===============================================
Technical Committee on Speech (SP)
Chair: Hisashi Kawai (NICT) Vice Chair: Akinobu Ri (Nagoya Inst. of Tech.)
Secretary: Hiroaki Nanjo (Kyoto Univ.), Tetsuji Ogawa (Waseda Univ.)
Assistant: Tomoki Koriyama (Univ. of Tokyo), Yusuke Ijima (NTT)
DATE:
Tue, Jan 28, 2020 13:30 - 16:40
Wed, Jan 29, 2020 09:10 - 11:55
PLACE:
TOPICS:
----------------------------------------
Tue, Jan 28 PM (13:30 - 15:40)
----------------------------------------
(1) 13:30 - 14:20
----- Break ( 5 min. ) -----
(2) 14:25 - 14:50
(3) 14:50 - 15:15
(4) 15:15 - 15:40
----- Break ( 10 min. ) -----
----------------------------------------
Tue, Jan 28 PM (15:50 - 16:40)
----------------------------------------
(5) 15:50 - 16:15
Measurement of momentum change in joint range using high-speed rtMRI movie
Takuya Asai, Hideaki Kikuchi (Waseda University), Kikuo Maekawa (NINJAL)
(6) 16:15 - 16:40
Multi-Speaker Speech Synthesis from EMA Data
Kouichi Katsurada (Tokyo Univ. Sci.), Korin Richmond (Univ. of Edinburgh)
----------------------------------------
Wed, Jan 29 AM (09:10 - 10:25)
----------------------------------------
(7) 09:10 - 10:00
[Invited Talk]
Multilevel modeling for Musical Temperament Analysis of Noh Singing
Katunobu Itou (Hosei Univ.), Toshifumi Tanaka (Kongoh School)
(8) 10:00 - 10:25
Conversation situation analysis that uses language independent information
-- Detection of reception trouble situation such as contact centers --
Naoshi Matsuo (FUJITSU LABORATORIES)
----- Break ( 15 min. ) -----
----------------------------------------
Wed, Jan 29 AM (10:40 - 11:55)
----------------------------------------
(1) 10:40 - 11:05
Near-speech Separation by BLSTM using Separated Speeches based on Spherical-harmonic-analysis
Sota Nishiguchi (Hosei Univ.), Yuma Koizumi, Noboru Harada (NTT), Katunobu Itou (Hosei Univ.)
(2) 11:05 - 11:30
Keyword spotting with few keyword utterances for adaptation
Ning Ding, Takehiko Kagoshima, Hiroshi Fujimura, Daiki Tanaka, Daichi Hayakawa (Toshiba)
(3) 11:30 - 11:55
Application of Deep Gaussian Process to Multi-Speaker Text-to-Speech Synthesis using Speaker Codes
Kentaro Mitsui, Tomoki Koriyama, Hiroshi Saruwatari (UTokyo)
# Information for speakers
General Talk will have 20 minutes for presentation and 5 minutes for discussion.
=== Technical Committee on Speech (SP) ===
# FUTURE SCHEDULE:
Mon, Mar 2, 2020 - Tue, Mar 3, 2020: Okinawa Industry Support Center [Fri, Jan 17]
Last modified: 2020-01-23 20:38:55
|
Notification: Mail addresses are partially hidden against SPAM.
|