IEICE Technical Report

Online edition: ISSN 2432-6380

Speech

Workshop Date : 2018-07-26 - 2018-07-27 / Issue Date : 2018-07-19

SP2018-16
[Invited Talk] Fundamentals and Research Trends on Acoustic Event and Scene Analysis
Keisuke Imoto (Ritsumeikan Univ.)
pp. 1 - 6

SP2018-17
[Invited Talk] Docomo AI Agent: Open Partner Initiative -- Project SEBASTIEN --
Takanobu Oba, Takashi Yoshikawa (Docomo), Takaaki Fukutomi, Kiyoaki Matsui, Yusuke Ijima (NTT)
pp. 7 - 8

SP2018-18
Ladder Network Driven from Auditory Computational Model for Multi-talker Speech Separation
Hiroshi Sekiguchi, Yoshiaki Narusue, Hiroyuki Morikawa (Univ. of Tokyo)
pp. 9 - 13

SP2018-19
Single channel noisy speech recognition based on combination of noisy speech and enhanced speech
Masakiyo Fujimoto, Hisashi Kawai (NICT)
pp. 15 - 20

SP2018-20
Knowledge Distillation from Neural Network Based Acoustic Model based on Different Decision Tree
Takashi Fukuda, Samuel Thomas (IBM)
pp. 21 - 24

SP2018-21
Spoken Term Detection Using Speech Comparator by Machine Learning for Zero-Resource Language
Akinori Ito, Masatoshi Koizumi (Tohoku Univ.)
pp. 25 - 30

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