独立性に基づくブラインド音源分離の発展と独立低ランク行列分析 History of independence-based blind source sep...Daichi Kitamura
東京大学 システム情報学専攻 談話会
2017年2月27日(月)15時~16時30分
北村大地, "独立性に基づくブラインド音源分離の発展と独立低ランク行列分析," 東京大学 システム情報学専攻 談話会, 2月27日, 2017年.
Daichi Kitamura, "History of independence-based blind source separation and independent low-rank matrix analysis," The University of Tokyo, Department of Information Physics and Computing, Seminar, 27th Feb., 2017.
音源分離における音響モデリング(Acoustic modeling in audio source separation)Daichi Kitamura
北村大地, "音源分離における音響モデリング," 日本音響学会 サマーセミナー 招待講演, September 11th, 2017.
Daichi Kitamura, "Acoustic modeling in audio source separation," The Acoustical Society of Japan, Summer Seminar Invited Talk, September 11th, 2017.
Effective Optimization Algorithms for Blind and Supervised Music Source Separation with Nonnegative Matrix Factorization
長倉研究奨励賞第三次審査,20分間の研究概要説明
内容は自身の学位論文の一部に相当
独立性に基づくブラインド音源分離の発展と独立低ランク行列分析 History of independence-based blind source sep...Daichi Kitamura
東京大学 システム情報学専攻 談話会
2017年2月27日(月)15時~16時30分
北村大地, "独立性に基づくブラインド音源分離の発展と独立低ランク行列分析," 東京大学 システム情報学専攻 談話会, 2月27日, 2017年.
Daichi Kitamura, "History of independence-based blind source separation and independent low-rank matrix analysis," The University of Tokyo, Department of Information Physics and Computing, Seminar, 27th Feb., 2017.
音源分離における音響モデリング(Acoustic modeling in audio source separation)Daichi Kitamura
北村大地, "音源分離における音響モデリング," 日本音響学会 サマーセミナー 招待講演, September 11th, 2017.
Daichi Kitamura, "Acoustic modeling in audio source separation," The Acoustical Society of Japan, Summer Seminar Invited Talk, September 11th, 2017.
Effective Optimization Algorithms for Blind and Supervised Music Source Separation with Nonnegative Matrix Factorization
長倉研究奨励賞第三次審査,20分間の研究概要説明
内容は自身の学位論文の一部に相当
ICASSP 2019音声&音響論文読み会(https://connpass.com/event/128527/)での発表資料です。
AASP (Audio and Acoustic Signal Processing) 分野の紹介と、ICASSP 2019での動向を紹介しています。#icassp2019jp
非負値行列分解の確率的生成モデルと多チャネル音源分離への応用 (Generative model in nonnegative matrix facto...Daichi Kitamura
北村大地, "非負値行列分解の確率的生成モデルと多チャネル音源分離への応用," 慶應義塾大学理工学部電子工学科湯川研究室 招待講演, Kanagawa, November, 2015.
Daichi Kitamura, "Generative model in nonnegative matrix factorization and its application to multichannel sound source separation," Keio University, Science and Technology, Department of Electronics and Electrical Engineeing, Yukawa Laboratory, Invited Talk, Kanagawa, November, 2015.
Presentation slide for AI seminar at Artificial Intelligence Research Center, The National Institute of Advanced Industrial Science and Technology, Japan.
URL (in Japanese): https://www.airc.aist.go.jp/seminar_detail/seminar_046.html
独立低ランク行列分析に基づく音源分離とその発展(Audio source separation based on independent low-rank...Daichi Kitamura
北村大地, "独立低ランク行列分析に基づく音源分離とその発展," IEICE信号処理研究会, 2021年8月24日.
Daichi Kitamura, "Audio source separation based on independent low-rank matrix analysis and its extensions," IEICE Technical Group on Signal Processing, Aug. 24th, 2021.
http://d-kitamura.net
日本音響学会2021春季研究発表会1-1-2
北村大地, 矢田部浩平, "スペクトログラム無矛盾性を用いた独立低ランク行列分析の実験的評価," 日本音響学会 2021年春季研究発表会講演論文集, 1-1-2, pp. 121–124, Tokyo, March 2021.
Daichi Kitamura and Kohei Yatabe, "Experimental evaluation of consistent independent low-rank matrix analysis," Proceedings of 2021 Spring Meeting of Acoustical Society of Japan, 1-1-2, pp. 121–124, Tokyo, March 2021 (in Japanese).
ICASSP 2019音声&音響論文読み会(https://connpass.com/event/128527/)での発表資料です。
AASP (Audio and Acoustic Signal Processing) 分野の紹介と、ICASSP 2019での動向を紹介しています。#icassp2019jp
非負値行列分解の確率的生成モデルと多チャネル音源分離への応用 (Generative model in nonnegative matrix facto...Daichi Kitamura
北村大地, "非負値行列分解の確率的生成モデルと多チャネル音源分離への応用," 慶應義塾大学理工学部電子工学科湯川研究室 招待講演, Kanagawa, November, 2015.
Daichi Kitamura, "Generative model in nonnegative matrix factorization and its application to multichannel sound source separation," Keio University, Science and Technology, Department of Electronics and Electrical Engineeing, Yukawa Laboratory, Invited Talk, Kanagawa, November, 2015.
Presentation slide for AI seminar at Artificial Intelligence Research Center, The National Institute of Advanced Industrial Science and Technology, Japan.
URL (in Japanese): https://www.airc.aist.go.jp/seminar_detail/seminar_046.html
独立低ランク行列分析に基づく音源分離とその発展(Audio source separation based on independent low-rank...Daichi Kitamura
北村大地, "独立低ランク行列分析に基づく音源分離とその発展," IEICE信号処理研究会, 2021年8月24日.
Daichi Kitamura, "Audio source separation based on independent low-rank matrix analysis and its extensions," IEICE Technical Group on Signal Processing, Aug. 24th, 2021.
http://d-kitamura.net
日本音響学会2021春季研究発表会1-1-2
北村大地, 矢田部浩平, "スペクトログラム無矛盾性を用いた独立低ランク行列分析の実験的評価," 日本音響学会 2021年春季研究発表会講演論文集, 1-1-2, pp. 121–124, Tokyo, March 2021.
Daichi Kitamura and Kohei Yatabe, "Experimental evaluation of consistent independent low-rank matrix analysis," Proceedings of 2021 Spring Meeting of Acoustical Society of Japan, 1-1-2, pp. 121–124, Tokyo, March 2021 (in Japanese).
Amplitude spectrogram prediction from mel-frequency cepstrum coefficients and...Kitamura Laboratory
Shoya Kawaguchi and Daichi Kitamura,
"Amplitude spectrogram prediction from mel-frequency cepstrum coefficients and loudness using deep neural networks,"
Proceedings of RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP 2023), pp. 225–228, Honolulu, USA, March 2023.
Heart rate estimation of car driver using radar sensors and blind source sepa...Kitamura Laboratory
Keito Murata, Daichi Kitamura, Ryo Saito, and Daichi Ueki,
"Heart rate estimation of car driver using radar sensors and blind source separation,"
Proceedings of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2022), pp. 1157–1164, Chiang Mai, Thailand, November 2022.
DNN-based frequency-domain permutation solver for multichannel audio source s...Kitamura Laboratory
Fumiya Hasuike, Daichi Kitamura, and Rui Watanabe,"DNN-based frequency-domain permutation solver for multichannel audio source separation," Proceedings of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2022), pp. 872–877, Chiang Mai, Thailand, November 2022.
Linear multichannel blind source separation based on time-frequency mask obta...Kitamura Laboratory
This document proposes a new method for linear multichannel blind source separation (BSS) based on time-frequency masks obtained from harmonic/percussive sound separation (HPSS). The proposed method applies HPSS independently to temporarily estimated sources to generate harmonic and percussive masks, then smooths the masks and uses them in time-frequency masking-based BSS. Experiments show the proposed method achieves higher source separation quality than single-channel HPSS and outperforms other multichannel BSS methods, demonstrating the effectiveness of integrating HPSS with multichannel BSS.
Prior distribution design for music bleeding-sound reduction based on nonnega...Kitamura Laboratory
Yusaku Mizobuchi, Daichi Kitamura, Tomohiko Nakamura, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo, "Prior distribution design for music bleeding-sound reduction based on nonnegative matrix factorization," Proceedings of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2021), pp. 651–658, Tokyo, Japan, December 2021.
Blind audio source separation based on time-frequency structure modelsKitamura Laboratory
Daichi Kitamura, "Blind audio source separation based on time-frequency structure models," Invited Overview Session in Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2021), Tokyo, Japan, December 2021.
1) The document proposes a new metric to predict the accuracy of source separation by independent component analysis (ICA) using finite sample data, as directly calculating independence from theoretical distributions is not possible with limited samples.
2) An experiment shows high correlation (0.97) between the proposed metric, which calculates the squared error between sample expectations of signal sources, and actual ICA separation accuracy, allowing prediction of ICA performance before application.
3) The metric improves on existing metrics like symmetric uncertainty coefficient that rely on approximating distributions from finite bins, and enables advance assessment of ICA feasibility for problems involving mixing of multiple signal sources observed through limited sensor data.
This document discusses independent low-rank matrix analysis (ILRMA) for blind source separation of multichannel audio signals. ILRMA introduces a low-rank source model in addition to maximizing statistical independence between sources, using an iterative optimization algorithm. ILRMA is one of the latest blind source separation techniques, building upon prior methods like independent component analysis (ICA), frequency-domain ICA, and independent vector analysis.
1) The document discusses a semi-supervised nonnegative matrix factorization method with a cosine penalty condition for audio source separation.
2) It proposes adding a cosine similarity penalty term to penalize similarity between basis matrices, to improve on existing penalized SNMF methods.
3) Experiments show the proposed method achieves higher source separation performance compared to existing methods, measured by average and median SDR values, but the optimal weight coefficient values are peaky.
次に,実験2における代表3曲の最終的なSDR改善量を示しています.縦軸が曲番号で,横軸はSDR改善量になっています.
有彩色のものが提案手法で,無彩色ものが従来法です.
Song no.2と14では,モノラルのHPSSの得手不得手に応じて提案手法のSDRが増幅されたような結果になっています.
Song no.9では,提案手法1ではモノラルのHPSSの得手不得手に従っていますが,提案手法2ではモノラルのHPSSのSDR改善量が低くても高いスコアを出しています.