Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380
[TOP] | [2013] | [2014] | [2015] | [2016] | [2017] | [2018] | [2019] | [Japanese] / [English]
SP2016-20
Evaluation of Japanese English DNN Acoustic Models with English Level
Yuta Kawachi, Hirokazu Masataki, Taichi Asami, Yushi Aono (NTT)
pp. 1 - 6
SP2016-21
Effective Basis Matrices Selection and Weight Parameter Estimation for Basis fMLLR
Hiroki Kanagawa, Yuuki Tachioka, Tomohiro Narita (Mitsubishi Electric Corp.)
pp. 7 - 12
SP2016-22
On the Use of Speaker Codes for Multi-Speaker Modeling in DNN-based Speech Synthesis
Nobukatsu Hojo, Yusuke Ijima (NTT), Hideyuki Mizuno (Tokyo University of Science, Suwa)
pp. 13 - 18
SP2016-23
[Invited Talk]
Natural Language Processing for Various Texts
Shinsuke Mori (Kyoto Univ.)
p. 19
SP2016-24
[Invited Talk]
Recent Researches and Introduction of DNN in Spoken Term Detection
Yoshiaki Itoh, Ryota Konno, Masato Obara (IPU), Shi-wook Lee (AIST), Kazuyo Tanaka (Univ. of Tsukuba)
pp. 21 - 26
SP2016-25
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, Yoshiaki Itoh (IPU)
pp. 27 - 32
SP2016-26
Discriminative Training Method of Recurrent Neural Network Language Models for Speech Recognition
Yuuki Tachioka (Mitsubishi Electric), Shinji Watanabe (MERL)
pp. 33 - 38
Note: Each article is a technical report without peer review, and its polished version will be published elsewhere.