Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
SP |
2014-11-13 13:45 |
Fukuoka |
Kyushu Univ. Chikushi Campus |
A comparative study of paralinguistic information control methods for HMM-based dialogue speech synthesis Hiroki Mori, Shunsuke Takahashi, Tomohiro Nagata (Utsunomiya Univ.) SP2014-90 |
Toward the realization of dialogue speech synthesis with capability to
control paralinguistic information,
we have pro... [more] |
SP2014-90 pp.1-6 |
SP |
2014-11-13 14:10 |
Fukuoka |
Kyushu Univ. Chikushi Campus |
Variable factor of laughter in an utterance for dialogue speech synthesis Tomohiro Nagata, Hiroki Mori (Utsunomiya Univ.) SP2014-91 |
[more] |
SP2014-91 pp.7-12 |
SP |
2014-11-13 14:35 |
Fukuoka |
Kyushu Univ. Chikushi Campus |
Shared emotion additive model for HMM-based emotional speech synthesis Yamato Ohtani, Yu Nasu, Ryo Morinaka, Masatsune Tamura, Masahiro Morita, Masami Akamine (Toshiba) SP2014-92 |
We have proposed an emotion addition method based on additive structure in HMM-based speech synthesis.
This technique ... [more] |
SP2014-92 pp.13-18 |
SP |
2014-11-13 15:15 |
Fukuoka |
Kyushu Univ. Chikushi Campus |
[Invited Talk]
Speech Synthesis for Conversation System Tetsunori Kobayashi, Kazuhiko Iwata (Waseda Univ.) SP2014-93 |
The essence of the conversation is efficient information transfer, which is realized by immediate interaction of rich in... [more] |
SP2014-93 pp.19-24 |
SP |
2014-11-13 16:30 |
Fukuoka |
Kyushu Univ. Chikushi Campus |
A study on intuitive control of emotional expressions and speaking styles using facial features by Kinect Yu Bi, Takashi Nose, Akinori Ito (Tohoku Univ.) SP2014-94 |
This paper proposes a style control technique of synthetic speech based on multiple regression HSMM (MRHSMM) using facia... [more] |
SP2014-94 pp.25-30 |
SP |
2014-11-13 16:55 |
Fukuoka |
Kyushu Univ. Chikushi Campus |
Emphasized Accent Phrase Prediction from Advertisement Text towards Expressive Text-to-speech Synthesis Hideharu Nakajima, Hideyuki Mizuno, Sumitaka Sakauchi (NTT) SP2014-95 |
Realizing Expressive Text-to-speech synthesis needs developments of both text processing and the rendering of natural ex... [more] |
SP2014-95 pp.31-36 |
SP |
2014-11-13 17:20 |
Fukuoka |
Kyushu Univ. Chikushi Campus |
Emotional speech synthesis for long words by generalizing accent types Yuko Aoyama (hakase.com), Tsuyoshi Moriyama (Tokyo Polytechnic Univ.) SP2014-96 |
More desirable speech synthesis methods require fewer number of training samples in synthesizing various kinds and stren... [more] |
SP2014-96 pp.37-40 |
SP |
2014-11-14 09:00 |
Fukuoka |
Kyushu Univ. Chikushi Campus |
Influence of the phase of voiced sound in source-filter speech synthesis on nerve cell responses in the auditory cortex
-- A study based on nerve cell responses in the primary auditory cortex of an awake cat -- Masanori Morise, Kaito Okubo, Sohei Chimoto, Yu Sato, Kenji Ozawa (Univ. of Yamanashi) SP2014-97 |
[more] |
SP2014-97 pp.41-46 |
SP |
2014-11-14 09:25 |
Fukuoka |
Kyushu Univ. Chikushi Campus |
A study for estimating the vocal-tract shape from speech spectrum using a sensitivity function Tokihiko Kaburagi (Kyushu Univ.) SP2014-98 |
To determine vocal-tract shape from speech, this paper presents an inversion method for simultaneously estimating the cr... [more] |
SP2014-98 pp.47-52 |
SP |
2014-11-14 09:50 |
Fukuoka |
Kyushu Univ. Chikushi Campus |
Application of a vocal tract mapping interface to inverse estimation of vocal tract shapes Kohichi Ogata, Tayuto Kodama, Tomohiro Hayakawa (Kumamoto Univ.) SP2014-99 |
This paper describes the application of a vocal tract mapping interface to inverse estimation of vocal tract shapes. The... [more] |
SP2014-99 pp.53-58 |
SP |
2014-11-14 10:30 |
Fukuoka |
Kyushu Univ. Chikushi Campus |
A study of speaker normalization based on voice conversion for statistical acoustic-to-articulatory mapping Hidetsugu Uchida, Daisuke Saito, Nobuaki Minematsu, Keikichi Hirose (Univ. of Tokyo) SP2014-100 |
[more] |
SP2014-100 pp.59-64 |
SP |
2014-11-14 10:55 |
Fukuoka |
Kyushu Univ. Chikushi Campus |
Design of control parameters for voice quality control based on multiple-regression Gaussian mixture model Kazutaka Kubo, Kazuhiro Kobayashi, Tomoki Toda, Graham Neubig, Sakriani Sakti, Satoshi Nakamura (NAIST) SP2014-101 |
This report presents a method for designing control parameters in statistical voice quality control. As a method for int... [more] |
SP2014-101 pp.65-70 |
SP |
2014-11-14 11:20 |
Fukuoka |
Kyushu Univ. Chikushi Campus |
An evaluation of target speech for nonaudible murmur enhancement focusing on its intelligibility under noisy environments Sakura Tsuruta, Kou Tanaka, Tomoki Toda, Graham Neubig, Sakriani Sakti, Satoshi Nakamura (NAIST) SP2014-102 |
Nonaudible murmur (NAM) is a soft whispered voice recorded with a NAM microphone through body conduction. NAM is effecti... [more] |
SP2014-102 pp.71-76 |
SP |
2014-11-14 13:00 |
Fukuoka |
Kyushu Univ. Chikushi Campus |
Analysis of color attributes derived from vowel sound impression
-- for multimodal expression of sentiment information -- Kanako Watanabe, Yoko Greenberg, Yoshinori Sagisaka (Waseda Univ.) SP2014-103 |
We have been proposing to specify communicative speech characteristics for synthesis using their perceptual impressions.... [more] |
SP2014-103 pp.77-82 |
SP |
2014-11-14 13:25 |
Fukuoka |
Kyushu Univ. Chikushi Campus |
An Acoustical Analysis of Singing Voice of Kugaki and Ufugaki in Ryukyuan Classical Music "Nomura Style" Yasufumi Uezu, Tokihiko Kaburagi (Kyushu Univ.) SP2014-104 |
Ryukyuan classical music is one of traditional art cultures of Okinawa, especially Nomura style is most popular these da... [more] |
SP2014-104 pp.83-88 |
SP |
2014-11-14 13:50 |
Fukuoka |
Kyushu Univ. Chikushi Campus |
A method of measuring articulatory space using NDI Wave speech research system Tatsuya Kitamura (Konan Univ.), Yukiko Nota (ATR-Promotions), Michiko Hashi (Pref. Univ. Hiroshima), Hiroaki Hatano (ATR/Kobe Univ.) SP2014-105 |
The Wave speech research system of Northern Digital Inc. is a type of electromagnetic articulograph that can track the p... [more] |
SP2014-105 pp.89-93 |