Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
SP, IPSJ-MUS, IPSJ-SLP [detail] |
2023-06-23 13:50 |
Tokyo |
(Primary: On-site, Secondary: Online) |
[Poster Presentation]
MS-Harmonic-Net++ vs SiFi-GAN: Comparison of fundamental frequency controllable fast neural waveform generative models. Sota Shimizu (Kobe Univ./NICT), Takuma Okamoto (NICT), Ryoichi Takashima (Kobe Univ.), Yamato Ohtani (NICT), Tetsuya Takiguchi (Kobe Univ.), Tomoki Toda (Nagoya Univ./NICT), Hisashi Kawai (NICT) SP2023-5 |
Although Harmonic-Net+ has been proposed as a fundamental frequency (fo) and speech rate (SR) controllable fast neural v... [more] |
SP2023-5 pp.20-25 |
SP, IPSJ-MUS, IPSJ-SLP [detail] |
2023-06-24 13:50 |
Tokyo |
(Primary: On-site, Secondary: Online) |
Fast Neural Waveform Generation Model With Fully Connected Upsampling Haruki Yamashita (Kobe cniv/NICT), Takuma Okamoto (NICT), Ryoichi Takashima (Kobe Univ), Yamato Ohtani (NICT), Tetsuya Takiguchi (Kobe Univ), Tomoki Toda (Nagoya Univ/NICT), Hisashi Kawai (NICT) SP2023-15 |
In recent years, in text-to-speech synthesis, it is required to improve the inference speed while keeping the quality.
... [more] |
SP2023-15 pp.73-78 |
SP, IPSJ-MUS, IPSJ-SLP [detail] |
2023-06-24 13:50 |
Tokyo |
(Primary: On-site, Secondary: Online) |
Evaluation of multi-speaker text-to-speech synthesis using a corpus for speech recognition with x-vectors for various speech styles Koki Hida (Wakayama Univ/NICT), Takuma Okamoto (NICT), Ryuichi Nisimura (Wakayama Univ), Yamato Ohtani (NICT), Tomoki Toda (Nagoya Univ/NICT), Hisashi Kawai (NICT) SP2023-25 |
We have implemented multi-speaker end-to-end text-to-speech synthesis based on JETS using x-vectors as speaker embedding... [more] |
SP2023-25 pp.125-130 |
SP, IPSJ-SLP, EA, SIP [detail] |
2023-02-28 09:10 |
Okinawa |
(Primary: On-site, Secondary: Online) |
Comparison of fundamental frequency controllable fast neural waveform generative models. Sota Shimizu (Kobe Univ./NICT), Takuma Okamoto (NICT), Ryoichi Takashima, Tetsuya Takiguchi (Kobe Univ.), Tomoki Toda (Nagoya Univ./NICT), Hisashi Kawai (NICT) EA2022-75 SIP2022-119 SP2022-39 |
Neural vocoders, which reconstruct speech waveforms from acoustic features with deep neural networks, have significantly... [more] |
EA2022-75 SIP2022-119 SP2022-39 pp.1-6 |
SP, IPSJ-SLP, EA, SIP [detail] |
2023-02-28 09:30 |
Okinawa |
(Primary: On-site, Secondary: Online) |
MS-FC-HiFiGAN : Fast Neural Waveform Generation Model With Learnable Lightweight Upsampling Haruki Yamashita (Kobe Univ/NICT), Takuma Okamoto (NICT), Ryoichi Takashima, Tetsuya Takiguchi (Kobe Univ), Tomoki Toda (Nagoya Univ/NICT), Hisashi Kawai (NICT) EA2022-76 SIP2022-120 SP2022-40 |
In recent years, in text-to-speech synthesis, it is required to improve the inference speed while keeping the quality.
... [more] |
EA2022-76 SIP2022-120 SP2022-40 pp.7-12 |
SP, IPSJ-SLP, EA, SIP [detail] |
2023-02-28 13:00 |
Okinawa |
(Primary: On-site, Secondary: Online) |
[Invited Talk]
Multiple sound spot synthesis meets multilingual speech synthesis
-- Implementation is really all we need -- Takuma Okamoto (NICT) EA2022-87 SIP2022-131 SP2022-51 |
A multilingual multiple sound spot synthesis system is implemented as a user interface for real-time speech translation ... [more] |
EA2022-87 SIP2022-131 SP2022-51 pp.73-76 |
EMCJ, IEE-EMC |
2020-11-27 13:35 |
Online |
Online |
Lens Antenna System Design and Beam Focal Field Distribution Measurement in Millimeter-Wave Band Focusing/Parallel Beam Measurement System Takuma Okamoto, Atsuhiro Nishikata (TokyoTech), Masataka Midori, Hiroshi Kurihara (TDK) EMCJ2020-51 |
[more] |
EMCJ2020-51 pp.1-6 |
EMCJ |
2020-04-17 14:00 |
Ishikawa |
Kanazawa Univ. Satellite 3F (Cancelled but technical report was issued) |
Construction of Focused/Parallel Beam Measurement System in Millimeter Wave Band and Improvement of Calculation Procedure of Transmission and Reflection Characteristics for Anisotropic Planer Materials Takuma Okamoto, Atsuhiro Nishikata (Tokyo Tech), Hiroshi Kurihara (TDK) EMCJ2020-2 |
The focused beam method and the parallel beam method, which are used as electrical constant measurement methods mainly f... [more] |
EMCJ2020-2 pp.5-10 |
SP, EA, SIP |
2020-03-02 09:20 |
Okinawa |
Okinawa Industry Support Center (Cancelled but technical report was issued) |
Investigation of neural speech rate conversion with multi-speaker WaveNet vocoder Takuma Okamoto (NICT), Keisuke Matsubara (Kobe Univ./NICT), Tomoki Toda (Nagoya Univ./NICT), Yoshinori Shiga, Hisashi Kawai (NICT) EA2019-101 SIP2019-103 SP2019-50 |
Speech rate conversion technology, which can expand or compress speech waveforms without changing pitch of sound, is con... [more] |
EA2019-101 SIP2019-103 SP2019-50 pp.1-6 |
EMCJ |
2019-07-18 10:05 |
Tokyo |
Kikai-Shinko-Kaikan Bldg. |
Formulation of focused beam method by plane wave spectrum representation for anisotropic planar material measurement system Takuma Okamoto, Atsuhiro Nishikata (Tokyo Tech), Hiroshi Kurihara (TDK) EMCJ2019-18 |
[more] |
EMCJ2019-18 pp.1-5 |
EA, US (Joint) |
2019-01-22 16:15 |
Kyoto |
Doshisha Univ. |
[Invited Talk]
Spatial Fourier transform-based localized sound zone generation with loudspeaker arrays Takuma Okamoto (NICT) EA2018-98 |
This paper provides spatial Fourier transform-based localized sound zone generation methods with multiple loudspeakers. ... [more] |
EA2018-98 pp.31-36 |
EA, ASJ-H |
2017-08-09 15:45 |
Miyagi |
Tohoku Univ., R. I. E. C. |
[Invited Talk]
Realization of 252ch real-time processing of SENZI binaural sound-space sensing and reproduction method Shuichi Sakamoto (Tohoku Univ.), Satoshi Hongo (NIT, Sendai College), Takuma Okamoto (NICT), Yukio Iwaya (Tohoku Gakuin Univ.), Yo-iti Suzuki (Tohoku Univ.) EA2017-33 |
It is crucially important to reproduce accurate auditory spatial information around listeners for development of advance... [more] |
EA2017-33 pp.39-40 |
EA, ASJ-H |
2015-08-03 15:50 |
Miyagi |
Tohoku Univ., Research Inst. of Electrical Communication |
Multiple sound spots generation by spatial filtering in wavenumber domain using a linear loudspeaker array Takuma Okamoto (NICT), Atsushi Sakaguchi (Panasonic) EA2015-15 |
An analytical method for generating acoustically bright and dark zones at arbitrary horizontal positions using a linear ... [more] |
EA2015-15 pp.29-34 |
EA |
2014-04-17 15:30 |
Kyoto |
NICT Universal Communication Research Lab. |
Spherical harmonic encoding of moving sound sources Jorge Trevino (Tohoku Univ.), Takuma Okamoto (NICT), Yukio Iwaya (Tohoku Gakuin Univ.), Yo-iti Suzuki (Tohoku Univ.) EA2014-3 |
The spatial information of sound fields can be encoded using the spherical harmonic functions. This is often applied to ... [more] |
EA2014-3 pp.19-24 |
EA |
2014-04-17 16:05 |
Kyoto |
NICT Universal Communication Research Lab. |
Local sound area generation using a circular loudspeaker array and an additional loudspeaker Takuma Okamoto (NICT) EA2014-4 |
Reproduction errors are occurred except at the reference circle in sound field reproduction using a circular loudspeaker... [more] |
EA2014-4 pp.25-30 |
EA |
2013-12-13 15:50 |
Ishikawa |
Satellite Plaza of Kanazawa University |
Multiple sound spots generation by spatial filtering in wavenumber domain using a linear loudspeaker array Takuma Okamoto (NICT) EA2013-94 |
Novel signal processing is proposed for generating acoustically bright and dark zones at arbitrary horizontal positions ... [more] |
EA2013-94 pp.37-42 |
EA |
2013-10-11 12:30 |
Kyoto |
NTT CS Lab. |
Sound field recording and reproduction by multiple parallel linear arrays using crosstalk cancellers in spatio-temporal frequency domain Takuma Okamoto, Seigo Enomoto, Ryouichi Nishimura (NICT) EA2013-64 |
A novel signal processing for sound field recording and reproduction using parallel multiple linear microphone / loudspe... [more] |
EA2013-64 pp.1-8 |
COMP |
2013-06-24 10:00 |
Nara |
Nara Women's University |
Morpion Solitaire: a new upper bound 121 of the maximum score Akitoshi Kawamura (Univ. of Tokyo), Takuma Okamoto, Yuichi Tatsu, Yushi Uno, Masahide Yamato (Osaka Prefecture Univ.) COMP2013-19 |
Morpion Solitaire is a pencil-and-paper game for a single player, popular in several countries including
France. A move... [more] |
COMP2013-19 pp.1-6 |
EA, EMM |
2012-11-17 14:10 |
Oita |
OITA Univ. |
Estimation of sound field based on inversion of Kirchhoff-Helmholtz integral equation and forward wave propagation Takuma Okamoto, Seigo Enomoto, Ryouichi Nishimura (NICT) EA2012-105 EMM2012-87 |
We propose a novel sound field estimation method based on inversion of Kirchhoff-Helmholtz integral equation and forward... [more] |
EA2012-105 EMM2012-87 pp.141-146 |
EA |
2012-08-01 14:40 |
Miyagi |
Tohoku Gakuin University |
Improvement of the accuracy of 3D sound space synthesized by 252ch real-time processing of SENZI sound space information acquisition system Shuichi Sakamoto, Jumpei Matsunaga (Tohoku Univ.), Satoshi Hongo (SNCT), Takuma Okamoto (NICT), Yukio Iwaya (Tohoku Gakuin Univ.), Yo-iti Suzuki (Tohoku Univ.) EA2012-55 |
[more] |
EA2012-55 pp.7-12 |