Wed, Dec 2 AM 10:00 - 12:50 |
(1) SP |
10:00-10:25 |
Voice Conversion based on Projection to Speaker Space Bases constructed by Deep Neural Network |
Tetsuya Hashimoto, Yosuke Kashiwagi, Daisuke Saito, Minematsu Nobuaki (UTokyo) |
(2) SP |
10:25-10:50 |
Simultaneous Modelling of Acoustic, Phonetic, Speaker Features Using Improved Three-Way Restricted Boltzmann Machine |
Toru Nakashika (UEC), Tetsuya Takiguchi (Kobe Univ.) |
(3) SP |
10:50-11:15 |
Parallel Dictionary Learning for Voice Conversion Using Alternating Direction Method of Multipliers |
Ryo Aihara, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) |
(4) SP |
11:15-11:40 |
Evaluation and Analysis of Duration Correction for Non-Native Speech Based on Waveform Modification |
Shinya Kura, Shinnosuke Takamichi (NAIST), Tomoki Toda (NAIST/Nagoya Univ.), Graham Neubig, Sakriani Sakti, Satoshi Nakamura (NAIST) |
|
11:40-12:50 |
Break ( 70 min. ) |
Wed, Dec 2 PM 12:50 - 13:55 |
(5) SP |
12:50-13:50 |
[Invited Talk]
When will computer speech technologies exceed human abilities ? |
Seiichi Nakagawa (TUT) |
|
13:50-13:55 |
Break ( 5 min. ) |
Wed, Dec 2 PM 13:55 - 15:15 |
(6) SP |
13:55-14:20 |
Automation of high performance system building for large vocabulary speech recognition using evolution strategy with pareto optimality |
Takafumi Moriya, Tomohiro Tanaka, Takahiro Shinozaki (Tokyo Tech), Shinji Watanabe (MERL), Kevin Duh (NAIST) |
(7) SP |
14:20-14:45 |
Investigation of DNN Based Distant-Talking Speech Enhancement |
Zeyan Oo, Longbiao Wang, Masahiro Iwahashi (NUT) |
(8) |
14:45-15:10 |
|
|
15:10-15:15 |
Break ( 5 min. ) |
Wed, Dec 2 PM 15:15 - 16:30 |
(9) |
15:15-16:15 |
|
|
16:15-16:30 |
Break ( 15 min. ) |
Wed, Dec 2 PM 16:30 - 18:00 |
(10) SP |
16:30-18:00 |
Distant-talking speech recognition by reverberation-aware denoising autoencoder |
Yuma Ueda (Shizuoka Univ.), Longbiao Wang (Nagaoka Univ.), Atsuhiko Kai (Shizuoka Univ.) |
(11) SP |
16:30-18:00 |
Evaluation of estimation accuracy of vocal tract shape by using FDTD simulation in extraction method of vocal tract area function |
Takaaki Kondo, Hideki Banno, Kensaku Asahi (Meijo Univ.) |
(12) SP |
16:30-18:00 |
An analysis of difference among singers in kurtosis of LPC residual spectrum of breathy vowel voice |
Masahiro Itou, Hideki Banno, Kensaku Asahi (Meijo Univ.) |
(13) |
16:30-18:00 |
|
(14) |
16:30-18:00 |
|
(15) |
16:30-18:00 |
|
(16) |
16:30-18:00 |
|
Thu, Dec 3 AM 08:50 - 09:00 |
(17) |
08:50-09:00 |
|
Thu, Dec 3 AM 09:00 - 10:20 |
(18) SP |
09:00-09:25 |
Evaluation of text-to-speech system construction for unknown-pronunciation languages |
Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda (Nagoya Inst. of Tech.) |
(19) SP |
09:25-09:50 |
Deep Auto-encoder based Low-dimensional Feature Extraction using FFT Spectral Envelopes in Statistical Parametric Speech Synthesis |
Shinji Takaki, Junichi Yamagishi (NII) |
(20) SP |
09:50-10:15 |
Multi-speaker speech synthesis and speaker adaptation based on deep bidirectional long short-term memory recurrent neural network |
Yi Zhao, Nobuaki Minematsu, Daisuke Saito (UTokyo) |
|
10:15-10:20 |
Break ( 5 min. ) |
Thu, Dec 3 AM 10:20 - 11:25 |
(21) SP |
10:20-11:20 |
[Invited Talk]
Statistical speech synthesis: past, present and future |
Keiichi Tokuda (NITECH) |
|
11:20-11:25 |
Break ( 5 min. ) |
Thu, Dec 3 AM 11:25 - 11:50 |
(22) |
11:25-11:50 |
|
Thu, Dec 3 AM 11:50 - 12:40 |
(23) SP |
11:50-12:15 |
Analyzing the human-human dialog and examining to build WOZ system for estimating the user's willingness to talk |
Yuya Chiba, Akinori Ito (Tohoku Univ.) |
(24) SP |
12:15-12:40 |
Unsupervised Sentence Compression of Speech Recognition Results Dealing with Speech Recognition Error |
Takaaki Sato (NTT), Takanobu Oba (NTT docomo), Hirokazu Masataki, Yushi Aono (NTT) |
Thu, Dec 3 PM 13:30 - 15:30 |
(1) NLC |
13:30-15:30 |
[Poster Presentation]
Extracting Relationship of Meeting Minutes Generated By Speech Recognition System based on phonemes |
Motoki Ito, Seikoh Nishita (Takushoku Univ.) |
(2) NLC |
13:30-15:30 |
[Poster Presentation]
Harnessing Chat Logs and User Profiles for Recurrent Neural Network Based Casual Conversation Generation |
Mitsuharu Makita, Roman Shtykh (CyberAgent) |
(3) NLC |
13:30-15:30 |
[Poster Presentation]
A Study of Semantic Role Labels for Annotating Predicate-Argument Structure Thesaurus to BCCWJ |
Koichi Takeuchi (Okayama Univ.) |
(4) NLC |
13:30-15:30 |
Detection of Mathematical Formula Regions in Images of Scientific Papers by using Deep Learning and OCR |
Shintaro Date, Hideki Isozaki (Okayama Pref. Univ.) |
(5) |
13:30-15:30 |
|
(6) |
13:30-15:30 |
|
|
15:30-15:45 |
Break ( 15 min. ) |
Thu, Dec 3 PM 15:45 - 16:55 |
(7) NLC |
15:45-15:55 |
[Invited Lecture]
International Conference Report EMNLP 2015 (1) |
Shinsuke Mori (Kyoto Univ.) |
(8) NLC |
15:55-16:15 |
[Invited Lecture]
EMNLP 2015 Report (2)
-- In terms of Deep Learning -- |
Ryo Masumura (NTT) |
(9) NLC |
16:15-16:35 |
[Invited Lecture]
EMNLP 2015 Report (3)
-- Recent Trends of Morphological Analysis -- |
Hajime Morita (Kyoto Univ.) |
(10) NLC |
16:35-16:55 |
[Invited Lecture]
EMNLP 2015 Report (4)
-- Document Summarization -- |
Hayato Kobayashi (Yahoo) |
Fri, Dec 4 AM 09:30 - 11:30 |
(11) |
09:30-10:00 |
|
(12) |
10:00-10:30 |
|
(13) |
10:30-11:00 |
|
(14) |
11:00-11:30 |
|
|
11:30-13:00 |
Break ( 90 min. ) |
Fri, Dec 4 PM 13:00 - 14:00 |
(15) NLC |
13:00-13:30 |
Book Explorer Based on User's Reading/Writing Experience |
Takumi Oikawa, Yasuyuki Sumi (FUN) |
(16) NLC |
13:30-14:00 |
Summarization of Free Description Questionnaires Using Topic Model |
Yusuke Ota, Takashi Hattori, Tatsuya Hagino (Keio Univ.) |
|
14:00-14:20 |
Break ( 20 min. ) |
Fri, Dec 4 PM 14:20 - 15:50 |
(17) |
14:20-14:50 |
|
(18) |
14:50-15:20 |
|
(19) |
15:20-15:50 |
|
|
15:50-16:00 |
Closing Adress ( 10 min. ) |