transformation of Duration and Spectrum Using Statistical Models Including Time-Sequence Matching |
Kaori Yutani, Yoshihiko Nankaku (Nagoya Institute of Technology), Tomoki Toda (Nara Institute of Science and Technology), Keiichi Tokuda (Nagoya Institute of Technology) |
| (15) |
10:45-11:10 |
Aperiodicity extraction based on linear prediction and temporal axis warping using fundamental frequency information |
Hideki Kawahara (Wakayama Univ.), Masanori Morise (Kwansei Univ.), Toru Takahashi (Kyoto Univ.), Hideki Banno (Meijo Univ.), Ryuichi Nisimura, Toshio Irino (Wakayama Univ.) |
| |
11:10-11:20 |
Break ( 10 min. ) |
Wed, Dec 10 AM
11:20 - 12:35 |
| (16) |
11:20-11:45 |
Mutually-Adaptive Generation of Utterances Based on Belief Shared by Human And Robots in Real World. |
Shinya Nakamura (UEC/NICT), Naoto Iwahashi (NICT/ATR), Takayuki Nagai (The University of Electro-Communications) |
| (17) |
11:45-12:10 |
Controlling thought-evoking dialogue using POMDP |
Yasuhiro Minami, Minako Sawaki, Ryuichiro Higashinaka, Kohji Dohsaka (NTT) |
| (18) |
12:10-12:35 |
Speech recognition system for spoken dialogue system |
Toru Taniguchi, Shinya Fujie, Tetsunori Kobayashi (Waseda Univ.) |
| |
12:35-13:40 |
Lunch Break ( 65 min. ) |
Wed, Dec 10 PM
13:40 - 14:30 |
| (19) |
13:40-14:30 |
[Invited Talk]
A New Paradigm for Speech Application System Development |
Tetsunori Kobayashi (Waseda Univ.) |
| |
14:30-14:40 |
Break ( 10 min. ) |
Wed, Dec 10 PM
14:40 - 15:55 |
| (20) |
14:40-15:05 |
Progress Report of SLP Spoken Document Processing Working Group |
Tomoyoshi Akiba (Toyohashi Univ. of Tech.), Kiyoaki Aikawa (Tokyo Univ. of Tech.), Yoshiaki Itoh (Iwate Prefectural Univ.), Tatsuya Kawahara (Kyoto Univ.), Hiroaki Nanjo (Ryukoku Univ.), Hiromitsu Nishizaki (Univ. of Yamanashi), Norihito Yasuda (NTT), Yoichi Yamashita (Ritsumeikan Univ.), Tomoko Matsui (The Institute of Statistical Mathematics), Xinhui Hu (NICT/ATR), Seiichi Nakagawa (Toyohashi Univ. of Tech.), Katunobu Itou (Hosei Univ.) |
| (21) |
15:05-15:30 |
An automatic transcription system for creation of meeting records in the Japanese Congress |
Yuya Akita, Masato Mimura, Tatsuya Kawahara (Kyoto Univ.) |
| (22) |
15:30-15:55 |
Effect of punctuation marks for speech translatio unit boundary detection |
Tohru Shimizu (NICT/ATR), Satoshi Nakamura (National Institute of Information and Communication), Tatsuya Kawahara (Kyoto University) |
| |
15:55-16:10 |
Break ( 15 min. ) |
Wed, Dec 10 PM
16:10 - 18:00 |
| (23) |
16:10-18:00 |
Characteristics of pitch accents in infant-directed speech
-- An analysis of Riken Japanese Mother-Infant Conversation Corpus -- |
Mafuyu Kitahara (Waseda Univ.), Ken'ya Nishikawa (RIKEN/Keio Univ.), Yosuke Igarashi (NIJL/RIKEN), Takahito Shinya (Sophi Univ./RIKEN), Reiko Mazuka (RIKEN/Duke Univ.) |
| (24) |
16:10-18:00 |
The effect of associated conditions on the received emotional information transferred by sound effects |
Mari Sato, Kiyoaki Aikawa (Univ. of Technology) |
| (25) |
16:10-18:00 |
Physical Model of the Vocal Tract with Flexible Velum |
Takayuki Arai, Kimi Tanaka (Sophia Univ.), Ryuta Kataoka (Showa Univ.) |
| (26) |
16:10-18:00 |
Articulatory feature extraction based on 3-stage MLNs and Inhibition/Enhancement Network |
Mohammad Nurul Huda, Hiroaki Kawashima, Tsuneo Nitta (Toyohashi Univ. of Tech.) |
| (27) |
16:10-18:00 |
Parameter optimization for a fundamental frequency extractor based on TANDEM-STRAIGHT |
Hanae Itagaki, Masanori Morise, Ryuichi Nisimura, Toshio Irino, Hideki Kawahara (Wakayama Univ.) |
| (28) |
16:10-18:00 |
Study on Spectro-Temporal Features Based on Gradient Histograms |
Takashi Muroi, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) |
| (29) |
16:10-18:00 |
Automatic Speech Character Identification using Vocal Tract information |
Yusuke Watanabe, Naoki Matsumoto (Meiji Univ.) |
| (30) |
16:10-18:00 |
Evaluation of speaker identification/verification method using phase information |
Longbiao Wang (Shizuoka Univ.), Kazue Minami, Kazumasa Yamamoto, Seiichi Nakagawa (Toyohashi Univ. of Tech.) |
| (31) |
16:10-18:00 |
Dialect-based speaker classification of Chinese using acoustic features invariant with extra-linguistic factors |
XueBin Ma, Nobuaki Minematsu, Yu Qiao, Keikichi Hirose (Univ. of Tokyo), Akira Nemoto (Nankai Univ.), Feng Shi (nankai Univ.) |
| (32) |
16:10-18:00 |
Speaker Recognition Based on Gaussian Mixture Models Using Variational Bayesian Method |
Tatsuya Ito, Kei Hashimoto, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda (Nitech) |
| (33) |
16:10-18:00 |
Sudden noise reduction using dynamic speech feature model |
Nobuyuki Miyake, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) |
| (34) |
16:10-18:00 |
Speech period detection using Hough transform of distance matrix images |
Hiroyuki Nishi, Yoshimasa Kimura, Nguyen Van Don (Sojo Univ.) |
| (35) |
16:10-18:00 |
Isolated word recognition based on speech structures and discriminant analysis |
Satoshi Asakawa, Yu Qiao, Nobuaki Minematsu, Keikichi Hirose (Univ. of Tokyo) |
| (36) |
16:10-18:00 |
Speech recognition using localized affine invariant features |
Masayuki Suzuki, Yu Qiao, Nobuaki Minematsu, Keikichi Hirose (Univ. of Tokyo) |
| (37) |
16:10-18:00 |
Tying covariance parameters for HMM-based speech synthesis |
Keiichiro Oura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda (Nagoya Inusitute of Technology) |
| (38) |
16:10-18:00 |
Speech Recognition Based on Statistical Models Including Multiple Decision Trees |
Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda (Nagoya Institute of Technology) |
| (39) |
16:10-18:00 |
Recording system for controlling speaking rate (ReCoK5) and public domain speech database with speaking rate variations (SRV-DB) |
Kota Takahashi, Keigo Tsutaki, Toru Yoshihara (The University of Electro-Communications) |
| (40) |
16:10-18:00 |
Speaking rate estimation and utterance analysis of fast speech for high-speed reproduction
-- A practical example of speech database with speaking rate variations -- |
Toru Yoshihara, Keigo Tsutaki, Kota Takahashi (The University of Electro-Communications) |
| (41) |
16:10-18:00 |
All directional Fatigue Detection Using Noise Ration at Vocal Cords Level and Spectrum Q
-- Considering Working Efficiency and MAnagement for Crisis of a Speaker -- |
Kazuhide Okada (Toyota) |
| (42) |
16:10-18:00 |
Driver's irritation detection using speech recognition results |
Lucas Malta, Chiyomi Miyajima, Akira Ozaki, Norihide Kitaoka, Kazuya Takeda (Nagoya Univ.) |
| (43) |
16:10-18:00 |
Language Model Adaptation by Topic Model Based on Sequence of Words |
Atsushi Sako, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) |
| (44) |
16:10-18:00 |
Discriminative Rescoring Based on Minimization of Word Errors for Speech Recognition |
Akio Kobayashi, Takahiro Oku, Shinichi Homma, Shoei Sato, Toru Imai, Tohru Takagi (NHK) |
| (45) |
16:10-18:00 |
Verification of Speech Recognition Results Based on the Utterance Classification Using Conditional Random Fields |
Kenko Ota, Terumasa Ehara (TUS, Suwa) |
| (46) |
16:10-18:00 |
Estimation of Spoken Dialog System using Automatically-generated question-and-answer database |
Takahiro Morimoto, Masashi Ito (Tohoku Univ.), Motoyuki Suzuki (The Univ. of Tokushima), Akinori Ito, Shozo Makino (Tohoku Univ.) |
| (47) |
16:10-18:00 |
Building a Question-Answer System based on RIME-TK, a Toolkit for Dialogue and Behavior Controller of Robots and Agents |
Hiromi Narimatsu (Tsuda College), Mikio Nakano (Honda Research Institute Japan Co., Ltd.), Kotaro Funakoshi, Yuji Hasegawa, Hiroshi Tsujino (Tsuda College) |