Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
SIP, SP, EA, IPSJ-SLP [detail] |
2024-02-29 16:45 |
Okinawa |
(Primary: On-site, Secondary: Online) |
Multiple Lag Window Pairs for Estimation of Fundamental Frequency and Periodicity Measure Michiki Koshimori (UEC), Shigeki Sagayama (UTokyo/UEC), Toru Nakashika (UEC) EA2023-75 SIP2023-122 SP2023-57 |
Extending the main concept of modified autocorrelation method in LPC, we investigate lag windows, lag window pairs, and ... [more] |
EA2023-75 SIP2023-122 SP2023-57 pp.85-90 |
SIP, SP, EA, IPSJ-SLP [detail] |
2024-03-01 10:40 |
Okinawa |
(Primary: On-site, Secondary: Online) |
Speech representation based on VAE assuming gamma distribution for latent variables and observation Nanako Imaichi, Toru Nakashika (UEC) EA2023-104 SIP2023-151 SP2023-86 |
Recently, deep generative models that can represent complex relationships in data generation have been attracting attent... [more] |
EA2023-104 SIP2023-151 SP2023-86 pp.256-261 |
SIP, SP, EA, IPSJ-SLP [detail] |
2024-03-01 10:40 |
Okinawa |
(Primary: On-site, Secondary: Online) |
An Investigation on the Speech Recovery from EEG Signals Using Transformer Tomoaki Mizuno (The Univ. of Electro-Communications), Takuya Kishida (Aichi Shukutoku Univ.), Natsue Yoshimura (Tokyo Tech), Toru Nakashika (The Univ. of Electro-Communications) EA2023-108 SIP2023-155 SP2023-90 |
Synthesizing full speech from ElectroEncephaloGraphy(EEG) signals is a challenging task. In this paper, speech reconstru... [more] |
EA2023-108 SIP2023-155 SP2023-90 pp.277-282 |
SP, IPSJ-MUS, IPSJ-SLP [detail] |
2023-06-23 13:50 |
Tokyo |
(Primary: On-site, Secondary: Online) |
Impression Conversion of Speech for Unknown Speakers Using FaderNet Saki Kugimoto, Toru Nakashika (UEC) SP2023-2 |
This paper proposes a model that can convert impressions of unknown speakers who do not have impression labels, based on... [more] |
SP2023-2 pp.4-7 |
SP, IPSJ-MUS, IPSJ-SLP [detail] |
2023-06-24 13:50 |
Tokyo |
(Primary: On-site, Secondary: Online) |
[Short Paper]
SBERT-based Musical Components Estimation from Lyrics Trained with Imbalanced "Orpheus" Data Mastuti Puspitasari, Takuya Takahashi (UEC), Gen Hori (AU), Shigeki Sagayama, Toru Nakashika (UEC) SP2023-18 |
This research was done to develop neural models that are capable of estimating appropriate musical components based on l... [more] |
SP2023-18 pp.86-90 |
SP, IPSJ-MUS, IPSJ-SLP [detail] |
2023-06-24 13:50 |
Tokyo |
(Primary: On-site, Secondary: Online) |
Non-chord Tone Data Collection for Music Analysis and Generation Takuya Takahashi, , Toru Nakashika, Shigeki Sagayama (UEC) SP2023-20 |
The non-chord tones are one of the components of harmony theory and play an important role in music analysis and composi... [more] |
SP2023-20 pp.97-102 |
SP, IPSJ-SLP, EA, SIP [detail] |
2023-03-01 10:40 |
Okinawa |
(Primary: On-site, Secondary: Online) |
Diffusion-based parallel voice conversion with source-feature condition Takuya Kishida, Toru Nakashika (UEC) EA2022-107 SIP2022-151 SP2022-71 |
We propose a voice conversion method based on a diffusion probabilistic model trained on a parallel dataset. Since the d... [more] |
EA2022-107 SIP2022-151 SP2022-71 pp.191-196 |
SP, IPSJ-MUS, IPSJ-SLP [detail] |
2022-06-17 15:00 |
Online |
Online |
Blind Source Separation based on Independent Low-Rank Matrix Analysis using Restricted Boltzmann Machines Shotaro Furuta, Takuya Kishida, Toru Nakashika (UEC) SP2022-8 |
In this paper, we propose a new blind source separation method that combines independent low-rank source separation (ILR... [more] |
SP2022-8 pp.26-29 |
SP, IPSJ-MUS, IPSJ-SLP [detail] |
2022-06-18 15:00 |
Online |
Online |
Improved speech analysis using F0-adaptive lag window Michiki Koshimori, Shigeki Sagayama, Takuya Kishida, Toru Nakashika (UEC) SP2022-21 |
The lag window method is based on a source-filter model, which separates the source information from the filter informat... [more] |
SP2022-21 pp.90-93 |
SP, IPSJ-MUS, IPSJ-SLP [detail] |
2022-06-18 15:00 |
Online |
Online |
VAE-VC based on cross-entropy error minimization of LSP frequency intervals Yoshihiro Hiramoto, Shigeki Sagayama, Takuya Kishida, Toru Nakashika (UEC) SP2022-23 |
[more] |
SP2022-23 pp.100-103 |
SP, IPSJ-SLP, IPSJ-MUS |
2021-06-19 15:00 |
Online |
Online |
Unseen speaker's Voice Conversion by FaderNetVC with Speaker Feature Extractor Takumi Isako, Takuya Kishida, Toru Nakashika (UEC) SP2021-20 |
In recent years, many voice conversion models using Deep Neural Network (DNN) have been proposed, and FaderNetVC is one ... [more] |
SP2021-20 pp.91-96 |
SP, SIP, EA |
2017-03-02 13:10 |
Okinawa |
Okinawa Industry Support Center |
Feature Extraction Using Adaptive Restricted Boltzmann Machine for Dysarthric Speech Recognition Yuki Takashima (Kobe Univ.), Toru Nakashika (UEC), Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) EA2016-140 SIP2016-195 SP2016-135 |
[more] |
EA2016-140 SIP2016-195 SP2016-135 pp.321-326 |
NLC, IPSJ-NL, SP, IPSJ-SLP (Joint) [detail] |
2015-12-02 10:25 |
Aichi |
Nagoya Inst of Tech. |
Simultaneous Modelling of Acoustic, Phonetic, Speaker Features Using Improved Three-Way Restricted Boltzmann Machine Toru Nakashika (UEC), Tetsuya Takiguchi (Kobe Univ.) SP2015-71 |
In this paper, we argue the way of modelling speech signals using improved three-way restricted Boltzmann machine (3WRBM... [more] |
SP2015-71 pp.7-12 |
WIT, SP, ASJ-H, PRMU |
2015-06-18 15:15 |
Niigata |
|
Phone Labeling Based on Gaussian Mixture Model for Dysarthric Speech Recognition Yuki Takashima (Kobe Univ.), Toru Nakashika (UEC), Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) PRMU2015-44 SP2015-13 WIT2015-13 |
We investigate in this paper speech recognition for a person with an articulation disorder resulting from athetoid cereb... [more] |
PRMU2015-44 SP2015-13 WIT2015-13 pp.71-76 |
NLC, IPSJ-NL, SP, IPSJ-SLP, JSAI-SLUD (Joint) [detail] |
2014-12-16 13:30 |
Kanagawa |
Tokyo Institute of Technology (Suzukakedai Campus) |
[Poster Presentation]
Voice Conversion Using Speaker Adapted Restricted Boltzmann Machine Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) SP2014-126 |
(Advance abstract in Japanese is available) [more] |
SP2014-126 pp.165-170 |
SP, IPSJ-MUS |
2014-05-25 11:30 |
Tokyo |
|
A joint restricted Boltzmann machine for dictionary learning in sparse-representation-based voice conversion Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) SP2014-34 |
In voice conversion, sparse-representation-based methods have recently been garnering attention because they are, relati... [more] |
SP2014-34 pp.343-348 |
SP, IPSJ-SLP |
2013-12-19 17:15 |
Tokyo |
|
Speaker-dependent conditional restricted Boltzmann machine for voice conversion Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) SP2013-88 |
In this paper, we present a voice conversion (VC) method that utilizes conditional restricted Boltzmann machines (CRBMs)... [more] |
SP2013-88 pp.83-88 |
SP |
2011-07-23 09:55 |
Hokkaido |
Jozankei Grand Hotel |
Constrained Spectrum Generation for Mixed Sound Analysis Based on Probabilistic Spectrum Envelope Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) SP2011-50 |
NMF (Non-negative matrix factorization) has been one of the most widely-used techniques for signal analysis in recent ye... [more] |
SP2011-50 pp.51-56 |
NLC, SP (Joint) [detail] |
2010-12-21 16:40 |
Tokyo |
National Olympics Memorial Youth Center |
Iterative basis generation and supervised non-negative matrix factorization for signal analysis Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) NLC2010-29 SP2010-102 |
NMF (Non-negative Matrix Factorization) has been one of the most useful techniques for signal analysis in recent years.
... [more] |
NLC2010-29 SP2010-102 pp.195-200 |
SP, NLC |
2009-12-22 15:50 |
Tokyo |
Univ. of Tokyo |
A study on speech synthesis by modeling harmonics structure with Multi Beta Mixture Model Toru Nakashika (Kobe Univ.), Ryuki Tachibana, Masafumi Nishimura (IBM Japan), Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) NLC2009-26 SP2009-90 |
There are currently some researches related to speech synthesis, but here we present a new framework
for speech synthes... [more] |
NLC2009-26 SP2009-90 pp.165-170 |