Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
SP |
2013-01-31 13:00 |
Kyoto |
Doshisha Univ. |
[Invited Talk]
Speaker and style diversification in statistical parametric speech synthesis Takashi Nose (Tokyo Inst. of Tech.) SP2012-109 |
This paper reviews representative techniques for adding and modifying various
speaker characteristics and style express... [more] |
SP2012-109 pp.67-72 |
SP |
2013-01-31 14:15 |
Kyoto |
Doshisha Univ. |
A study on speaker-normalized style conversion for arbitrary speaker's expressive speech synthesis Hiroki Kanagawa, Takashi Nose, Takao Kobayashi (Tokyo Inst. of Tech.) SP2012-110 |
This paper proposes a technique for improving naturalness of synthetic speech using a framework of speaker adaptive trai... [more] |
SP2012-110 pp.73-78 |
SP |
2013-01-31 14:45 |
Kyoto |
Doshisha Univ. |
A Study on Style Control Based on Multiple-Regression HSMM for Synthesizing Singing Voices with Various Expressivity Takashi Nose, Misa Kanemoto, Tomoki Koriyama, Takao Kobayashi (Tokyo Inst. of Tech.) SP2012-111 |
This paper proposes a style control technique based on multiple regression HSMM (MRHSMM)
for changing styles and their ... [more] |
SP2012-111 pp.79-84 |
SP |
2013-01-31 15:15 |
Kyoto |
Doshisha Univ. |
A Study on Multi-class Local Prosodic Context for Expressive Prosody Generation Yu Maeno, Takashi Nose, Takao Kobayashi, Tomoki Koriyama (Tokyo Inst. of Tech.), Yusuke Ijima, Hideharu Nakajima, Hideyuki Mizuno, Osamu Yoshioka (NTT) SP2012-112 |
This paper describes a technique for reproducing local prosodic variability which appears in expressive speech including... [more] |
SP2012-112 pp.85-90 |
SP |
2012-11-08 14:45 |
Miyagi |
Ichibancho Lobby, Tohoku Institute of Technology |
Improvements of HMM-based speech synthesis using rich context models Shinnosuke Takamichi, Tomoki Toda (NAIST), Yoshinori Shiga (NICT), Sakriani Sakti, Graham Neubig, Satoshi Nakamura (NAIST) SP2012-78 |
In the traditional HMM-based speech synthesis, generated speech parameters tend to be excessively smoothed.
To allevia... [more] |
SP2012-78 pp.37-42 |
SP |
2012-11-08 15:15 |
Miyagi |
Ichibancho Lobby, Tohoku Institute of Technology |
Modeling of local variance of spectral features and its application to parameter generation in HMM-based speech synthesis Takashi Nose, Vataya Chunwijitra, Takao Kobayashi (Tokyo Tech) SP2012-79 |
In this paper, we describe a technique for modeling local variance (LV)
of speech features and propose a novel paramete... [more] |
SP2012-79 pp.43-48 |
SP |
2012-06-14 11:00 |
Kanagawa |
NTT Atsugi R&D Center |
A Study on Automatic Prosodic Context Labeling for Emphatic Speech Synthesis Yu Maeno, Takashi Nose, Takao Kobayashi (Tokyo Tech), Yusuke Ijima, Hideharu Nakajima, Hideyuki Mizuno, Osamu Yoshioka (NTT) SP2012-33 |
This paper describes automatic prosodic context labeling of training data for synthesizing expressive speech in HMM-base... [more] |
SP2012-33 pp.1-6 |
SP, NLC, IPSJ-SLP [detail] |
2011-12-20 15:45 |
Tokyo |
|
An MRHSMM-based conversational speech synthesis with controllability of paralinguistic information Tomohiro Nagata, Hiroki Mori (Utsunomiya Univ), Takashi Nose (Tokyo Tech) NLC2011-52 SP2011-97 |
In this paper, we aim at the realization of the speech synthesis that can control paralinguistic informationusing multip... [more] |
NLC2011-52 SP2011-97 pp.179-184 |
SP, NLC, IPSJ-SLP [detail] |
2011-12-20 16:10 |
Tokyo |
|
On the use of prosodic-event-based HMM in F0 generation of conversational speech Tomoki Koriyama, Takashi Nose, Takao Kobayashi (Tokyo Tech) NLC2011-53 SP2011-98 |
In this paper, we propose prosodic-event-based HMM
for effectively modeling F0 pattern of spontaneous conversational sp... [more] |
NLC2011-53 SP2011-98 pp.185-190 |
SP, NLC, IPSJ-SLP [detail] |
2011-12-20 16:35 |
Tokyo |
|
A Study on Speaker Independent Style Conversion in HMM Speech Synthesis Hiroki Kanagawa, Takashi Nose, Takao Kobayashi (Tokyo Tech) NLC2011-54 SP2011-99 |
This paper proposes a technique for synthesizing speech of a desired style using speaker-independent style conversion in... [more] |
NLC2011-54 SP2011-99 pp.191-196 |
SP, NLC, IPSJ-SLP [detail] |
2011-12-20 17:00 |
Tokyo |
|
A study on modeling phone duration using dynamic features for HMM-based speech synthesis Takashi Nose, Takao Kobayashi (Tokyo Tech) NLC2011-55 SP2011-100 |
This paper proposes a technique for modeling and generating phone durations
using their dynamic features to improve pre... [more] |
NLC2011-55 SP2011-100 pp.197-202 |
EA, SIP, SP |
2011-05-13 13:00 |
Osaka |
Ritsumeikan Univ. |
Performance evaluation of contexts for conversational speech synthesis using Corpus of Spontaneous Japanese Tomoki Koriyama, Takashi Nose, Takao Kobayashi (Tokyo Tech) EA2011-27 SIP2011-27 SP2011-27 |
This paper proposes an extended context set for generating the prosodic variability of spontaneous speech in HMM-based c... [more] |
EA2011-27 SIP2011-27 SP2011-27 pp.155-160 |
NLC, SP (Joint) [detail] |
2010-12-21 16:40 |
Tokyo |
National Olympics Memorial Youth Center |
Study on HMM-based F0 Coding for Very Low Bit-Rate Vocoder Takashi Nose, Masashi Kumamoto, Takao Kobayashi (Tokyo Inst. of Tech.) NLC2010-28 SP2010-101 |
This paper presents a novel F0 coding technique for very low bit-rate HMM-based phonetic vocoder. Our technique is based... [more] |
NLC2010-28 SP2010-101 pp.189-194 |
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 |
PRMU, SP, MVE, CQ |
2010-01-21 10:40 |
Kyoto |
Kyoto Univ. |
Performance evaluation of Voice Conversion Based on F0 Quantization and Non-parallel Training Yuhei Ota, Takashi Nose, Takao Kobayashi (Tokyo Inst. of Tech.) CQ2009-60 PRMU2009-159 SP2009-100 MVE2009-82 |
This paper describes the performance evaluation results of a context-dependent HMM-based voice conversion technique to s... [more] |
CQ2009-60 PRMU2009-159 SP2009-100 MVE2009-82 pp.27-32 |
SP, NLC |
2009-12-22 15:50 |
Tokyo |
Univ. of Tokyo |
HMM-based Speech Synthesis Using Quantized-F0-based Prosodic Context Koujirou Ooki, Takashi Nose, Takao Kobayashi (Tokyo Inst. of Tech.) NLC2009-23 SP2009-87 |
This paper describes a technique for an HMM-based speech synthesis without using any manual labeling of accent informati... [more] |
NLC2009-23 SP2009-87 pp.141-146 |
SP, NLC |
2009-12-22 15:50 |
Tokyo |
Univ. of Tokyo |
A study on Voice Conversion Based on F0 Quantization and Non-parallel Training Yuhei Ota, Takashi Nose, Takao Kobayashi (Tokyo Inst. of Tech.) NLC2009-27 SP2009-91 |
This paper presents a novel voice conversion technique using HMM-based phoneme recognition and speech synthesis with non... [more] |
NLC2009-27 SP2009-91 pp.171-176 |
SP, NLC |
2009-12-22 15:50 |
Tokyo |
Univ. of Tokyo |
Factor analysis models representing various voice characteristics for HMM based speech synthesis Kyosuke Kazumi, Yoshihiko Nankaku, Keiichi Tokuda (Nagoya Inst. of Tech.) NLC2009-28 SP2009-92 |
This paper describes factor analysis models for realizing
various voice characteristics in the HMM-based speech synthe... [more] |
NLC2009-28 SP2009-92 pp.177-182 |
SP |
2009-06-25 14:30 |
Hokkaido |
Clark Memorial Hall, Hokkaido Univ. |
A mean F0 speaker adaptation method for regression model-based F0 contour generation Hosana Kamiyama, Takahiro Shinozaki (Tokyo Inst. of Tech.), Koji Iwano (Tokyo City Univ.), Sadaoki Furui (Tokyo Inst. of Tech.) SP2009-38 |
This paper proposes a new speaker adaptation method for the fundamental frequency ($F_0$) contour generation models base... [more] |
SP2009-38 pp.87-92 |
SP, NLC |
2008-12-10 09:55 |
Tokyo |
Waseda Univ. |
Bayesian Context Clustering Using Cross Validation for HMM-Based Speech Synthesis Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda (Nagoya Institute of Technology) NLC2008-36 SP2008-91 |
This paper proposes a prior distribution determination technique using cross validation for HMM-based speech synthesis b... [more] |
NLC2008-36 SP2008-91 pp.73-78 |