Takuma Okamoto - My portal

Profile Information

Affiliation: Senior Researcher, Universal Communication Research Institute, National Institute of Information and Communications Technology

Degree: Ph.D.(Mar, 2009, Tohoku University)

ORCID iD: https://orcid.org/0000-0001-9913-4647
J-GLOBAL ID: 202001006298609279
researchmap Member ID: R000007783

External link: https://www.okamotocamera.com

Research Interests

Research History

Jul, 2020 - Present

Senior Researcher, National Institute of Information and Communications Technology
Apr, 2012 - Jun, 2020

Researcher, National Institute of Information and Communications Technology
Jul, 2009 - Mar, 2012

COE Fellow, Graduate School of Engineering, Tohoku University
Apr, 2009 - Jun, 2009

Post-doctor research fellow, Research Institute of Electrical Communication, Tohoku University
Nov, 2007 - Mar, 2009

Research fellow (DC2), Japan Society for the Promotion of Science
Jun, 2007 - Oct, 2007

Research Assistant, Research Institute of Electrical Communication, Tohoku University

Education

Apr, 2006 - Mar, 2009

Department of System Information Sciences, Doctor's Program, Graduate School of Information Sciences, Tohoku University
Apr, 2004 - Mar, 2006

Department of System Information Sciences, Master's Program, Graduate School of Information Sciences, Tohoku University
Apr, 2000 - Mar, 2004

Faculty of Engineering, Tohoku University

Committee Memberships

Apr, 2021 - Present

Secretary, Kansai Chapter, Acoustical Society of Japan
Nov, 2013 - Present

Publicity and Computerization Committee, Acoustical Society of Japan
Jul, 2021 - May, 2023

Science Committee, Acoustical Society of Japan
Nov, 2021 - Mar, 2022

Organizing Committee of 2022 Spring Meeting, Acoustical Society of Japan
Jul, 2021 - Mar, 2022

Organizing Committee of 2021 Autumn Meeting, Acoustical Society of Japan
Nov, 2020 - Mar, 2021

Organizing Committee of 2021 Spring Meeting, Acoustical Society of Japan
Aug, 2020 - Sep, 2020

Organizing Committee of 2020 Autumn Meeting, Acoustical Society of Japan
Jun, 2013 - Jun, 2019

Editorial Committee, Acoustical Society of Japan
Jun, 2017 - May, 2019

Science Committee, Acoustical Society of Japan
Apr, 2016 - Apr, 2018

Treasurer, Kansai Chapter, Acousical Society of Japan
Mar, 2012 - Mar, 2017

Acoustics ABC Pedia Editorial Committee, Acoustical Society of Japan
Apr, 2010 - Mar, 2013

Delegate of Students and Young Researchers Forum Meeting, Acoustical Society of Japan
Mar, 2007 - Mar, 2013

Students and Young Researchers Forum Meeting, Acoustical Society of Japan

Awards

Mar, 2022

9th Society Activity Contribution Award, Acoustical Society of Japan

T. Okamoto
Mar, 2018

57th Sato Prize Paper Award, Acoustical Society of Japan

S. Sakamoto, S. Hongo, T. Okamoto, Y. Iwaya, Y. Suzuki
Sep, 2012

32nd Awaya Prize, Acoustical Society of Japan

Major Papers

Neural speech-rate conversion with multispeaker WaveNet vocoder

T. Okamoto, K. Matsubara, T. Toda, Y. Shiga, H. Kawai

Speech Communication, 138 1-12, Mar, 2022 Peer-reviewedLead authorCorresponding author
Comparison of real-time multi-speaker neural vocoders on CPUs

K. Matsubara, T. Okamoto, R. Takashima, T. Takiguchi, T. Toda, H. Kawai

Acoustical Science and Technology, 43(2) 121-124, Mar, 2022 Peer-reviewed
Pronunciation adaptive self speaking agent using WaveGrad

T. Tanaka, R. Komatsu, T. Okamoto, T. shinozaki

The 2nd Workshop on Self-supervised Learning for Audio and Speech Processing (AAAI SAS 2022), Feb, 2022 Peer-reviewed
Automatic spoken language acquisition based on observation and dialogue

R. Komatsu, S. Gao, W. Hou, M. Zhang, T. Tanaka, K. Toyoda, Y. Kimura, K. Hino, Y. Iwamoto, K. Mori …

IEEE Journal of Selected Topics in Signal Processing, 2022 Peer-reviewed
Multi-Stream HiFi-GAN with data-driven waveform decomposition

T. Okamoto, T. Toda, H. Kawai

2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 610-617, Dec, 2021 Peer-reviewedLead authorCorresponding author
2D multizone sound field synthesis with Interior-exterior Ambisonics

T. Okamoto

2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 276-280, Oct 17, 2021 Peer-reviewedLead authorCorresponding author
High-intelligibility speech synthesis for dysarthric speakers with LPCNet-based TTS and CycleVAE-based VC

K. Matsubara, T. Okamoto, R. Takashima, T. Takiguchi, T. Toda, Y. Shiga, H. Kawai

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 7058-7062, Jun, 2021 Peer-reviewed
Noise level limited sub-modeling for diffusion probabilistic vocoders

T. Okamoto, T. Toda, Y. Shiga, H. Kawai

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 6029-6033, Jun, 2021 Peer-reviewedLead authorCorresponding author
Close-talking recording with planarly distributed microphones

T. Okamoto

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 4470-4474, Jun, 2021 Peer-reviewedLead authorCorresponding author
Full-band LPCNet: A real-time neural vocoder for 48 kHz audio with a CPU

K. Matsubara, T. Okamoto, R. Takashima, T. Takiguchi, T. Toda, Y. Shiga, H. Kawai

IEEE Access, 9 94923-94933, 2021 Peer-reviewed
Quasi-Periodic Parallel WaveGAN: A non-autoregressive raw waveform generative model with pitch-dependent dilated convolution neural network

Y.-C. Wu, T. Hayashi, T. Okamoto, H. Kawai, T. Toda

IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29 792-806, 2021 Peer-reviewed
Investigation of training data size for real-time neural vocoders on CPUs

K. Matsubara, T. Okamoto, R. Takashima, T. Takiguchi, T. Toda, Y. Shiga, H. Kawai

Acoustical Science and Technology, 42(1) 65-68, Jan 1, 2021 Peer-reviewed
Transformer-based text-to-speech with weighted forced attention

T. Okamoto, T. Toda, Y. Shiga, H. Kawai

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 6729-6733, May, 2020 Peer-reviewedLead authorCorresponding author
Tacotron-based acoustic model using phoneme alignment for practical neural text-to-speech systems

T. Okamoto, T. Toda, Y. Shiga, H. Kawai

2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 214-221, Dec, 2019 Peer-reviewedLead authorCorresponding author
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

Interspeech 2019, 1308-1312, Sep 15, 2019 Peer-reviewedLead authorCorresponding author
Investigations of real-time Gaussian FFTNet and parallel WaveNet neural vocoders with simple acoustic features

T. Okamoto, T. Toda, Y. Shiga, H. Kawai

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 7020-7024, May, 2019 Peer-reviewedLead authorCorresponding author
Improving FFTNet vocoder with noise shaping and subband approaches

T. Okamoto, T. Toda, Y. Shiga, H. Kawai

2018 IEEE Spoken Language Technology Workshop (SLT), 304-311, Dec, 2018 Peer-reviewedLead authorCorresponding author
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

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 5654-5658, Apr, 2018 Peer-reviewedLead authorCorresponding author
Subband WaveNet with overlapped single-sideband filterbanks

T. Okamoto, K. Tachibana, T. Toda, Y. Shiga, H. Kawai

2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 698-704, Dec, 2017 Peer-reviewedLead authorCorresponding author

Major Misc.

Neural network-based speech waveform generative models

T. Okamoto

Journal of Acoustical Society of Japan, 78(6) 328-337, Jun, 2022 InvitedLead authorCorresponding author
Ambisonics and VR

T. Okamoto

Journal of Virtual Reality Society of Japan, 25(2) 25-28, Jun 30, 2020 InvitedLead authorCorresponding author
Spatial Fourier transform-based localized sound zone generation methods with loudspeaker arrays

T. Okamoto

Journal of the Acoustical Society of America, 146(4) 2761-2762, Nov, 2019 InvitedLead authorCorresponding author
音声波形直接生成モデル「ニューラルボコーダ」の比較

岡本拓磨, 戸田智基, 志賀芳則, 河井恒

研究報告音声言語情報処理, 2019-SLP-129(3) 1-6, Oct, 2019 InvitedLead authorCorresponding author
Real time multimedia programming by Pure Data

OKAMOTO Takuma

The Journal of the Acoustical Society of Japan, 69(6) 285-290, Jun, 2013 InvitedLead authorCorresponding author
Sound field expression using spherical acoustics

IWAYA Yukio, OKAMOTO Takuma, TREVINO Jorge, SUZUKI Yoiti

The Journal of the Acoustical Society of Japan, 67(11) 544-549, Nov, 2011 Invited

Books and Other Publications

Speech-to-speech translation

Y. Shiga, J. Ni, K. Tachibana, T. Okamoto (Role: Contributor, Text-to-Speech Synthesis)

Springer, 2020 (ISBN: 9789811505942)
音響学入門ペディア

日本音響学会 (Role: Contributor, Q26: ケプストラムについてやさしく教えてください)

コロナ社, Mar, 2017 (ISBN: 9784339008951)
音響学入門ペディア

日本音響学会 (Role: Contributor, Q13: 周波数領域領域で設計したフィルタを時間領域にするには?)

コロナ社, Mar, 2017 (ISBN: 9784339008951)
Principles and applications of spatial hearing

S. Sakamoto, J. Kodama, S. Hongo, T. Okamoto, Y. Iwaya, Y. Suzuki (Role: Contributor, Effects of microphone arrangement on the accuracy of a spherical microphone array (SENZI) in acquiring high-definition 3D sound space information)

World Scientific, 2011 (ISBN: 9789814313872)
Principles and applications of spatial hearing

T. Okamoto, B. FG Katz, M. Noisternig, Y. Iwaya, Y. Suzuki (Role: Contributor, Implementation of real-time room auralization using a surrounding 157 loudspeaker array)

World Scientific, 2011 (ISBN: 9789814313872)
Principles and applications of spatial hearing

T. Okamoto, Y. Iwaya, Y. Suzuki (Role: Contributor, Estimation of high-resolution sound properties for realizing an editable sound-space system)

World Scientific, 2011 (ISBN: 9789814313872)

Presentations

Toward the realization of automatic spoken language acquisition mechanism for human-symbiotic robots

T. Shinozaki, T. Okamoto, S. Mori

APSIPA ASC 2021, Dec, 2021
系列変換でできる音声認識・音声合成＋∞ -実装 is all we need-

岡本拓磨

日本音響学会第22回サマーセミナー「音響学の基礎と最近のトピックス」, Aug 24, 2021 Invited
Puredataによるサウンドプログラミングの紹介およびリアルタイムデモ

岡本拓磨

日本音響学会第14回サマーセミナー「音響学の基礎と最近のトピックス」, Jul 30, 2012 Invited
Over 100 channels sound field recording and reproduction systems and their applications

T. Okamoto

Centre for Noise and Viblation Control Seminar, Mar, 2012 Invited

Professional Memberships

Feb, 2014 - Present

IEEE
May, 2013 - Present

Audio Engineering Society
Jun, 2005 - Present

Acousical Society of Japan

Research Projects

Spoken Language Acquisition Agent with Fluent Intonation

Grants-in-Aid for Scientific Research, Grant-in-Aid for Scientific Research (C), Japan Society for the Promotion of Science, Apr, 2022 - Mar, 2025
アクティブマルチスポット音空間再生システムの開発

科学研究費助成事業基盤研究(C), 基盤研究(C), 日本学術振興会, Apr, 2018 - Mar, 2021

岡本拓磨
Development of multilingual-multizone generation system

Grants-in-Aid for Scientific Research Grant-in-Aid for Young Scientists (B), Grant-in-Aid for Young Scientists (B), Japan Society for the Promotion of Science, Apr, 2015 - Mar, 2018

Okamoto Takuma
Improvement for simple summation based sound spot system

Grants-in-Aid for Scientific Research Grant-in-Aid for Young Scientists (B), Grant-in-Aid for Young Scientists (B), Japan Society for the Promotion of Science, Apr, 2013 - Mar, 2015

OKAMOTO Takuma
包囲型マイクロホンアレイを用いた音情報の解析と抽出

科学研究費助成事業特別研究員奨励費, 特別研究員奨励費, 日本学術振興会, 2007 - 2008

岡本拓磨

Academic Activities

Meeting of Acoustical Society of Japan

Panel moderator, session chair, etc.

Sep, 2013 - Present
APSIPA ASC 2021

Panel moderator, session chair, etc.

Dec 16, 2021
INTERSPEECH 2020

Panel moderator, session chair, etc.

Oct 27, 2020