TODA Tomoki

J-GLOBAL         Last updated: Nov 17, 2019 at 16:32
 
Avatar
Name
TODA Tomoki
Affiliation
Nagoya University
Section
Information Technology Center Information Media Division
Job title
Professor
Degree
Doctor of Engineering(Nara Institute of Science and Technology)

Academic & Professional Experience

 
Apr 2003
 - 
Mar 2005
Research Fellow, Japan Society for the Promotion of Science
 
Apr 2005
 - 
Mar 2007
Assistant Professor, Graduate School of Information Science, Nara Institute of Science and Technology
 
Apr 2007
 - 
Mar 2011
Assistant Professor, Graduate School of Information Science, Nara Institute of Science and Technology
 
Apr 2011
 - 
Aug 2015
Associate Professor, Graduate School of Information Science, Nara Institute of Science and Technology
 
Sep 2015
 - 
Today
Professor, Information Technology Center Information Media Division, Nagoya University
 

Education

 
Apr 1995
 - 
Mar 1999
Electrical and Electronic Engineering and Information Engineering, School of Engineering, Nagoya University
 
Apr 1999
 - 
Mar 2001
Master course, Graduate School of Information Science, Nara Institute of Science and Technology
 
Apr 2001
 - 
Mar 2003
PhD Course, Graduate School of Information Science, Nara Institute of Science and Technology
 

Committee Memberships

 
Nov 2016
 - 
Today
IEEE Signal Processing Letters, Editorial Board  Associate Editor
 
Apr 2013
 - 
Today
EURASIP Journal on Audio, Speech, and Music Processing, Editorial Board  Associate Editor
 
Jun 2016
 - 
Dec 2017
IEEE ASRU 2017, Organizing Committee  Organizing Committee Member
 
Jan 2014
 - 
Dec 2016
IEEE Signal Processing Society Speech and Language Technical Committee  Technical Committee Member
 
Apr 2010
 - 
Dec 2016
APSIPA Speech, Language, and Audio Technical Committee  Technical Committee Member
 
Aug 2014
 - 
Dec 2015
IEEE ASRU 2015, Organizing Committee  Organizing Committee Member
 
Apr 2015
 - 
Sep 2015
International Workshop on Machine Learning in Spoken Language Processing (MLSLP), Organizing Committee  Organizing Committee Member
 
Feb 2013
 - 
Jan 2015
IEEE Signal Processing Society Kansai Chapter  Treasurer
 
Mar 2011
 - 
Dec 2013
ACM Transactions on Speech and Language Processing, Editorial Board  Associate Editor
 
Feb 2011
 - 
Jan 2013
IEEE Signal Processing Society Kansai Chapter  Secretary
 
Dec 2011
 - 
Mar 2012
IEEE ICASSP 2012, Organizing Committee  Organizing Committee Member
 
Sep 2011
 - 
Mar 2012
International Workshop on Statistical Machine Learning for Speech Processing (IWSML), Organizing Committee  Organizing Committee Member
 
Jan 2010
 - 
Sep 2010
INTERSPEECH 2010, Organizing Committee  Organizing Committee Member
 
Aug 2008
 - 
Sep 2010
The 7th ISCA Speech Synthesis Workshop (SSW7), Organizing Committee  Organizing Committee Member
 
Jan 2007
 - 
Dec 2009
IEEE Signal Processing Society Speech and Language Technical Committee  Technical Committee Member
 

Awards & Honors

 
Dec 2014
APSIPA ASC 2014 The Best Paper Award, APSIPA
Winner: S. Takamichi, T. Toda, A.W. Black, S. Nakamura
 
Sep 2013
The 2013 EURASIP-ISCA Best Paper Award (Speech Communication Journal), EURASIP, and ISCA
Winner: T. Toda, A.W. Black, K. Tokuda
 
Dec 2012
APSIPA ASC 2012 The Best Paper Award (Short Paper in Regular Session Category), APSIPA
Winner: H. Doi, T. Toda, T. Nakano, M. Goto, S. Nakamura
 
Mar 2010
IEEE Signal Processing Society 2009 Young Author Best Paper Award, IEEE Signal Processing Society
Winner: T. Toda
 

Published Papers

 
Designing a pneumatic bionic voice prosthesis - statistical approach for source excitation generation
F. Ahmadi, T. Toda
Proc. INTERSPEECH   3142-3146   Sep 2018   [Refereed]
Self-produced speech enhancement and suppression method using air- and body-conductive microphones
M. Takada, S. Seki, T. Toda
Proc. APSIPA ASC   1240-1245   Nov 2018   [Refereed]
Investigations of real-time Gaussian FFTNet and parallel WaveNet neural vocoders with simple acoustic features
T. Okamoto, T. Toda, Y. Shiga, H. Kawai
Proc. IEEE ICASSP   7020-7024   May 2019   [Refereed]
Refined WaveNet vocoder for variational autoencoder based voice conversion
W.-C. Huang, Y.-C. Wu, H.-T. Hwang, P.L. Tobing, T. Hayashi, K. Kobayashi, T. Toda, Y. Tsao, H.-M. Wang
Proc. EUSIPCO   5 pages   Sep 2019   [Refereed]
Audio-visual voice conversion using deep canonical correlation analysis for deep bottleneck features
S. Tamura, K. Horio, H. Endo, S. Hayamizu, T. Toda
Proc. INTERSPEECH   2469-2473   Sep 2018   [Refereed]
Voice conversion with cyclic recurrent neural network and fine-tuned WaveNet vocoder
P.L. Tobing, Y. Wu, T. Hayashi, K. Kobayashi, T. Toda
Proc. IEEE ICASSP   6815-6819   May 2019   [Refereed]
Generalized multichannel variational autoencoder for underdetermined source separation
S. Seki, H. Kameoka, L. Li, T. Toda, K. Takeda
Proc. EUSIPCO   5 pages   Sep 2019   [Refereed]
Frequency domain variants of velvet noise and their application to speech processing and synthesis
H. Kawahara, K. Sakakibara, M. Morise, H. Banno, T. Toda, T. Irino
Proc. INTERSPEECH   2027-2031   Sep 2018   [Refereed]
Scene-dependent anomalous acoustic-event detection based on conditional WaveNet and i-Vector
T. Komatsu, T. Hayashi, R. Kondo, T. Toda, K. Takeda
Proc. IEEE ICASSP   870-874   May 2019   [Refereed]
Pre-trained text embeddings for enhanced text-to-speech synthesis
T. Hayashi, S. Watanabe, T. Toda, K. Takeda, S. Toshniwal, K. Livescu
Proc. INTERSPEECH   4430-4434   Sep 2019   [Refereed]
Collapsed segment detection and reduction for WaveNet vocoder
Y. Wu, K. Kobayashi, T. Hayashi, P.L. Tobing, T. Toda
Proc. INTERSPEECH   1998-1992   Sep 2018   [Refereed]
Back-translation-style data augmentation for end-to-end ASR
T. Hayashi, S. Watanabe, Y. Zhang, T. Toda, T. Hori, R. Astudillo, K. Takeda
Proc. IEEE SLT   426-433   Dec 2018   [Refereed]
Real-time neural text-to-speech with sequence-to-sequence acoustic model and WaveGlow or single Gaussian WaveRNN vocoders
T. Okamoto, T. Toda, Y. Shiga, H. Kawai
Proc. INTERSPEECH   1308-1312   Sep 2019   [Refereed]
Multi-Head Decoder for end-to-end speech recognition
T. Hayashi, S. Watanabe, T. Toda, K. Takeda
Proc. INTERSPEECH   801-805   Sep 2018   [Refereed]
Improving FFTNet vocoder with noise shaping and subband approaches
T. Okamoto, T. Toda, Y. Shiga, H. Kawai
Proc. IEEE SLT   304-311   Dec 2018   [Refereed]
Investigation of F0 conditioning and fully convolutional networks in variational autoencoder based voice conversion
W.-C. Huang, Y.-C. Wu, C.-C. Lo, P.L. Tobing, T. Hayashi, K. Kobayashi, T. Toda, Y. Tsao, H.-M. Wang
Proc. INTERSPEECH   709-713   Sep 2019   [Refereed]
Anomalous sound event detection based on WaveNet
T. Hayashi, T. Komatsu, R. Kondo, T. Toda, K. Takeda
Proc. EUSIPCO   2508-2512   Sep 2018   [Refereed]
An evaluation of deep spectral mappings and WaveNet vocoder for voice conversion
P.L. Tobing, T. Hayashi, Y. Wu, K. Kobayashi, T. Toda
Proc. IEEE SLT   297-303   Dec 2018   [Refereed]
Robustness of statistical voice conversion based on direct waveform modification against background sounds
Y. Kurita, K. Kobayashi, K. Takeda, T. Toda
Proc. INTERSPEECH   684-688   Sep 2019   [Refereed]
Electrolarygeal speech enhancement with statistical voice conversion based on CLDNN
K. Kobayashi, T. Toda
Proc. EUSIPCO   2129-2133   Sep 2018   [Refereed]
An end-to-end model for cross-lingual transformation of paralinguistic information
T. Kano, S. Takamichi, S. Sakti, G. Neubig, T. Toda, S. Nakamura
Machine Translation   32(4) 353-368   Dec 2018   [Refereed]
Non-parallel voice conversion with cyclic variational autoencoder
P.L. Tobing, Y.-C. Wu, T. Hayashi, K. Kobayashi, T. Toda
Proc. INTERSPEECH   674-678   Sep 2019   [Refereed]
Connectionist temporal classification-based sound event encoder for converting sound events into onomatopoeia representations
K. Miyazaki, T. Hayashi, T. Toda, K. Takeda
Proc. EUSIPCO   857-861   Sep 2018   [Refereed]
Daily activity recognition based on recurrent neural network using multi-modal signals
A. Tamamori, T. Hayashi, T. Toda, K. Takeda
APSIPA Transactions on Signal and Information Processing   7(e21) 1-11   Dec 2018   [Refereed]
Quasi-periodic WaveNet vocoder: a pitch dependent dilated convolution model for parametric speech generation
Y.-C. Wu, T. Hayashi, P.L. Tobing, K. Kobayashi, T. Toda
Proc. INTERSPEECH   196-200   Sep 2019   [Refereed]
Stereophonic music separation based on non-negative tensor factorization with cepstral distance regularization
S. Seki, T. Toda, K. Takeda
IEICE Transactions on Fundamentals   E101-A(7) 1057-1064   Jul 2018   [Refereed]
An investigation of features for fundamental frequency pattern prediction in electrolaryngeal speech enhancement
M. Eshghi, K. Tanaka, K. Kobayashi, H. Kameoka, T. Toda
Proc. 10th ISCA Speech Synthesis Workshop (SSW10)   251-256   Sep 2019   [Refereed]
NU voice conversion system for the voice conversion challenge 2018
P.L. Tobing, Y. Wu, T. Hayashi, K. Kobayashi, T. Toda
Proc. Odyssey 2018   219-226   Jun 2018   [Refereed]
Statistical voice conversion with quasi-periodic WaveNet vocoder
Y.-C. Wu, T. Hayashi, P.L. Tobing, K. Kobayashi, T. Toda
Proc. 10th ISCA Speech Synthesis Workshop (SSW10)   63-68   Sep 2019   [Refereed]
The NU non-parallel voice conversion system for the voice conversion challenge 2018
Y. Wu, P.L. Tobing, T. Hayashi, K. Kobayashi, T. Toda
Proc. Odyssey 2018   211-218   Jun 2018   [Refereed]
Generalization of spectrum differential based direct waveform modification for voice conversion
W.-C. Huang, Y.-C. Wu, K. Kobayashi, Y.-H. Peng, H.-T. Hwang, P.L. Tobing, Y. Tsao, H.-M. Wang, T. Toda
Proc. 10th ISCA Speech Synthesis Workshop (SSW10)   57-62   Sep 2019   [Refereed]
sprocket: open-source voice conversion software
K. Kobayashi, T. Toda
Proc. Odyssey 2018   203-210   Jun 2018   [Refereed]
Development of a real-time bionic voice generation system based on statistical excitation prediction
F. Ahmadi, K. Kobayashi, T. Toda
Proc. ACM ASSETS   655-657   Oct 2019   [Refereed]
The voice conversion challenge 2018: promoting development of parallel and nonparallel methods
J. Lorenzo-Trueba, J. Yamagishi, T. Toda, D. Saito, F. Villavicencio, T. Kinnunen, Z. Ling
Proc. Odyssey 2018   195-202   Jun 2018   [Refereed]
Improving singing aid system for laryngectomees with statistical voice conversion and VAE-SPACE
L. Li, T. Toda, K. Morikawa, K. Kobayashi, S. Makino
Proc. ISMIR   784-790   Nov 2019   [Refereed]
A spoofing benchmark for the 2018 voice conversion challenge: leveraging from spoofing countermeasures for speech artifact assessment
T. Kinnunen, J. Lorenzo-Trueba, J. Yamagishi, T. Toda, D. Saito, F. Villavicencio, Z. Ling
Proc. Odyssey 2018   187-194   Jun 2018   [Refereed]
K. Kobayashi, T. Toda, S. Nakamura
Speech Communication   99 211-220   May 2018   [Refereed]
An investigation of noise shaping with perceptual weighting for WaveNet-based speech generation
K. Tachibana, T. Toda, Y. Shiga, H. Kawai
Proc. IEEE ICASSP   5664-5668   Apr 2018   [Refereed]
An investigation of subband WaveNet vocoder covering entire audible frequency range with limited acoustic features
T. Okamoto, K. Tachibana, T. Toda, Y. Shiga, H. Kawai
Proc. IEEE ICASSP   5654-5658   Apr 2018   [Refereed]
Development of "KamiRepo" system with automatic student identification to handle handwritten assignments on LMS
S. Seiya, R. Ito, K. Okamoto, U. Tanikawa, S. Ohira, D. Deguchi, T. Toda
Proc. IEEE EDUCON   841-848   Apr 2018   [Refereed]
T. Okamoto, K. Tachibana, T. Toda, Y. Shiga, H. Kawai
Acoustical Science and Technology, Acoustical Letter   39(2) 163-166   Mar 2018   [Refereed]
T. Hayashi, M. Nishida, N. Kitaoka, T. Toda, K. Takeda
IEICE Transactions on Fundamentals   E101-A(1) 199-210   Jan 2018   [Refereed]
P.L. Tobing, K. Kobayashi, T. Toda
IEEE/ACM Transactions on Audio, Speech, and Language Processing   25(12) 2337-2350   Dec 2017   [Refereed]
H. Kawahara, K. Sakakibara, M. Morise, H. Banno, T. Toda
Proc. APSIPA ASC   9 pages   Dec 2017   [Refereed]
K. Kubo, K. Kobayashi, T. Toda, G. Neubig, S. Sakti, S. Nakamura
Proc. APSIPA ASC   4 pages   Dec 2017   [Refereed]
A. Tamamori, T. Hayashi, T. Toda, K. Takeda
Proc. APSIPA ASC   7 pages   Dec 2017   [Refereed][Invited]
P.L. Tobing, H. Kameoka, T. Toda
Proc. APSIPA ASC   4 pages   Dec 2017   [Refereed]
K. Morikawa, T. Toda
Proc. APSIPA ASC   4 pages   Dec 2017   [Refereed]
T. Hayashi, A. Tamamori, K. Kobayashi, K. Takeda, T. Toda
Proc. IEEE ASRU   712-718   Dec 2017   [Refereed]
T. Okamoto, K. Tachibana, T. Toda, Y. Shiga, H. Kawai
Proc. IEEE ASRU   698-704   Dec 2017   [Refereed]

Misc

 
K. Tokuda, Y. Nankaku, T. Toda, H. Zen, J. Yamagishi, K. Oura
Proceedings of the IEEE   101(5) 1234-1252   May 2013   [Refereed][Invited]
Post-filter using modulation spectrum as a metric to quantify qver-smoothing effects in statistical parametric speech synthesis
S. Takamichi, T. Toda, A.W. Black, S. Nakamura
APSIPA newsletter   (9) 14-16   Apr 2015   [Invited]
K. Miyazaki, T. Toda, T. Hayashi, K. Takeda
IEEJ Transactions on Electronics, Information and Systems   14(3) 340-351   Mar 2019   [Refereed][Invited]
Y. Stylianou, T. Toda, C.-H. Wu, A. Kain, O. Rosec
IEEE Transactions on Audio, Speech and Language Processing   18(5) 909-911   Jul 2010   [Invited]
K. Vijayan, H. Li, T. Toda
IEEE Signal Processing Magazine   36(1) 95-102   Jan 2019   [Refereed]
Optimizing segment selection for high-quality Text-to-Speech
T. Toda, H. Kawai, M. Tsuzaki, K. Shikano
ATR Technical Report   (TR-SLT-0033)    Mar 2003

Books etc

 
Hidden Markov Models, Theory and Applications
T. Toda (Part:Contributor, Modeling of speech parameter sequence considering global variance for HMM-based speech synthesis)
InTech   Apr 2011   

Conference Activities & Talks

 
Electrolaryngeal Speech Enhancement by Using Attached Microphones onto Electrolarynx
M. Eshghi, S. Seki, K. Kobayashi, T. Toda
日本音響学会研究発表会   Sep 2018   
Voice conversion with cyclic recurrent neural network for WaveNet fine-tuning
P.L. Tobing, Y.-C. Wu, T. Hayashi, K. Kobayashi, T. Toda
日本音響学会研究発表会   Mar 2019   
An investigation of fundamental frequency pattern prediction in electrolaryngeal speech enhancement
M. Eshghi, K. Tanaka, K. Kobayashi, H. Kameoka, T. Toda
日本音響学会研究発表会   Sep 2019   
Development of NU non-parallel voice conversion system 2018
Y. Wu, P.L. Tobing, T. Hayashi, K. Kobayashi, T. Toda
電子情報通信学会音声研究会   Mar 2018   
Hands on voice conversion [Invited]
T. Toda
Speech Processing Courses in Crete (SPCC 2018)   Jul 2018   
Augmented vocal production towards new singing style development [Invited]
T. Toda
Dagstuhl Seminar, Stimulus Talk at Seminar 19052: computational methods for melody and voice processing in music recordings   Jan 2019   
Development of NU Voice Conversion System 2018
P.L. Tobing, Y. Wu, T. Hayashi, K. Kobayashi, T. Toda
電子情報通信学会音声研究会   Mar 2018   
Advanced voice conversion [Invited]
T. Toda
Speech Processing Courses in Crete (SPCC 2018)   Jul 2018   
Reducing mismatch of WaveNet vocoder for variational autoencoder based voice conversion
W.-C. Huang, Y.-C. Wu, H.-T. Hwang, P.L. Tobing, T. Hayashi, K. Kobayashi, T. Toda, Y. Tsao, H.-M. Wang
日本音響学会研究発表会   Mar 2019   
A Hybrid approach to electrolaryngeal speech enhancement based on log-spectral differential conversion and noise suppression
M. Eshghi, K. Kobayashi, T. Toda
電子情報通信学会音声研究会   Mar 2018   
Electrolaryngeal speech enhancement based on vocoder-free statistical voice conversion and noise suppression
M. Eshghi, K. Kobayashi, T. Toda
日本音響学会研究発表会   Mar 2018   
Development of NU non-parallel voice conversion system for Voice Conversion Challenge 2018
Y. Wu, P.L. Tobing, T. Hayashi, K. Kobayashi, T. Toda
日本音響学会研究発表会   Mar 2018   
Development of NU voice conversion system for Voice Conversion Challenge 2018
P.L. Tobing, Y. Wu, T. Hayashi, K. Kobayashi, T. Toda
日本音響学会研究発表会   Mar 2018   
Sneak Preview of the 2nd Voice Conversion Challenge 2018
J. Yamagishi, J. Lorenzo-Trueba, T. Toda, D. Saito, F. Villavicencio, T. Kinnunen, Z. Ling
情報処理学会音声言語情報処理研究会   Feb 2018   
Acoustic-to-articulatory inversion mapping with variational latent trajectory Gaussian mixture models
P.L. Tobing, H. Kameoka, T. Toda
日本音響学会研究発表会   Mar 2017   
Convolutional bidirectional long short-term memory hidden Markov model hybrid system for polyphonic sound event detection
T. Hayashi, S. Watanabe, T. Toda, T. Hori, J.L. Roux, K. Takeda
5th Joint Meeting of the ASA and the ASJ   Dec 2016   
Acoustic-to-articulatory inversion mapping with variational latent trajectory Gaussian mixture model
P.L. Tobing, H. Kameoka, T. Toda
電子情報通信学会音声研究会   Mar 2017   
Combination of state clustering and adaptive training for modeling continuous word-level emphasis
Q. Truong Do, T. Toda, S. Sakti, S. Nakamura
日本音響学会研究発表会   Mar 2017   
Statistical voice conversion and its application to augmented speech production [Invited]
T. Toda
名古屋工業大学情報科学フロンティア研究院特別講演会   Nov 2016   
Evaluation of electrolarynx controlled by real-time statistical F0 prediction
K. Tanaka, T. Toda, S. Nakamura
5th Joint Meeting of the ASA and the ASJ   Nov 2016   

Research Grants & Projects

 
CASSIS -- Computer-Assisted communication and Silent Speech InterfaceS --
Japan Society for the Promotion of Science: Japan-France Integrated Action Program (SAKURA)
Project Year: Apr 2009 - Mar 2011    Investigator(s): TODA Tomoki