Information and Systems-Speech(Date:2016/08/24)

Presentation
Daily Activity Recognition Based on Recurrent Neural Network

Akira Tamamori(Nagoya Univ.),  Tomoki Hayashi(Nagoya Univ.),  Tomoki Toda(Nagoya Univ.),  Kazuya Takeda(Nagoya Univ.),  

[Date]2016-08-24
[Paper #]SP2016-28
［ポスター講演］マルチチャネル音源分離のためのネスト型基底・音源混合モデルに基づく時間周波数クラスタリング

Kousuke Itakura(Kyoto Univ.),  Yoshiaki Bando(Kyoto Univ.),  Eita Nakamura(Kyoto Univ.),  Katsutoshi Itoyama(Kyoto Univ.),  Kazuyoshi Yoshii(Kyoto Univ.),  Tatsuya Kawahara(Kyoto Univ.),  

[Date]2016-08-24
[Paper #]SP2016-31
[Poster Presentation] Joint Enhancement of Spectral and Cepstral Sequences of Noisy Speech

Li Li(Univ.Tsukuba),  Hirokazu Kameoka(NTT),  Takuya Higuchi(NTT),  Hiroshi Saruwatari(Univ.Tokyo),  Shoji Makino(Univ.Tsukuba),  

[Date]2016-08-24
[Paper #]SP2016-32
［ポスター講演］LSTMによる単語履歴を考慮した未知語検出法

Yuki Ikeshita(Tokyo Tech),  Takahiro Shinozaki(Tokyo Tech),  

[Date]2016-08-24
[Paper #]SP2016-33
Adaptation Methods for Daily Activity Recognition Based on Deep Neural Network

Tomoki Hayashi(Nagoya Univ.),  Norihide Kitaoka(Tokushima Univ.),  Tomoki Toda(Nagoya Univ.),  Kazuya Takeda(Nagoya Univ.),  

[Date]2016-08-24
[Paper #]SP2016-27
[Invited Talk] Extension of Array Signal Processing to Asynchronous Distributed Channels

Nobutaka Ono(NII),  

[Date]2016-08-24
[Paper #]SP2016-30
[Invited Talk] Unsupervised Music Understanding based on Hierarchical Bayesian Acoustic and Language Models

Kazuyoshi Yoshii(Kyoto Univ.),  

[Date]2016-08-24
[Paper #]SP2016-29
[Poster Presentation] Extraction of brain activity related to auditory impressions induced by HVAC sound using non-negative tensor decomposition

Hajime Yano(Kobe Univ.),  Tetsuya Takiguchi(Kobe Univ.),  Yasuo Ariki(Kobe Univ.),  Takuya Hotehama(AIST),  Masaru Kamiya(DENSO),  Seiji Nakagawa(Chiba Univ.),  

[Date]2016-08-24
[Paper #]SP2016-34
変分ベイズ多チャネルロバストNMFに基づくマイクロホンの移動・被覆を許容する音声強調

Yoshiaki Bando(Kyoto Univ.),  Katsutoshi Itoyama(Kyoto Univ.),  Masashi Konyo(Tohoku Univ.),  Satoshi Tadokoro(Tohoku Univ.),  Kazuhiro Nakadai(Tokyo Tech/HRI-JP),  Kazuyoshi Yoshii(Kyoto Univ.),  Tatsuya Kawahara(Kyoto Univ.),  Hiroshi G. Okuno(Waseda Univ.),  

[Date]2016-08-25
[Paper #]SP2016-36
Diversity-driven Semi-supervised Ensemble DNN Acoustic Model Training

Sheng Li(Kyoto Univ.),  Xugang Lu(NICT),  Shinsuke Sakai(Kyoto Univ.),  Tatsuya Kawahara(Kyoto Univ.),  

[Date]2016-08-25
[Paper #]SP2016-40
Sound collection systems using a crowdsourcing approach for constructing subjective evaluation-based sound maps

Sunao Hara(Okayama Univ.),  Shota Kobayashi(Okayama Univ.),  Masanobu Abe(Okayama Univ.),  

[Date]2016-08-25
[Paper #]SP2016-35
Pronunciation Error Detection using DNN Articulatory Model based on Transfer Learning

Richeng Duan(Kyoto Univ.),  Tatsuya Kawahara(Kyoto Univ.),  Masatake Dantsuji(Kyoto Univ.),  

[Date]2016-08-25
[Paper #]SP2016-39
複数スマートフォンで収録された会話音声の対話グループ検出と話者決定の性能改善

Koji Iwano(Tokyo City Univ.),  Yuki Arake(Tokyo City Univ.),  Yuki Kodaira(Tokyo City Univ.),  Koichi Shinoda(TokyoTech),  

[Date]2016-08-25
[Paper #]SP2016-37
Parallel Dictionary Learning for Voice Conversion Using Discriminative Graph-embedded Non-negative Matrix Factorization

Ryo Aihara(Kobe Univ.),  Tetsuya Takiguchi(Kobe Univ.),  Yasuo Ariki(Kobe Univ.),  

[Date]2016-08-25
[Paper #]SP2016-38