Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
NC, MBE (Joint) |
2024-03-11 16:50 |
Tokyo |
The Univ. of Tokyo (Primary: On-site, Secondary: Online) |
A Method of Timbre Synthesis Reflecting Impression Using Conditional-VAE
-- Applying the Temporal Information -- Miyu Yoshikawa, Susumu Kuroyanagi (NIT) NC2023-49 |
It is difficult to systematically explain the relationship between tones and the impressions people have of them. In th... [more] |
NC2023-49 pp.37-42 |
PRMU, IPSJ-CVIM, IPSJ-DCC, IPSJ-CGVI |
2023-11-17 09:20 |
Tottori |
(Primary: On-site, Secondary: Online) |
Co-speech Gesture Generation with Variational Auto Encoder Shihichi Ka, Koichi Shinoda (Tokyo Tech) PRMU2023-29 |
Co-speech gesture generation is the study of generating gestures from speech. In prior works, deterministic methods lear... [more] |
PRMU2023-29 pp.74-79 |
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 |
NC, MBE (Joint) |
2023-03-14 15:25 |
Tokyo |
The Univ. of Electro-Communications (Primary: On-site, Secondary: Online) |
A Method of Timbre Synthesis Reflecting Impression Using Conditional-VAE
-- Conditioning by Impression and Generating Sound Waveforms -- Takeru Watanabe, Susumu Kuroyanagi (NIT) NC2022-106 |
In This paper, we aim to propose a method of timbre synthesis based on impressions recalled by humans. We worked on this... [more] |
NC2022-106 pp.84-89 |
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 |
EA, US (Joint) |
2022-12-22 13:30 |
Hiroshima |
Satellite Campus Hiroshima |
[Poster Presentation]
Quality Improvement of Children's Speech with Multiple Inputs of Speaker Vectors in a General Purpose Vocoder Satoshi Yoshida, Ken'ichi Furuya (Oita Univ.), Hideyuki Mizuno (SUS) EA2022-64 |
Neural vocoders used in speech synthesis are capable of synthesizing high-quality speech that is indistinguishable from ... [more] |
EA2022-64 pp.18-23 |
SP, IPSJ-MUS, IPSJ-SLP [detail] |
2022-06-18 10:50 |
Online |
Online |
[Invited Talk]
Crazy vocoder is unbreakable
-- But let's talk about an informal vision of the future -- Masanori Morise (Meiji Univ.) SP2022-15 |
When current speech synthesis researchers refer to Vocoder in their papers, they are most likely referring to Neural voc... [more] |
SP2022-15 pp.61-66 |
WIT, IPSJ-AAC |
2022-03-08 10:55 |
Online |
Online |
A study on high-intelligibility speech synthesis of dysarthric speakers using voice conversion from normal speech and multi-speaker vocoder Tetsuro Takano (HTS), Takashi Nose, Aoi Kanagaki (Tohoku Univ.), Satoshi Watanabe (HTS) WIT2021-46 |
In this study, we investigated the possibility of generating intelligible synthetic speech by converting the voice of a ... [more] |
WIT2021-46 pp.18-23 |
EA, US (Joint) |
2021-12-22 13:30 |
Kumamoto |
Sojo University |
[Poster Presentation]
Improved voice quality due to multi-speaker learning with WaveNet vocoder Satoshi Yoshida, Shingo Uenohara, Ken'ichi Furuya (Oita Univ.) EA2021-57 |
In recent years, speech synthesis and voice quality conversion techniques using neural networks have attracted much atte... [more] |
EA2021-57 pp.1-6 |
EA, US, SP, SIP, IPSJ-SLP [detail] |
2021-03-03 14:05 |
Online |
Online |
[Poster Presentation]
A unified source-filter network for neural vocoder Reo Yoneyama, Yi-Chiao Wu, Tomoki Toda (Nagoya Univ.) EA2020-69 SIP2020-100 SP2020-34 |
In this paper, we propose a method to develop a neural vocoder using a single network based on the source-filter theory.... [more] |
EA2020-69 SIP2020-100 SP2020-34 pp.57-62 |
WIT, SP, IPSJ-SLP [detail] |
2020-10-22 13:00 |
Online |
Online |
[Invited Talk]
NHK's activities on Japanese end-to-end speech synthesis Kiyoshi Kurihara (NHK) SP2020-11 WIT2020-12 |
The main business of NHK (Japan Broadcasting Corporation) is the production and broadcasting of programs. Many programs ... [more] |
SP2020-11 WIT2020-12 pp.19-20 |
RECONF |
2020-05-28 15:15 |
Online |
Online |
RECONF2020-7 |
A Bayesian network is one of the graphical models that represent the causality or correlation of multiple observed pheno... [more] |
RECONF2020-7 pp.37-42 |
PRMU, IPSJ-CVIM |
2020-03-16 11:15 |
Kyoto |
(Cancelled but technical report was issued) |
Image Synthesis Based on Style Features and Mask Images Using a Ramen Style Encoder Jaehyeong Cho, Wataru Shimoda, Keiji Yanai (UEC) PRMU2019-71 |
(To be available after the conference date) [more] |
PRMU2019-71 pp.33-38 |
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 |
AI |
2020-02-14 14:40 |
Shimane |
Izumo Campus, Shimane University |
Quine's Philosophy concerning Analysis and Synthesis of Data
-- Reflecting "Two Dogmas of Empiricism" from a Modern Perspective -- Makoto Koike (MK Microwave) AI2019-47 |
Although“Two Dogmas of Empiricism” by Quine relates to metaphysics such as empiricism and analytical philosophy, its ess... [more] |
AI2019-47 pp.23-31 |
SP |
2020-01-29 11:30 |
Toyama |
|
Application of Deep Gaussian Process to Multi-Speaker Text-to-Speech Synthesis using Speaker Codes Kentaro Mitsui, Tomoki Koriyama, Hiroshi Saruwatari (UTokyo) SP2019-49 |
Speaker codes are widely used to achieve multi-speaker text-to-speech synthesis.
Conventionally, Deep Neural Network (D... [more] |
SP2019-49 pp.31-36 |
IT, SIP, RCS |
2020-01-24 09:30 |
Hiroshima |
Hiroshima City Youth Center |
Precoder Design Algorithm using Spatial Signal Synthesis with Multiple Antenna Subset Selection for Hybrid MIMO System Daichi Tamate, Yukitoshi Sanada (Keio Univ.) IT2019-60 SIP2019-73 RCS2019-290 |
In this paper, a precoder design algorithm using spatial signal synthesis with selected multiple antennas for hybrid mul... [more] |
IT2019-60 SIP2019-73 RCS2019-290 pp.135-141 |
IPSJ-SLDM, RECONF, VLD, CPSY, IPSJ-ARC [detail] |
2020-01-23 11:50 |
Kanagawa |
Raiosha, Hiyoshi Campus, Keio University |
Binary Synthesis from RISC-V Executables Shoki Hamana, Nagisa Ishiura (Kwansei Gakuin Univ.) VLD2019-71 CPSY2019-69 RECONF2019-61 |
This article presents a method of synthesizing hardware from RISC-V binary codes. RISC-V is an open source instruction s... [more] |
VLD2019-71 CPSY2019-69 RECONF2019-61 pp.111-115 |