Information and Systems-Speech(Date:2018/08/27)

Presentation
［ポスター講演］転移学習による注意機構付き単語単位音声認識の適応

Sei Ueno(NTT/Kyoto Univ),  Takafumi Moriya(NTT),  Masato Mimura(Kyoto Univ),  Shinsuke Sakai(Kyoto Univ),  Yusuke Shinohara(NTT),  Yoshikazu Yamaguchi(NTT),  Yushi Aono(NTT),  Tatsuya Kawahara(Kyoto Univ),  

[Date]2018-08-27
[Paper #]SP2018-23
Simple method for detecting GCI and GOI based on complex wavelet analysis with cosine series envelope

Hideki Kawahara(Wakayama Univ.),  Ken-Ichi Sakakibara(Health Science Univ. Hokkaido),  

[Date]2018-08-27
[Paper #]SP2018-22
[Poster Presentation] Discrimination of pharyngeal residue using swallowing sound in dysphagia diagnosis

Tatsunori Uchino(Nagoya Univ.),  Atsushi Hashizume(Nagoya Univ.),  Masahisa Katsuno(Nagoya Univ.),  Tomoki Toda(Nagoya Univ.),  

[Date]2018-08-27
[Paper #]SP2018-27
[Poster Presentation] Question answering system by integration of intention understanding and keyword extraction using attention-based LSTM

Yuki Matsuyoshi(Kobe Univ.),  Tetsuya Takiguchi(Kobe Univ.),  Yasuo Ariki(Kobe Univ.),  

[Date]2018-08-27
[Paper #]SP2018-24
[Poster Presentation] A Study on Representation of Speaker Information for DNN Speech Synthesis

Lin Yuhan(Ritsumeikan Univ.),  Keisuke Imoto(Ritsumeikan Univ.),  Masahiro Niitsuma(Ritsumeikan Univ.),  Ryosuke Yamanishi(Ritsumeikan Univ.),  Yoichi Yamashita(Ritsumeikan Univ.),  

[Date]2018-08-27
[Paper #]SP2018-25
Sound Event Encoder Using Onomatopoeic Representations based on End-to-End Approach

Koichi Miyazaki(Nagoya Univ.),  Tomoki Hayashi(Nagoya Univ.),  Tomoki Toda(Nagoya Univ.),  Kazuya Takeda(Nagoya Univ.),  

[Date]2018-08-27
[Paper #]SP2018-30
[Invited Talk] Interface Development and Visualization Based on Information Processing for Music and Singing Voices

Tomoyasu Nakano(AIST),  

[Date]2018-08-27
[Paper #]SP2018-31
[Poster Presentation] An Experimental Study on Transforming the Emotion in Speech using GAN

Kenji Yasuda(UEC),  Ryohei Orihara(UEC),  Yuichi Sei(UEC),  Yasuyuki Tahara(UEC),  Akihiko Ohsuga(UEC),  

[Date]2018-08-27
[Paper #]SP2018-26
Neural Error Corrective Language Models with Multiple Hypotheses

Tomohiro Tanaka(NTT),  Ryo Masumura(NTT),  Yushi Aono(NTT),  

[Date]2018-08-27
[Paper #]SP2018-29
[Invited Talk] Product models and semi-supervised word segmentation

Daichi Mochihashi(ISM),  

[Date]2018-08-27
[Paper #]SP2018-28