Information and Systems-Speech(Date:2016/07/28)

Presentation
On the Use of Speaker Codes for Multi-Speaker Modeling in DNN-based Speech Synthesis

Nobukatsu Hojo(NTT),  Yusuke Ijima(NTT),  Hideyuki Mizuno(Tokyo University of Science, Suwa),  

[Date]2016-07-28
[Paper #]SP2016-22
Evaluation of Japanese English DNN Acoustic Models with English Level

Yuta Kawachi(NTT),  Hirokazu Masataki(NTT),  Taichi Asami(NTT),  Yushi Aono(NTT),  

[Date]2016-07-28
[Paper #]SP2016-20
Effective Basis Matrices Selection and Weight Parameter Estimation for Basis fMLLR

Hiroki Kanagawa(Mitsubishi Electric Corp.),  Yuuki Tachioka(Mitsubishi Electric Corp.),  Tomohiro Narita(Mitsubishi Electric Corp.),  

[Date]2016-07-28
[Paper #]SP2016-21
[Invited Talk] Recent Researches and Introduction of DNN in Spoken Term Detection

Yoshiaki Itoh(IPU),  Ryota Konno(IPU),  Masato Obara(IPU),  Shi-wook Lee(AIST),  Kazuyo Tanaka(Univ. of Tsukuba),  

[Date]2016-07-29
[Paper #]SP2016-24
[Invited Talk] Natural Language Processing for Various Texts

Shinsuke Mori(Kyoto Univ.),  

[Date]2016-07-29
[Paper #]SP2016-23
A study of acustic distance construction methods for spoken term detection

Ryota Konno(IPU),  Shi-wook Lee(AIST),  Kazuyo Tanaka(Univ. of Tsukuba),  Kazunori Kojima(IPU),  Yoshiaki Itoh(IPU),  

[Date]2016-07-29
[Paper #]SP2016-25
Discriminative Training Method of Recurrent Neural Network Language Models for Speech Recognition

Yuuki Tachioka(Mitsubishi Electric),  Shinji Watanabe(MERL),  

[Date]2016-07-30
[Paper #]SP2016-26