Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
SP |
2012-06-14 11:30 |
Kanagawa |
NTT Atsugi R&D Center |
Eigenvoice-based character conversion and its evaluation Teeraphon Pongkittiphan, Daisuke Saito, Nobuaki Minematsu, Keikichi Hirose (Univ. of Tokyo) SP2012-34 |
This paper describes a new method of voice conversion,
which aims at character conversion based on eigenvoice
GMM (EV-... [more] |
SP2012-34 pp.7-12 |
EA, SP, SIP |
2012-05-25 14:10 |
Osaka |
Osaka Univ. Nakanoshima Center |
SPLICE leveraging lip image information for ASR in noisy environments. Yosuke Kashiwagi, Masayuki Suzuki, Nobuaki Minematsu, Keikichi Hirose (Univ. of Tokyo) EA2012-27 SIP2012-27 SP2012-27 |
[more] |
EA2012-27 SIP2012-27 SP2012-27 pp.155-160 |
EA, SP, SIP |
2012-05-25 14:35 |
Osaka |
Osaka Univ. Nakanoshima Center |
Combination of noise compensation and SPLICE for noise robust speech recognition Tsunenobu Kai, Masayuki Suzuki, Nobuaki Minematsu, Keikichi Hirose (The Univ. of Tokyo) EA2012-28 SIP2012-28 SP2012-28 |
Recently, voices are often used as input modality to mobile terminals or car navigation systems. However, the voices rec... [more] |
EA2012-28 SIP2012-28 SP2012-28 pp.161-166 |
SP |
2011-11-28 14:15 |
Fukuoka |
Kyusyu University Chikushi Campus |
Voice conversion from/to arbitrary speakers based on tensor representation of speaker space Daisuke Saito, Keisuke Yamamoto, Nobuaki Minematsu, Keikichi Hirose (Univ. of Tokyo) SP2011-70 |
This paper describes a novel approach to flexible control of speaker characteristics using tensor representation of spea... [more] |
SP2011-70 pp.7-12 |
SP |
2011-11-29 14:00 |
Fukuoka |
Kyusyu University Chikushi Campus |
Pitch Level Fall Transition Probability for Bimoraic Units in Japanese Words Greg Short, Keikichi Hirose, Nobuaki Minematsu (Unv. of Tokyo) SP2011-80 |
[more] |
SP2011-80 pp.67-72 |
SP |
2011-03-04 15:15 |
Tokyo |
Faculty of Engineering, The University of Tokyo |
Perceptual Study on the Effects of Language Transfer on the Naturalness of Japanese Prosody for Isolated Words Shuhei Kato, Greg Short, Nobuaki Minematsu, Keikichi Hirose (Univ. of Tokyo) SP2010-118 |
Many Japanese language learners have a desire to learn how to speak natural sounding Japanese. Despite this, due to lang... [more] |
SP2010-118 pp.19-24 |
SP |
2011-03-05 10:00 |
Tokyo |
Faculty of Engineering, The University of Tokyo |
Evaluations of an Open Source WFST-based Phoneticizer Josef Novak, Nobuaki Minematsu, Keikichi Hirose (Univ. of Tokyo.) SP2010-121 |
[more] |
SP2010-121 pp.37-42 |
SP |
2011-03-05 14:30 |
Tokyo |
Faculty of Engineering, The University of Tokyo |
Gesture Design of Hand-to-Speech Conversion Based on Probabilistic Integration of Speech-to-Hand Joint Density Model and Hand Gesture Model Aki Kunikoshi, Daisuke Saito (Univ. of Tokyo), Yu Qiao (SIAT), Nobuaki Minematsu, Keikichi Hirose (Univ. of Tokyo) SP2010-127 |
[more] |
SP2010-127 pp.73-78 |
SP |
2011-03-05 15:15 |
Tokyo |
Faculty of Engineering, The University of Tokyo |
An Analysis on the Perception of Pitch Level Changes for Japanese Words Greg Short, Keikichi Hirose, Nobuaki Minematsu (Univ. of Tokyo.) SP2010-128 |
In order to successfully construct a system to recognize errors in pitch accent for Japanese language learners, we have ... [more] |
SP2010-128 pp.79-84 |
SP |
2010-07-22 14:20 |
Miyagi |
Ryokusui-tei (Sendai) |
Pronunciation assessment based on multilayer multiple regression analysis using structural features Masayuki Suzuki, Ayano Nakamura (Univ. of Tokyo.), Yu Qiao (Shenzhen Institutes), Nobuaki Minematsu, Keikichi Hirose (Univ. of Tokyo.) SP2010-37 |
In the rapid internationalization and informatization, many research efforts have been made to build computer-aided lang... [more] |
SP2010-37 pp.13-18 |
SP |
2010-06-17 13:30 |
Fukuoka |
Kyushu University |
HMM-based F0 Contour Synthesis using the Generation Process Model Tetsuya Matsuda, Keikichi Hirose, Nobuaki Minematsu (Univ. of Tokyo) SP2010-34 |
A method was proposed to increase naturalness of prosody generated by the speech synthesis based on the hidden Markov mo... [more] |
SP2010-34 pp.73-78 |
SP, NLC |
2009-12-21 10:35 |
Tokyo |
Univ. of Tokyo |
Experimental study of acoustic modeling using speaker-invariant speech contrast as modeling unit Daisuke Saito, Ryo Matsuura, Nobuaki Minematsu, Keikichi Hirose (Univ. of Tokyo) NLC2009-13 SP2009-77 |
Speech acoustics vary due to differences in age, gender, vocal tract length, microphone, and so on. The authors recently... [more] |
NLC2009-13 SP2009-77 pp.7-12 |
SP |
2009-11-26 16:30 |
Shizuoka |
Shizuoka University |
Flexible Control of Focusing in Corpus-based Generation of Prosodic Features based on the F0 Contour Generation Process Model Keiko Ochi, Keikichi Hirose, Nobuaki Minematsu (Univ. of Tokyo) SP2009-67 |
[more] |
SP2009-67 pp.31-36 |
SP |
2009-11-27 09:30 |
Shizuoka |
Shizuoka University |
Improvement of structure to speech conversion based on a structural cost function Daisuke Saito, Yu Qiao, Nobuaki Minematsu, Keikichi Hirose (Univ. of Tokyo) SP2009-70 |
Speech acoustics vary due to differences in age, gender, vocal tract length, microphone, and so on. The authors recently... [more] |
SP2009-70 pp.49-54 |
SP |
2009-11-27 10:00 |
Shizuoka |
Shizuoka University |
Cross-speaker and cross-language voice conversion based on structural representation of speech Ryusuke Mihara, Daisuke Saito, Nobuaki Minematsu, Keikichi Hirose (Univ. of Tokyo.) SP2009-71 |
Speech acoustics easily vary due to non-linguistic factors such as speaker differences and microphone differences. The a... [more] |
SP2009-71 pp.55-60 |
WIT, SP |
2009-10-30 09:15 |
Aomori |
ASPAM |
Nasal sounds generation and pitch control for the real-time hand to speech system Aki Kunikoshi, Yu Qiao, Nobuaki Minematsu, Keikichi Hirose (Tokyo Univ.) SP2009-56 WIT2009-62 |
[more] |
SP2009-56 WIT2009-62 pp.43-48 |
SP |
2009-07-18 09:25 |
Fukushima |
|
Structural analysis of Chinese dialects and its experimental application to pronunciation assessment Xuebin Ma, Nobuaki Minematsu (Univ. of Tokyo), Akira Nemoto (Nankai Univ.), Yu Qiao, Keikichi Hirose (Univ. of Tokyo) SP2009-45 |
The current situation of Chinese dialects is very complicated, not only because there are hundreds kinds of dialects, su... [more] |
SP2009-45 pp.25-30 |
SP |
2009-06-25 09:30 |
Hokkaido |
Clark Memorial Hall, Hokkaido Univ. |
Analysis and Utilization of Speaker Adaptation Techniques for Shadowing and Read-Speech Pronunciation Evaluation Dean Luo, Yu Qiao, Nobuaki Minematsu (Univ. of Tokyo), Yutaka Yamauchi (Tokyo International Univ.), Keikichi Hirose (Univ. of Tokyo) SP2009-32 |
In this paper, we investigate the effects and problems of MLLR speaker adaptation when applied to pronunciation evaluati... [more] |
SP2009-32 pp.51-56 |
EA, SIP, SP |
2009-05-29 10:30 |
Hyogo |
|
Robust estimation of fundamental frequencies of speech signals in noisy environments based on signal filtering by empirical mode decomposition Tetsuya Matsuda, Keikichi Hirose, Nobuaki Minematsu (Univ. of Tokyo) EA2009-10 SIP2009-10 SP2009-15 |
A number of methods have already been developed for the estimation of fundamental frequencies of speech signals. However... [more] |
EA2009-10 SIP2009-10 SP2009-15 pp.49-54 |
WIT |
2009-02-20 17:30 |
Ehime |
Ehime University |
[Invited Talk]
A system "is" to assist simultaneous interpretation and its possible application to aiding hearing-impaired Michiko Watanabe (Univ. Tokyo), Youich Tokioka (Straightword), Keikichi Hirose (Univ. Tokyo) WIT2008-60 |
We have been developing a system to assist simultaneous interpretation by introducing merits of consecutive interpretati... [more] |
WIT2008-60 pp.23-26 |