Online edition: ISSN 2432-6380
[TOP] | [2016] | [2017] | [2018] | [2019] | [2020] | [2021] | [2022] | [Japanese] / [English]
SP2019-1
A study on style transplantation modeling techniques for DNN-based speech synthesis
Yoshiki Hiruta (Tokyo Tech), Tomoki Koriyama (The Univ. of Tokyo), Yuuki Tachioka (Denso IT Lab), Takao Kobayashi (Tokyo Tech)
pp. 1 - 6
SP2019-2
Collection of large-scale Japanese articulatory-acoustic parallel data
Kohei Wakamiya, Fumiaki Taguchi, Riko Watanabe (Kyushu Univ.), Kouichi Katsurada (Tokyo Univ. of Science), Takehiko Makino (Chuo Univ.), Tokihiko Kaburagi (Kyushu Univ.)
pp. 7 - 12
SP2019-3
A large collection of sentences read aloud by Vietnamese learners of Japanese and native speakers' reverse shadowings
Shintaro Ando, Tasavat Trisitichoke, Yusuke Inoue, Fuki Yoshizawa, Daisuke Saito, Nobuaki Minematsu (UTokyo)
pp. 13 - 17
SP2019-4
Evaluation of Comprehensibility of L2 Speech Based on Native Listeners’ Reverse Shadowing and Their Facial Expressions
Tasavat Trisitichoke, Shintaro Ando, Daisuke Saito, Nobuaki Minematsu (UTokyo)
pp. 19 - 24
SP2019-5
[Invited Talk]
Constructing voice corpus for next-generation speech research
Shinnosuke Takamichi (UTokyo)
p. 25
Note: Each article is a technical report without peer review, and its polished version will be published elsewhere.