Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
CAS, CS |
2024-03-14 15:55 |
Okinawa |
|
Residual Noise Removal in of Sound Source Separation Signal by Spectral Replacement Taiga Saito, Kenji Suyama (Tokyo Denki Univ.) CAS2023-122 CS2023-115 |
Although sound source separation method based on a multiplication of multiple weighted sum circuits has high suppression... [more] |
CAS2023-122 CS2023-115 pp.64-69 |
SIP, SP, EA, IPSJ-SLP [detail] |
2024-02-29 09:50 |
Okinawa |
(Primary: On-site, Secondary: Online) |
Derivation of Direct Update Rule for Back-Projected Separation Matrix Yui Kuriki, Taishi Nakashima, Nobutaka Ono (TMU) EA2023-66 SIP2023-113 SP2023-48 |
Blind source separation (BSS) is a widely used technique for separating mixed signals originating from multiple sources.... [more] |
EA2023-66 SIP2023-113 SP2023-48 pp.31-36 |
SIP, SP, EA, IPSJ-SLP [detail] |
2024-02-29 10:10 |
Okinawa |
(Primary: On-site, Secondary: Online) |
Analysis of Overlapped Utterances in Everyday Conversation and Source Separation by Online Independent Vector Analysis for Asynchronous Distributed Recordings Haruki Nammoku, Taishi Nakashima, Kouei Yamaoka, Yukoh Wakabayashi, Nobutaka Ono (TMU) EA2023-67 SIP2023-114 SP2023-49 |
In this study, we investigate the effects of overlapped utterances on transcription in everyday conversation and propose... [more] |
EA2023-67 SIP2023-114 SP2023-49 pp.37-42 |
SIP, SP, EA, IPSJ-SLP [detail] |
2024-02-29 10:30 |
Okinawa |
(Primary: On-site, Secondary: Online) |
Accelerating and stabilizing vectorwise coordinate descent for spatially regularized independent low-rank matrix analysis Yuto Ishikawa, Takuya Okubo, Norihiro Takamune (UTokyo), Tomohiko Nakamura (AIST), Daichi Kitamura (NIT Kagawa), Hiroshi Saruwatari (UTokyo), Yu Takahashi, Kazunobu Kondo (Yamaha) EA2023-68 SIP2023-115 SP2023-50 |
Spatially regularized independent low-rank matrix analysis (SR-ILRMA) is the method that introduces the spatial prior in... [more] |
EA2023-68 SIP2023-115 SP2023-50 pp.43-50 |
SIP, SP, EA, IPSJ-SLP [detail] |
2024-02-29 16:20 |
Okinawa |
(Primary: On-site, Secondary: Online) |
Comparison of DNN architectures for determined BSS by proximal average of IVA and DNN Kazuki Matsumoto (Waseda Univ.), Koki Yamada, Kohei Yatabe (TUAT) EA2023-88 SIP2023-135 SP2023-70 |
We have proposed a framework called PA-BSS for high-performance separation matrix estimation using deep denoisers based ... [more] |
EA2023-88 SIP2023-135 SP2023-70 pp.162-167 |
SIP, SP, EA, IPSJ-SLP [detail] |
2024-03-01 16:35 |
Okinawa |
(Primary: On-site, Secondary: Online) |
Evaluations of Multi-channel Blind Source Separation for Speech Recognition in Car Environments Yutsuki Takeuchi, Natsuki Ueno, Nobutaka Ono (Tokyo Metropolitan Univ.), Takashi Takazawa, Shuhei Shimanoe, Tomoki Tanemura (MIRISE Technologies) EA2023-127 SIP2023-174 SP2023-109 |
In car environments, speech recognition is difficult due to various types of noise. For this issue, speech enhancement b... [more] |
EA2023-127 SIP2023-174 SP2023-109 pp.388-393 |
EST |
2024-01-26 14:50 |
Kyoto |
Kyoto University ROHM Plaza (Primary: On-site, Secondary: Online) |
Magnetic field separation of DC signal source in geomagnetic environment by using tensor decomposition Yuji Ogata, Tomonori Yanagida, Bunichi Kakinuma, Masayuki Kimishima (Advantest Lab) EST2023-120 |
In non-destructive testing and tracking using magnetic fields, it is necessary to estimate the position of the signal so... [more] |
EST2023-120 pp.117-122 |
EA, US (Joint) |
2023-12-22 13:00 |
Fukuoka |
|
[Poster Presentation]
Multichannel Blind Source Separation Using Independent Low-Rank Matrix Analysis with Observed-Signal-Dependent Regularization Based on Spectrogram Consistency Takaaki Kojima, Norihiro Takamune, Sota Misawa (UTokyo), Daichi Kitamura (NIT,Kagawa), Hiroshi Saruwatari (UTokyo) EA2023-51 |
Independent low-rank matrix analysis (ILRMA) is the state-of-the-art technique for blind source separation under the ove... [more] |
EA2023-51 pp.13-20 |
SR |
2023-11-10 10:55 |
Miyagi |
(Primary: On-site, Secondary: Online) |
[Short Paper]
On Model Transfer with Deep Joint Source Channel Coding Katsuya Suto, Issa Matsumura, Junichiro Yamada (UEC) SR2023-58 |
Based on the source channel separation theorem, the current multimedia transfer system employs independently designed so... [more] |
SR2023-58 pp.61-63 |
SIS |
2023-03-02 11:00 |
Chiba |
Chiba Institute of Technology (Primary: On-site, Secondary: Online) |
Blink detection from one-dimensional face signal by using convolutional sparse dictionary learning Souichiro Maruyama, Makoto Nakashizuka (CIT) SIS2022-40 |
In this report, a blink detection method from average intensities of whole facial videos using convolutional dictionary... [more] |
SIS2022-40 pp.1-4 |
CAS, CS |
2023-03-01 10:20 |
Fukuoka |
Kitakyushu International Conference Center (Primary: On-site, Secondary: Online) |
Approximate joint diagonalization for blind separation of superimposed images Shinya Saito, Kunio Oishi (Tokyo University of Tech.) CAS2022-98 CS2022-75 |
This report presents blind separation of superimposed images. When we take a picture for panorama thought window glass a... [more] |
CAS2022-98 CS2022-75 pp.12-17 |
CAS, CS |
2023-03-02 15:40 |
Fukuoka |
Kitakyushu International Conference Center (Primary: On-site, Secondary: Online) |
Sound Quality Improvement of Source Separation Signal by Binary Mask Taiga Saito, Kenji Suyama (Tokyo Denki Univ.) CAS2022-122 CS2022-99 |
A two-microphone source separation method using multiple complex weighted sum circuits (WSCs) has been proposed. However... [more] |
CAS2022-122 CS2022-99 pp.150-154 |
SP, IPSJ-SLP, EA, SIP [detail] |
2023-03-01 09:50 |
Okinawa |
(Primary: On-site, Secondary: Online) |
Regularization Term Design Based on Spectrogram Consistency in Independent Low-Rank Matrix Analysis for Multichannel Audio Source Separation Sota Misawa, Norihiro Takamune (UTokyo), Kohei Yatabe (TUAT), Daichi Kitamura (NIT, Kagawa), Hiroshi Saruwatari (UTokyo) EA2022-105 SIP2022-149 SP2022-69 |
It is known that block permutation occurs in the separated signals obtained by independent low-rank matrix analysis. Rec... [more] |
EA2022-105 SIP2022-149 SP2022-69 pp.177-184 |
ICTSSL, CAS |
2023-01-26 14:20 |
Tokyo |
TBD (Primary: On-site, Secondary: Online) |
Effects of Suppression Section Expansion in Actual Room Environment Sound Source Separation Tsukasa Hidaka, Kenji Suyama (Tokyo Denki Univ.) CAS2022-71 ICTSSL2022-35 |
In actual room environments, it is easy to assume that the sound source signal arrives with any spatial propagation spre... [more] |
CAS2022-71 ICTSSL2022-35 pp.51-55 |
ICTSSL, CAS |
2023-01-26 14:40 |
Tokyo |
TBD (Primary: On-site, Secondary: Online) |
Sound Source Separation Avoiding Sound Quality Degradation by Spatial Propagation Kai Furusawa, Kenji Suyama (Tokyo Denki Univ.) CAS2022-72 ICTSSL2022-36 |
In general, the farther the distance between the microphone and the sound source, the greater the spatial propagation sp... [more] |
CAS2022-72 ICTSSL2022-36 pp.56-61 |
EA, US (Joint) |
2022-12-23 09:00 |
Hiroshima |
Satellite Campus Hiroshima |
Proposal of Speech Decomposition Algorithm by Cepstral-Basis-Decomposed Nonnegative Matrix Factorization and Application to Speech Source Separation Technique Fuga Oshima, Masashi Nakayama (Hiroshima City) EA2022-69 |
Nonnegative matrix factorization (NMF) is the algorithm that effectively represents acoustical signals by inputting ampl... [more] |
EA2022-69 pp.49-54 |
EA, EMM, ASJ-H |
2022-11-21 10:00 |
Online |
Online |
[Poster Presentation]
Sound signal mixing method using both source-separated and non-separated signals Yuto Nishitani, Kota Takahashi (UEC) EA2022-48 EMM2022-48 |
We are researching a smart mixer, a device that performs better sound mixing than conventional sound mixers.
The smart ... [more] |
EA2022-48 EMM2022-48 pp.40-45 |
EA, ASJ-H |
2022-08-04 15:15 |
Miyagi |
(Primary: On-site, Secondary: Online) |
[Invited Talk]
Audio Source Separation Combining Wavelet Transform and Deep Neural Network Tomohiko Nakamura (Univ. Tokyo) EA2022-32 |
Audio source separation is a technique of separating an observed audio signal into individual source signals. The use of... [more] |
EA2022-32 p.25 |
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 |
Unsupervised Training of Sequential Neural Beamformer Using Blindly-separated and Non-separated Signals Kohei Saijo, Tetsuji Ogawa (Waseda Univ.) SP2022-25 |
We present an unsupervised training method of the sequential neural beamformer (Seq-NBF) using the separated signals fro... [more] |
SP2022-25 pp.110-115 |