IEICE Technical Report

Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380

Speech

Workshop Date : 2017-07-27 - 2017-07-28 / Issue Date : 2017-07-20

SP2017-15
[Invited Talk] Image Processing with Neural Networks
Satoshi Iizuka (Waseda Univ.)
p. 1

SP2017-16
[Invited Talk] Synthesis, Recognition and Conversion of Various Speech Using Deep Learning and Their Applications
Takashi Nose (Tohoku Univ.)
pp. 3 - 8

SP2017-17
Voice Conversion Using Sequence-to-Sequence Learning of Context Posterior Probabilities and Evaluation of Dual Learning
Hiroyuki Miyoshi, Yuki Saito, Shinnosuke Takamichi, Hiroshi Saruwatari (Univ. of Tokyo)
pp. 9 - 14

SP2017-18
Noise robust speech recognition based on factored deep convolutional neural networks
Masakiyo Fujimoto (NICT)
pp. 15 - 20

SP2017-19
Speaker Diarization for Face-to-Face Dialog of Service Counters Based on Appearance Pattern of Speakers
Mizuki Watabe (NTT DOCOMO), Atsushi Ando, Hosana Kamiyama, Satoshi Kobashikawa, Yushi Aono (NTT), Takanobu Oba, Yoshinori Isoda (NTT DOCOMO)
pp. 21 - 26

Note: Each article is a technical report without peer review, and its polished version will be published elsewhere.

The Institute of Electronics, Information and Communication Engineers (IEICE), Japan