Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
SP |
2017-01-21 10:00 |
Tokyo |
The University of Tokyo |
Spoken dialogue system with brain machine interface Makoto Koike (MK Microwave Researh) SP2016-65 |
We propose herein that brain-machine interfaces are applied to both output and input interfaces of the spoken dialogue s... [more] |
SP2016-65 pp.1-9 |
SP |
2017-01-21 10:25 |
Tokyo |
The University of Tokyo |
Non-parametric duration modelling for speech synthesis with a joint model of acoustics and duration Gustav Eje Henter (NII), Srikanth Ronanki, Oliver Watts, Simon King (University of Edinburgh) SP2016-66 |
[more] |
SP2016-66 pp.11-16 |
SP |
2017-01-21 11:00 |
Tokyo |
The University of Tokyo |
[Poster Presentation]
A Study on Singer-Independent Singing Voice Conversion Using Read Speech Based on Neural Network Harunori Koike, Takashi Nose, Akinori Ito (Tohoku Univ.) SP2016-67 |
There is a problem that the conventional method requires the speech of the source speaker for training. We proposed a me... [more] |
SP2016-67 pp.17-22 |
SP |
2017-01-21 11:00 |
Tokyo |
The University of Tokyo |
[Poster Presentation]
An Interactive Test System for Japanese Special Mora Pronunciation Using Smartphones and Its Evaluation Sho Sasaki, Jouji Miwa (Iwate Univ.) SP2016-68 |
This paper describes an interactive test system for pronunciation of Japanese special morae in contracted sound words us... [more] |
SP2016-68 pp.23-28 |
SP |
2017-01-21 11:00 |
Tokyo |
The University of Tokyo |
[Poster Presentation]
Evaluation of DNN-Based Voice Conversion Deceiving Anti-spoofing Verification Yuki Saito, Shinnosuke Takamichi, Hiroshi Saruwatari (UT) SP2016-69 |
This paper proposes a novel training algorithm for high-quality Deep Neural Network (DNN)-based voice conversion. To imp... [more] |
SP2016-69 pp.29-34 |
SP |
2017-01-21 11:00 |
Tokyo |
The University of Tokyo |
[Poster Presentation]
Designing linguistic features for expressive speech synthesis using audiobooks Chiaki Asai, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda (Nagoya Inst. of Tech.) SP2016-70 |
In order to synthesize expressive speech, various statistical parametric speech synthesis systems have been proposed. Sp... [more] |
SP2016-70 pp.35-40 |
SP |
2017-01-21 13:00 |
Tokyo |
The University of Tokyo |
[Invited Talk]
Interesting! Deep learning for text-to-speech synthesis Shinji Takaki (NII) SP2016-71 |
(To be available after the conference date) [more] |
SP2016-71 pp.41-46 |
SP |
2017-01-21 14:00 |
Tokyo |
The University of Tokyo |
[Invited Talk]
Deep learning in voice conversion Daisuke Saito (UTokyo) SP2016-72 |
In this paper, deep learning techniques in voice conversion studies are overviewed. Recently, deep learning techniques w... [more] |
SP2016-72 pp.47-52 |
SP |
2017-01-21 15:10 |
Tokyo |
The University of Tokyo |
A Study on the Construction of Articulatory to Acoustic Mapping by Using Deep Neural Network Fumiaki Taguchi, Tokihiko Kaburagi (Kyushu Univ.) SP2016-73 |
This paper presents a method for estimating time series of the acoustic property of the vocal tract expressed by line sp... [more] |
SP2016-73 pp.53-57 |
SP |
2017-01-21 15:35 |
Tokyo |
The University of Tokyo |
Conversational Speech Synthesis dealing with Sequence of Sentences Ishin Fukuoka, Kazuhiko Iwata, Tetsunori Kobayashi (Waseda Univ.) SP2016-74 |
We proposed a conversational speech synthesis system that takes account of dialogue structure-based features. Convention... [more] |
SP2016-74 pp.59-64 |
SP |
2017-01-21 16:10 |
Tokyo |
The University of Tokyo |
A study on DNN-based speech synthesis using vector quantization of spectral features Takashi Nose, Suzunosuke Ito (Tohoku Univ.) SP2016-75 |
[more] |
SP2016-75 pp.65-70 |
SP |
2017-01-21 16:35 |
Tokyo |
The University of Tokyo |
Simultaneous modeling of acoustic feature sequences and its temporal structures for DNN-based speech synthesis Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda (Nagoya Inst. of Tech.) SP2016-76 |
In statistical parametric speech synthesis, a hidden Markov model (HMM) is widely used as an acoustic model. Recently, d... [more] |
SP2016-76 pp.71-76 |