Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
SP, IPSJ-SLP, IPSJ-MUS |
2021-06-19 15:00 |
Online |
Online |
Source Separation for Asynchronous Recordings of Conversation Using Time-Frequency Masking and Independent Vector Analysis Haruki Nammoku, Kouei Yamaoka, Yukoh Wakabayashi, Nobutaka Ono (TMU) SP2021-22 |
In this study, we investigate the source separation for conversational speech recorded by multiple voice recorders that ... [more] |
SP2021-22 pp.101-106 |
EMM |
2020-03-05 14:25 |
Okinawa |
(Cancelled but technical report was issued) |
[Poster Presentation]
Proposal of BSS-based video watermarking method using similarity between frames Akane Yokota, Masaki Kawamura (Yamaguchi Univ.) EMM2019-105 |
Movies are composed of sequential still images, and similarity between consecutive frames is very high.
In this work, w... [more] |
EMM2019-105 pp.19-24 |
SP, EA, SIP |
2020-03-02 10:10 |
Okinawa |
Okinawa Industry Support Center (Cancelled but technical report was issued) |
Multichannel NMF with Joint-Diagonalizable Constraint Based on Generalized Gaussian Distribution for Blind Source Separation Keigo Kamo, Yuki Kubo, Norihiro Takamune (UTokyo), Daichi Kitamura (NIT Kagawa), Hiroshi Saruwatari (UTokyo), Yu Takahashi, Kazunobu Kondo (Yamaha) EA2019-103 SIP2019-105 SP2019-52 |
Multichannel nonnegative matrix factorization (MNMF) is a blind source separation technique, which employs the full-rank... [more] |
EA2019-103 SIP2019-105 SP2019-52 pp.13-19 |
EA |
2019-12-13 13:25 |
Fukuoka |
Kyushu Inst. Tech. |
Rank-constrained spatial covariance matrix estimation based on multivariate complex generalized Gaussian distribution and its acceleration for blind speech extraction Yuki Kubo, Norihiro Takamune (UTokyo), Daichi Kitamura (NIT, Kagawa), Hiroshi Saruwatari (UTokyo) EA2019-78 |
In this paper, we generalize a generative model in rank-constrained spatial covariance matrix estimation that separates ... [more] |
EA2019-78 pp.85-92 |
EA, ASJ-H |
2019-10-28 14:00 |
Tokyo |
NHK Science&Technology Research Lab. |
FastMNMF based on multivariant complex Student's t distribution for blind source separation Keigo Kamo, Yuki Kubo, Norihiro Takamune (UTokyo), Daichi Kitamura (Kagawa NCIT), Hiroshi Saruwatari (UTokyo), Yu Takahashi, Kazunobu Kondo (Yamaha) EA2019-40 |
FastMNMF is a blind source separation technique, which is an accelerated algorithm of multichannel nonnegative matrix fa... [more] |
EA2019-40 pp.23-29 |
RCS |
2019-10-25 16:05 |
Kanagawa |
Yokosuka Research Park |
[Encouragement Talk]
Nonlinear Feature Extraction by epsilon -Vanishing Polynomial Networks Learning and Underdetermined BSS Lu Wang, Tomoaki Ohtsuki (Keio Univ.) RCS2019-202 |
Similar to the deep architectures, a novel multi-layer architecture is used to extend the linear blind source separation... [more] |
RCS2019-202 pp.133-138 |
RCS |
2019-04-19 10:55 |
Hokkaido |
Noboribetsu Grand Hotel |
Blind Source Separation in Nonlinear Mixture: Separation and a Multi-Subspace Representation Lu Wang, Tomoaki Ohtsuki (Keio Univ.) RCS2019-16 |
The process deals with blind source separation in the nonlinear domain is to estimate the original signals or mixture fu... [more] |
RCS2019-16 pp.73-78 |
EA, SIP, SP |
2019-03-14 10:25 |
Nagasaki |
i+Land nagasaki (Nagasaki-shi) |
Blind speech separation based on approximate joint diagonalization utilizing correlation between neighboring frequency bins Taiki Asamizu, Toshihiro Furukawa (TUS) EA2018-100 SIP2018-106 SP2018-62 |
In this paper, we propose a new method that extends the approximate joint diagonalization blind speech separation (BSS).... [more] |
EA2018-100 SIP2018-106 SP2018-62 pp.7-12 |
EA, SIP, SP |
2019-03-14 15:15 |
Nagasaki |
i+Land nagasaki (Nagasaki-shi) |
Convergence-guaranteed independent positive semidefinite tensor analysis for blind source separation Kanta Fukushige, Norihiro Takamune (UTokyo), Daichi Kitamura (Kagawa-NICT), Hiroshi Saruwatari (UTokyo), Rintaro Ikeshita, Tomohiro Nakatani (NTT) EA2018-127 SIP2018-133 SP2018-89 |
This paper focuses on independent positive semidefinite tensor analysis (IPSDTA), which is a technique for over-determin... [more] |
EA2018-127 SIP2018-133 SP2018-89 pp.167-172 |
EA, SIP, SP |
2019-03-14 15:40 |
Nagasaki |
i+Land nagasaki (Nagasaki-shi) |
Estimation of rank-constrained spatial covariance model based on multivariate complex Student's t distribution for blind source separation Yuki Kubo, Norihiro Takamune (UTokyo), Daichi Kitamura (Kagawa NCIT), Hiroshi Saruwatari (UTokyo) EA2018-128 SIP2018-134 SP2018-90 |
In this paper, we generalize a generative model in estimation of rank-constrained spatial covariance model that separate... [more] |
EA2018-128 SIP2018-134 SP2018-90 pp.173-178 |
EA, SIP, SP |
2019-03-15 11:25 |
Nagasaki |
i+Land nagasaki (Nagasaki-shi) |
[Invited Talk]
Realization of real-time blind source separation with auxiliary-function-based algorithms Nobutaka Ono (TMU) EA2018-133 SIP2018-139 SP2018-95 |
Blind source separation is a signal processing technique to estimate sound source signals only from the observation of m... [more] |
EA2018-133 SIP2018-139 SP2018-95 p.203 |
RCS, SR, SRW (Joint) |
2019-03-06 10:55 |
Kanagawa |
YRP |
Performance Analysis for Nonlinear Separation Model with a Flexible Approximation Lu Wang, Tomoaki Ohtsuki (Keio Univ.) RCS2018-292 |
The process deals with blind source separation in the nonlinear domain is to estimate the original signals or mixture fu... [more] |
RCS2018-292 pp.61-66 |
NC, MBE (Joint) |
2019-03-05 11:10 |
Tokyo |
University of Electro Communications |
Unsupervised blind source separation using self conditioned entropy minimization Yuan-chieh Ling, Toshitake Asabuki (UTokyo), Tomoki Fukai (RIKEN CBS) NC2018-67 |
Unsupervised blind source separation refers to extracting underlying source signals from mixed signals without additiona... [more] |
NC2018-67 pp.127-129 |
SIS, ITE-BCT |
2018-10-25 10:00 |
Kyoto |
Kyoto University Clock Tower Centennial Hall |
Accuracy Analysis of Background Noise Estimation Using Outer Product Expansion with Lower Norm Kouta Sugiura, Akitoshi Itai (Chubu Univ.) SIS2018-10 |
In this paper, the background noise estimation using outer product expansion is developed.
We have shown that a possib... [more] |
SIS2018-10 pp.1-5 |
SIP, EA, SP, MI (Joint) [detail] |
2018-03-19 09:00 |
Okinawa |
|
Adaptive BSS algorithm for approximate joint diagonalization with variable epoch length Kei Nishiyama, Shinya Saito (TUS), Kunio Oishi (TUT), Toshihiro Furukawa (TUS) EA2017-102 SIP2017-111 SP2017-85 |
This paper presents an adaptive blind speech separation (BSS) technique for recovering original speech source signals fr... [more] |
EA2017-102 SIP2017-111 SP2017-85 pp.1-6 |
SIP, EA, SP, MI (Joint) [detail] |
2018-03-20 09:00 |
Okinawa |
|
[Poster Presentation]
Blind Source Separation Based on the Sparsity of Impulse Responses Ryota Oda, Daichi Kitahara, Akira Hirabayashi (Ritsumeikan Univ.) EA2017-164 SIP2017-173 SP2017-147 |
We propose a blind source separation (BSS) algorithm using a priori information of the mixing process based on the state... [more] |
EA2017-164 SIP2017-173 SP2017-147 pp.341-346 |
EA, ASJ-H |
2017-12-01 14:20 |
Overseas |
University of Auckland (New Zealand) |
[Invited Talk]
Blind Audio Source Separation based on Independent Component Analysis Shoji Makino (Univ. of Tsukuba) EA2017-78 |
This talk describes a method for the blind source separation (BSS) of convolutive mixtures of audio signals, especially ... [more] |
EA2017-78 p.107 |
MBE, NC (Joint) |
2017-11-25 15:10 |
Miyagi |
Tohoku University |
Ensemble Learning with Feature Extraction for EEG Signal Discrimination using Source Separation Shuichi Nishino, Tomohiro Yoshikawa, Takeshi Furuhashi (Nagoya Univ.) NC2017-36 |
BCI allows a user to control external devices and to communicate with other people by measuring and discriminating EEG. ... [more] |
NC2017-36 pp.49-52 |
EA, ASJ-H |
2017-10-22 09:00 |
Toyama |
Ushidake-Onsen |
[Invited Talk]
Blind source separation based on independent low-rank matrix analysis Daichi Kitamura (UT), Nobutaka Ono (NII), Hiroshi Sawada, Hirokazu Kameoka (NTT), Hiroshi Saruwatari (UT) EA2017-56 |
In this paper, we propose a new effective algorithm for blind source separation problem (BSS) called independent low-ran... [more] |
EA2017-56 pp.73-80 |
SP |
2017-08-30 11:00 |
Kyoto |
Kyoto Univ. |
[Poster Presentation]
Semi-blind speech separation and enhancement using recurrent neural network Masaya Wake, Yoshiaki Bando, Masato Mimura, Katsutoshi Itoyama, Kazuyoshi Yoshii, Tatsuya Kawahara (Kyoto Univ.) SP2017-22 |
This paper describes a semi-blind speech enhancement method using a neural network.
In a human-robot speech interaction... [more] |
SP2017-22 pp.13-18 |