Mon, Dec 15 AM 09:30 - 11:10 |
(1) SP |
09:30-09:55 |
Recognition and Analysis of Emotion in Indonesian Conversational Speech |
Nurul Lubis, Sakriani Sakti, Graham Neubig, Tomoki Toda (NAIST), Dessi Lestari, Ayu Purwarianti (ITB), Satoshi Nakamura (NAIST) |
(2) |
09:55-10:20 |
|
(3) |
10:20-10:45 |
|
(4) SP |
10:45-11:10 |
Investigation of Deep Neural Network and Cross-adaptation for Voice Activity Detection in Meeting Speech |
Akihiro Nakadani (Shizuoka Univ.), Longbiao Wang (Nagaoka Univ. of Tech.), Atsuhiko Kai (Shizuoka Univ.) |
|
11:10-11:20 |
Break ( 10 min. ) |
Mon, Dec 15 AM 11:20 - 12:20 |
(5) |
11:20-11:50 |
|
(6) |
11:50-12:20 |
|
|
12:20-13:10 |
Break ( 50 min. ) |
Mon, Dec 15 PM 13:10 - 14:50 |
(7) SP |
13:10-14:00 |
[Invited Talk]
Dialogue state tracking in statistical dialogue management |
Kai Yu, Lu Chen (SJTU) |
(8) SP |
14:00-14:50 |
[Invited Talk]
Statistical approach to flexible speech synthesis
-- towards human-like talking machines -- |
Keiichi Tokuda (NITech/Google) |
|
14:50-15:00 |
Break ( 10 min. ) |
Mon, Dec 15 PM 15:00 - 15:50 |
(9) |
15:00-15:50 |
Optimization of Large Scale Neural Networks for Speech Recognition
Michiel Bacchiani(Google) |
|
15:50-15:55 |
Break ( 5 min. ) |
Mon, Dec 15 PM 15:55 - 18:25 |
(10) |
15:55-16:25 |
|
(11) |
16:25-16:55 |
|
(12) |
16:55-17:25 |
|
(13) |
17:25-17:55 |
|
(14) |
17:55-18:25 |
|
|
18:25-18:30 |
Break ( 5 min. ) |
Mon, Dec 15 PM 18:30 - 19:45 |
(15) |
18:30-18:55 |
|
(16) |
18:55-19:20 |
|
(17) SP |
19:20-19:45 |
An experimental study of definitions of reference pronunciation distances and acoustic features used for distance prediction with the aim of pronunciation clustering |
Shun Kasahara (Univ. of Tokyo), Tianze Shi (Tsinghua Univ.), Nobuaki Minematsu, Daisuke Saito, Keikichi Hirose (Univ. of Tokyo) |
Tue, Dec 16 AM 09:15 - 10:45 |
(18) |
09:15-09:45 |
|
(19) |
09:45-10:15 |
|
(20) |
10:15-10:45 |
|
|
10:45-11:00 |
Break ( 15 min. ) |
Tue, Dec 16 AM 11:00 - 12:30 |
(21) |
11:00-12:30 |
|
(22) SP |
11:00-12:30 |
Articulatory Controllable Speech Modification using Sequential Inversion and Production Mapping with Gaussian Mixture Models |
Patrick Lumban Tobing, Tomoki Toda, Graham Neubig, Sakriani Sakti, Satoshi Nakamura (NAIST), Ayu Purwarianti (ITB) |
(23) SP |
11:00-12:30 |
Prosody Correction Preserving Speaker Individuality in English-Read-By-Japanese Speech Synthesis Based on HMM |
Yuji Oshima, Shinnosuke Takamichi, Tomoki Toda, Graham Neubig, Sakriani Sakti, Satoshi Nakamura (NAIST) |
(24) SP |
11:00-12:30 |
Noise robust speech recognition by non-negative matrix factorization using GMM clustering in MFCC domain |
Kentaro Fujigaki, Yosuke Kashiwagi, Daisuke Saito, Nobuaki Minematsu, Keikichi Hirose (Univ. of Tokyo) |
(25) SP |
11:00-12:30 |
Many-to-one Voice Conversion using Multiple Non-negative Matrix Factorization |
Ryo Aihara, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) |
(26) SP |
11:00-12:30 |
HMM-Based Speech Synthesis System with Prosody Modification Based on Speech Input |
Yuri Nishigaki, Shinnosuke Takamichi, Tomoki Toda, Graham Neubig, Sakriani Sakti, Satoshi Nakamura (NAIST) |
(27) SP |
11:00-12:30 |
Multimodal Voice Conversion using Weighted Features in Noisy Environments |
Kenta Masaka, Ryo Aihara, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) |
(28) |
11:00-12:30 |
|
(29) SP |
11:00-12:30 |
Voice conversion based on deep neural network with multiple output sub-networks |
Tetsuya Hashimoto, Yosuke Kashiwagi, Daisuke Saito, Keikichi Hirose, Nobuaki Minematsu (Univ. of Tokyo) |
(30) SP |
11:00-12:30 |
Speaker adaptation using speaker-normalized DNN based on speaker codes |
Yosuke Kashiwagi, Daisuke Saito, Nobuaki Minematsu, Keikichi Hirose (Univ. of Tokyo) |
(31) |
11:00-12:30 |
|
(32) |
11:00-12:30 |
|
(33) |
11:00-12:30 |
|
(34) |
11:00-12:30 |
|
|
12:30-13:30 |
Break ( 60 min. ) |
Tue, Dec 16 PM 13:30 - 15:15 |
(35) SP |
13:30-15:00 |
[Poster Presentation]
Deep neural network-based feature transformation for reverberant speaker identification |
Zhaofeng Zhang, Longbiao Wang (NUT), Atsuhiko Kai (Shizuoka Univ.), Weifeng Li (Tsinghua Univ.), Masahiro Iwahashi (NUT) |
(36) |
13:30-15:00 |
|
(37) SP |
13:30-15:00 |
[Poster Presentation]
Accent identification by conbining GMM and DNN under reverberant environment |
Ryota Sakagami, Longbiao Wang, Zhang Zhaofeng, Khomdet Phapatanaburi, Masahiro Iwahashi (NUT) |
(38) SP |
13:30-15:00 |
[Poster Presentation]
speech selection and environmental adaptation for asynchronous speech recording based on deep neural network |
Bo Ren, Longbiao Wang (Nagaoka Univ. of Tech.), Atsuhiko Kai (Shizuoka Univ.) |
(39) SP |
13:30-15:00 |
STD for SQ using MSRR |
Satoshi Oshima, Yoshiaki Itoh (Iwate Prefectural Univ.) |
(40) SP |
13:30-15:00 |
A Study on Speaker Recognition Method in Consideration of Speaking Style Differences in Lecture Speech |
Kota Nakatsuji (Doshisha Univ.), Masafumi Nishida (Nagoya Univ.), Seiichi Yamamoto (Doshisha Univ.) |
(41) SP |
13:30-15:00 |
[Poster Presentation]
relationship between speakers' characteristics and the information transmission quality in Dialog |
Bohan Chen (Nagoya Univ.), Norihide Kitaoka (Tokushima Univ.), Kazuya Takeda (Nagoya Univ.) |
(42) SP |
13:30-15:00 |
[Poster Presentation]
Automatic Language Identification Based on Posterior Probability on Articulatory Classes |
Takumi Hirata, Kazuyuki Takagi (UEC) |
(43) |
13:30-15:00 |
|
(44) SP |
13:30-15:00 |
[Poster Presentation]
Voice Conversion Using Speaker Adapted Restricted Boltzmann Machine |
Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) |
(45) |
13:30-15:00 |
|
(46) |
13:30-15:00 |
|
(47) |
13:30-15:00 |
|
(48) |
13:30-15:00 |
|
(49) |
13:30-15:00 |
|
(50) NLC |
13:30-15:00 |
Twitter users' characteristics and their emotional expressions in the tweets |
Atsumi Taketomi, Masaki Hisano (UEC) |
|
15:00-15:10 |
Break ( 10 min. ) |
|
- |
Opening (5 minutes) |
Tue, Dec 16 PM 15:15 - 16:30 |
(51) |
15:15-15:40 |
|
(52) |
15:40-16:05 |
|
(53) |
16:05-16:30 |
|
|
16:30-16:40 |
Break ( 10 min. ) |
Tue, Dec 16 PM 16:40 - 17:55 |
(54) NLC |
16:40-17:05 |
Words have no meanings. (Digital Linguistics)
-- The Meaning Mechanism of Complex Concept 'Self-Reproducing Automata' -- |
Kimiaki Tokumaru (Natural Philosopher) |
(55) NLC |
17:05-17:30 |
The Trial Analysis of the Response Words to the Stimulus Word "Radiation"
-- Based on the Result of the Association Test Given to the 6th Graders of Elementary School Children Before and After the Radiation Class -- |
Hiroko Miyuki (Kyoto Univ.) |
(56) |
17:30-17:55 |
|
Wed, Dec 17 AM 09:00 - 10:45 |
|
- |
Greetings (5 minutes) |
(57) NLC |
09:05-09:30 |
Qualitative Evaluation of Available Japanese Resources for Lexical Paraphrasing |
Tomoyuki Kajiwara, Kazuhide Yamamoto (NUT) |
(58) NLC |
09:30-09:55 |
Selecting Noun Concepts Based on Accounting Data
-- As a Mechanism in the Integrated Narrative Generation System -- |
Jumpei Ono, Takashi Ogata (Iwate Prefectural Univ.) |
(59) NLC |
09:55-10:20 |
Constructing an Automatic Anotator of Semantic Role Label and Frame of Predicate Thesaurus |
Yoshimasa Ikeda, Koichi Takeuchi (Okayama Univ.) |
(60) |
10:20-10:45 |
|
|
10:45-10:55 |
Break ( 10 min. ) |
Wed, Dec 17 AM 10:55 - 11:45 |
(61) |
10:55-11:20 |
|
(62) |
11:20-11:45 |
|
|
11:45-13:00 |
Lunch Break ( 75 min. ) |
Wed, Dec 17 PM 13:00 - 14:15 |
(63) NLC |
13:00-13:25 |
Narrative Focalization Mechanisms and the Implementation in the Integrated Narrative Generation System |
Taisuke Akimoto (UEC), Takashi Ogata (IPU) |
(64) |
13:25-13:50 |
|
(65) NLC |
13:50-14:15 |
Construction of Hotel Review Analyzing System for Helping Hotel Refurbishment |
Takuma Monden, Koichi Takeuchi (Okayama Univ.) |
|
14:15-14:25 |
Break ( 10 min. ) |
Wed, Dec 17 PM 14:25 - 15:25 |
(66) |
14:25-15:25 |
EMNLP 2014 report (60 minutes)
Yo Ehara (NICT), Nobuhiro Kaji (University of Tokyo), Hiroshi Kanayama (IBM) |
|
15:25-15:35 |
Break ( 10 min. ) |
Wed, Dec 17 PM 15:35 - 16:50 |
(67) NLC |
15:35-16:00 |
Link Generation for TV Programs based on Semantic Relations between Words |
Kikuka Miura, Ichiro Yamada, Taro Miyazaki, Masaru Miyazaki, Atsushi Matsui, Naoto Kato, Hideki Sumiyoshi, Hideki Tanaka (NHK) |
(68) |
16:00-16:25 |
|
(69) |
16:25-16:50 |
|
|
16:50-17:00 |
Break ( 10 min. ) |
Wed, Dec 17 PM NL/NLC Challengeing Topics 17:00 - 18:20 |
(70) |
17:00-17:25 |
|
(71) NLC |
17:25-17:50 |
Detecting Novel Allergy Risks by Using Crowdsourcing
-- the semi-automatic research from hypothesis making to experimentation -- |
Eiji Aramaki, Shuko Shikata (Kyoto University), Eriko Watabe (IRALT), Mai Miyabe, Yasuyuki Usuda (Kyoto University), Satsuki Ayaya, Shinichiro Kumagaya (Univ. of Tokyo) |
(72) |
17:50-18:15 |
|
|
- |
Closing (5 minutes) |