• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Unification of Deep Learning and Generalized Mathematical Model for Independence-Based Audio Source Separation

Research Project

Project/Area Number 19K20306
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 61010:Perceptual information processing-related
Research InstitutionKagawa National College of Technology

Principal Investigator

Kitamura Daichi  香川高等専門学校, 電気情報工学科, 講師 (40804745)

Project Period (FY) 2019-04-01 – 2022-03-31
Project Status Completed (Fiscal Year 2021)
Budget Amount *help
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2021: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2020: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2019: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Keywords音源分離 / 統計的信号処理 / アレイ信号処理 / 深層学習 / 補聴器 / 独立成分分析 / 独立低ランク行列分析 / 生成モデル / 確率的信号処理 / 音響信号処理
Outline of Research at the Start

本研究では,音響信号を対象とした音源分離の数理的深化と高性能化を目的として,申請者が過去に提案した手法である「独立低ランク行列分析」を数理的に一般化した新しい音源分離フレームワークを確立する.これは「音源間の統計的独立性と各音源の構造に関する制約条件」という新たな考え方であり,いかに適切な音源構造制約を与えるかについて,数理的・データ的観点から発展させる.具体的には「一般化ガウス分布生成モデル」と「音源モデルplug-and-playな最適化法」の理論解析と確立,「深層学習に基づく音源教師あり手法」への発展,「ユーザの介入を組み合わせたインタラクティブ音源分離手法」の開発の3点を目標とする.

Outline of Final Research Achievements

This research project aims at extending an existing audio source separation techniques. Audio source separation is a technique that estimates specific audio sources from an observed mixture signal. It is expected that this technique can be applied to many applications using audio signals. In particular, this research project addresses mathematical deepening of the method called "independent low-rank matrix analysis (ILRMA)", which was proposed by the principal investigator. The framework established by this research project is a generalization of conventional techniques and improves performance of audio source separation. This framework provides a new investigation about the unification of "statistical independence between sources" and "structures of each source (source model)" and extends the source model from the viewpoint of both mathematical generalizations and data-driven approaches.

Academic Significance and Societal Importance of the Research Achievements

本成果により,従来の音源分離手法よりもさらに高性能なアルゴリズムを複数提案することができた.具体的には,(1)「一般化ガウス分布生成モデル」と「音源モデルplug-and-playな最適化法」の理論解析と確立,(2)「深層学習に基づく音源教師あり手法」への発展,(3)「ユーザの介入を組み合わせたインタラクティブ音源分離手法」の3点について,新しい理論として構築できた.(1)については,純粋な音源分離性能の向上に寄与し,(2)については,近年充実しつつある音響信号の学習データの有効活用へとつなげることが可能である.さらに,(3)によって,人と機械が協働する音源分離アルゴリズムが実現された.

Report

(4 results)
  • 2021 Annual Research Report   Final Research Report ( PDF )
  • 2020 Research-status Report
  • 2019 Research-status Report
  • Research Products

    (86 results)

All 2022 2021 2020 2019 Other

All Journal Article (10 results) (of which Int'l Joint Research: 2 results,  Peer Reviewed: 9 results,  Open Access: 10 results) Presentation (72 results) (of which Int'l Joint Research: 22 results,  Invited: 1 results) Remarks (2 results) Patent(Industrial Property Rights) (2 results)

  • [Journal Article] Supervised audio source separation based on nonnegative matrix factorization with cosine similarity penalty2022

    • Author(s)
      Yuta Iwase and Daichi Kitamura
    • Journal Title

      IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

      Volume: E105-A (6)

    • NAID

      130008126154

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Interactive speech source separation based on independent low-rank matrix analysis2021

    • Author(s)
      Oshima Fuga、Nakano Masaki、Kitamura Daichi
    • Journal Title

      Acoustical Science and Technology

      Volume: 42 Issue: 4 Pages: 222-225

    • DOI

      10.1250/ast.42.222

    • NAID

      130008060585

    • ISSN
      0369-4232, 1346-3969, 1347-5177
    • Year and Date
      2021-07-01
    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Noise Robust Acoustic Anomaly Detection System with Nonnegative Matrix Factorization Based on Generalized Gaussian Distribution2021

    • Author(s)
      AIBA Akihito、YOSHIDA Minoru、KITAMURA Daichi、TAKAMICHI Shinnosuke、SARUWATARI Hiroshi
    • Journal Title

      IEICE Transactions on Information and Systems

      Volume: E104.D Issue: 3 Pages: 441-449

    • DOI

      10.1587/transinf.2020EDK0002

    • NAID

      130007993183

    • ISSN
      0916-8532, 1745-1361
    • Year and Date
      2021-03-01
    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Determined BSS Based on Time-Frequency Masking and Its Application to Harmonic Vector Analysis2021

    • Author(s)
      Yatabe Kohei、Kitamura Daichi
    • Journal Title

      IEEE/ACM Transactions on Audio, Speech, and Language Processing

      Volume: 29 Pages: 1609-1625

    • DOI

      10.1109/taslp.2021.3073863

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Joint-diagonalizability-constrained multichannel nonnegative matrix factorization based on time-variant multivariate complex sub-Gaussian distribution2021

    • Author(s)
      Kamo Keigo、Mitsui Yoshiki、Kubo Yuki、Takamune Norihiro、Kitamura Daichi、Saruwatari Hiroshi、Takahashi Yu、Kondo Kazunobu
    • Journal Title

      Signal Processing

      Volume: 188 Pages: 108183-108183

    • DOI

      10.1016/j.sigpro.2021.108183

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Consistent independent low-rank matrix analysis for determined blind source separation2020

    • Author(s)
      Kitamura Daichi、Yatabe Kohei
    • Journal Title

      EURASIP Journal on Advances in Signal Processing

      Volume: 2020 Issue: 1 Pages: 1-35

    • DOI

      10.1186/s13634-020-00704-4

    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Independent Low-Rank Matrix Analysis Based on Time-Variant Sub-Gaussian Source Model for Determined Blind Source Separation2020

    • Author(s)
      Mogami Shinichi、Takamune Norihiro、Kitamura Daichi、Saruwatari Hiroshi、Takahashi Yu、Kondo Kazunobu、Ono Nobutaka
    • Journal Title

      IEEE/ACM Transactions on Audio, Speech, and Language Processing

      Volume: 28 Pages: 503-518

    • DOI

      10.1109/taslp.2019.2959257

    • Related Report
      2019 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Multichannel Non-Negative Matrix Factorization Using Banded Spatial Covariance Matrices in Wavenumber Domain2020

    • Author(s)
      Mitsufuji Yuki、Uhlich Stefan、Takamune Norihiro、Kitamura Daichi、Koyama Shoichi、Saruwatari Hiroshi
    • Journal Title

      IEEE/ACM Transactions on Audio, Speech, and Language Processing

      Volume: 28 Pages: 49-60

    • DOI

      10.1109/taslp.2019.2948770

    • Related Report
      2019 Research-status Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Nonnegative matrix factorization based on complex generative model2019

    • Author(s)
      Kitamura Daichi
    • Journal Title

      Acoustical Science and Technology

      Volume: 40 Issue: 3 Pages: 155-161

    • DOI

      10.1250/ast.40.155

    • NAID

      130007641587

    • ISSN
      0369-4232, 1346-3969, 1347-5177
    • Year and Date
      2019-05-01
    • Related Report
      2019 Research-status Report
    • Open Access
  • [Journal Article] Independent Deeply Learned Matrix Analysis for Determined Audio Source Separation2019

    • Author(s)
      Makishima Naoki、Mogami Shinichi、Takamune Norihiro、Kitamura Daichi、Sumino Hayato、Takamichi Shinnosuke、Saruwatari Hiroshi、Ono Nobutaka
    • Journal Title

      IEEE/ACM Transactions on Audio, Speech, and Language Processing

      Volume: 27 Issue: 10 Pages: 1601-1615

    • DOI

      10.1109/taslp.2019.2925450

    • Related Report
      2019 Research-status Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Presentation] 混合Differentiable DSPモデルによる混合楽器音からの合成パラメータ抽出の実験的評価2022

    • Author(s)
      川村真也, 中村友彦, 北村大地, 猿渡洋, 高橋祐, 近藤多伸
    • Organizer
      日本音響学会 2022年春季研究発表会
    • Related Report
      2021 Annual Research Report
  • [Presentation] 解像度の異なる複数の時間周波数表現を用いた独立低ランク行列分析2022

    • Author(s)
      細谷泰稚, 北村大地, 矢田部浩平
    • Organizer
      日本音響学会 2022年春季研究発表会
    • Related Report
      2021 Annual Research Report
  • [Presentation] Deficient basis estimation of noise spatial covariance matrix for rank-constrained spatial covariance matrix estimation method in blind speech extraction2021

    • Author(s)
      Yuto Kondo, Yuki Kubo, Norihiro Takamune, Daichi Kitamura, and Hiroshi Saruwatari
    • Organizer
      IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2021)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Linear multichannel blind source separation based on time-frequency mask obtained by harmonic/percussive sound separation2021

    • Author(s)
      Soichiro Oyabu, Daichi Kitamura, and Kohei Yatabe
    • Organizer
      IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2021)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Independent deeply learned tensor analysis for determined audio source separation2021

    • Author(s)
      Naoki Narisawa, Rintaro Ikeshita, Norihiro Takamune, Daichi Kitamura, Tomohiko Nakamura, Hiroshi Saruwatari, and Tomohiro Nakatani
    • Organizer
      European Signal Processing Conference (EUSIPCO 2021)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Empirical Bayesian independent deeply learned matrix analysis for multichannel audio source separation2021

    • Author(s)
      Takuya Hasumi, Tomohiko Nakamura, Norihiro Takamune, Hiroshi Saruwatari, Daichi Kitamura, Yu Takahashi, and Kazunobu Kondo
    • Organizer
      European Signal Processing Conference (EUSIPCO 2021)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Speech enhancement by noise self-supervised rank-constrained spatial covariance matrix estimation via independent deeply learned matrix analysis2021

    • Author(s)
      Sota Misawa, Norihiro Takamune, Tomohiko Nakamura, Daichi Kitamura, Hiroshi Saruwatari, Masakazu Une, and Shoji Makino
    • Organizer
      Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2021)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Multichannel audio source separation with independent deeply learned matrix analysis using product of source models2021

    • Author(s)
      Takuya Hasumi, Tomohiko Nakamura, Norihiro Takamune, Hiroshi Saruwatari, Daichi Kitamura, Yu Takahashi, and Kazunobu Kondo
    • Organizer
      Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2021)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Prior distribution design for music bleeding-sound reduction based on nonnegative matrix factorization2021

    • Author(s)
      Yusaku Mizobuchi, Daichi Kitamura, Tomohiko Nakamura, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo
    • Organizer
      Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2021)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 非負値行列因子分解を導入したproduct of experts型音源モデルに基づく独立深層学習行列分析による多チャネル音源分離2021

    • Author(s)
      蓮実拓也, 中村友彦, 高宗典玄, 猿渡洋, 北村大地, 高橋祐, 近藤多伸
    • Organizer
      情報処理学会 第131回音楽情報科学研究会
    • Related Report
      2021 Annual Research Report
  • [Presentation] 基底共有型非負値行列因子分解を用いた楽器音の音色変換2021

    • Author(s)
      北村大地, 香西海斗
    • Organizer
      情報処理学会 第131回音楽情報科学研究会
    • Related Report
      2021 Annual Research Report
  • [Presentation] 独立低ランク行列分析に基づく音源分離とその発展2021

    • Author(s)
      北村大地
    • Organizer
      電子情報通信学会 信号処理研究会
    • Related Report
      2021 Annual Research Report
    • Invited
  • [Presentation] ヘビーテイル生成モデルに基づく独立深層学習テンソル分析2021

    • Author(s)
      成澤直輝, 池下林太郎, 高宗典玄, 北村大地, 中村友彦, 猿渡洋, 中谷智広
    • Organizer
      日本音響学会 2021年秋季研究発表会
    • Related Report
      2021 Annual Research Report
  • [Presentation] コサイン類似度罰則条件付き非負値行列因子分解に基づく音源分離の実験的評価2021

    • Author(s)
      岩瀬佑太, 北村大地
    • Organizer
      日本音響学会 2021年秋季研究発表会
    • Related Report
      2021 Annual Research Report
  • [Presentation] 独立深層学習行列分析を用いたランク制約付き空間共分散行列推定による音声強調2021

    • Author(s)
      三澤颯大, 中村友彦, 高宗典玄, 北村大地, 猿渡洋
    • Organizer
      日本音響学会 2021年秋季研究発表会
    • Related Report
      2021 Annual Research Report
  • [Presentation] Product of Priors型確率分布を導入した音源モデルに基づく独立深層学習行列分析による多チャネル音源分離2021

    • Author(s)
      蓮実拓也, 中村友彦, 高宗典玄, 猿渡洋, 北村大地, 高橋祐, 近藤多伸
    • Organizer
      日本音響学会 2021年秋季研究発表会
    • Related Report
      2021 Annual Research Report
  • [Presentation] 深層学習に基づく間引きインジケータ付き周波数帯域補間手法による音源分離処理の高速化2021

    • Author(s)
      渡辺瑠伊, 北村大地, 中村友彦, 猿渡洋, 高橋祐, 近藤多伸
    • Organizer
      日本音響学会 2021年秋季研究発表会
    • Related Report
      2021 Annual Research Report
  • [Presentation] 多変量一般化Gauss分布に基づくランク制約付き空間共分散行列推定法における雑音欠落ランク空間基底推定2021

    • Author(s)
      近藤祐斗, 久保優騎, 高宗典玄, 北村大地, 猿渡洋
    • Organizer
      日本音響学会 2021年秋季研究発表会
    • Related Report
      2021 Annual Research Report
  • [Presentation] 楽譜情報を援用した音楽音響信号に対する混合Differentiable DSPモデルの合成パラメータ推定2021

    • Author(s)
      川村真也, 中村友彦, 北村大地, 猿渡洋, 高橋祐, 近藤多伸
    • Organizer
      情報処理学会 第132回音楽情報科学研究会(夏のシンポジウム)
    • Related Report
      2021 Annual Research Report
  • [Presentation] 非負値行列因子分解を用いた被り音の抑圧2021

    • Author(s)
      溝渕悠朔, 北村大地, 中村友彦, 猿渡洋, 高橋祐, 近藤多伸
    • Organizer
      情報処理学会 第132回音楽情報科学研究会(夏のシンポジウム)
    • Related Report
      2021 Annual Research Report
  • [Presentation] コサイン類似度罰則条件付き非負値行列因子分解に基づく音源分離の仮説検定2021

    • Author(s)
      岩瀬佑太, 北村大地
    • Organizer
      第24回 日本音響学会関西支部 若手研究者交流研究発表会
    • Related Report
      2021 Annual Research Report
  • [Presentation] 深層学習に基づく周波数帯域予測による高速音源分離法の実験的評価2021

    • Author(s)
      渡辺瑠伊, 北村大地, 中村友彦, 猿渡洋, 高橋祐, 近藤多伸
    • Organizer
      第24回 日本音響学会関西支部 若手研究者交流研究発表会
    • Related Report
      2021 Annual Research Report
  • [Presentation] Joint-Diagonalizability-Constrained Multichannel Nonnegative Matrix Factorization Based on Multivariate Complex Sub-Gaussian Distribution2021

    • Author(s)
      Keigo Kamo, Yuki Kubo, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi and Kazunobu Kondo
    • Organizer
      European Signal Processing Conference (EUSIPCO 2020)
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] DNN-Based Frequency Component Prediction for Frequency-Domain Audio Source Separation2021

    • Author(s)
      Rui Watanabe, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo
    • Organizer
      European Signal Processing Conference (EUSIPCO 2020)
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] 多変量複素Sub-Gauss分布に基づく同時対角化制約付き多チャネル非負値行列因子分解におけるmajorization-equalizationアルゴリズムを用いた更新則2021

    • Author(s)
      加茂佳吾,久保優騎,高宗典玄,北村大地,猿渡洋,高橋祐,近藤多伸
    • Organizer
      日本音響学会 2021年春季研究発表会講演論文集
    • Related Report
      2020 Research-status Report
  • [Presentation] ランク制約付き空間共分散行列推定法における補助関数法に基づく雑音欠落ランク空間基底に対する新しい更新則2021

    • Author(s)
      近藤祐斗, 久保優騎, 高宗典玄, 北村大地, 猿渡洋
    • Organizer
      日本音響学会2021春季研究発表会
    • Related Report
      2020 Research-status Report
  • [Presentation] スタガードモデル化三重対角型共分散行列を用いた独立半正定値テンソル分析によるブラインド音源分離2021

    • Author(s)
      近藤 樹、高宗 典玄、北村 大地、猿渡 洋、池下 林太郎、中谷 智広
    • Organizer
      日本音響学会2021春季研究発表会
    • Related Report
      2020 Research-status Report
  • [Presentation] 経験ベイズ独立深層学習行列分析による多チャネル音源分離2021

    • Author(s)
      蓮実拓也,中村友彦,高宗典玄,猿渡洋,北村大地,高橋祐,近藤多伸
    • Organizer
      日本音響学会2021春季研究発表会
    • Related Report
      2020 Research-status Report
  • [Presentation] 独立深層学習テンソル分析に基づく多チャネル音源分離2021

    • Author(s)
      成澤直輝,池下林太郎,高宗典玄,北村大地,中村友彦,猿渡洋,中谷智広
    • Organizer
      日本音響学会2021春季研究発表会
    • Related Report
      2020 Research-status Report
  • [Presentation] 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2021

    • Author(s)
      北村大地,矢田部浩平
    • Organizer
      日本音響学会2021年春季研究発表会
    • Related Report
      2020 Research-status Report
  • [Presentation] 深層学習に基づく周波数帯域補間手法による音源分離処理の高速化2021

    • Author(s)
      渡辺瑠伊,北村大地,猿渡洋,高橋祐,近藤多伸
    • Organizer
      日本音響学会2021年春季研究発表会
    • Related Report
      2020 Research-status Report
  • [Presentation] 基底共有型非負値行列因子分解に基づく楽器音の共通・固有成分の分析2021

    • Author(s)
      香西海斗, 北村大地
    • Organizer
      日本音響学会2021年春季研究発表会
    • Related Report
      2020 Research-status Report
  • [Presentation] メディアン型HPSSを用いた時間周波数マスクに基づくブラインド音源分離2021

    • Author(s)
      大藪宗一郎,北村大地,矢田部浩平
    • Organizer
      日本音響学会2021年春季研究発表会
    • Related Report
      2020 Research-status Report
  • [Presentation] Joint-Diagonalizability-Constrained Multichannel Nonnegative Matrix Factorization Based on Multivariate Complex Student's t-distribution2020

    • Author(s)
      Keigo Kamo, Yuki Kubo, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi and Kazunobu Kondo
    • Organizer
      Asia-Pacific Signal and Information Processing Association (APSIPA 2020)
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] "DNN-Based Permutation Solver for Frequency-Domain Independent Component Analysis in Two-Source Mixture Case"2020

    • Author(s)
      Shuhei Yamaji and Daichi Kitamura
    • Organizer
      Asia-Pacific Signal and Information Processing Association (APSIPA 2020)
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] Convergence-Guaranteed Independent Positive Semidefinite Tensor Analysis Based on Student's T Distribution2020

    • Author(s)
      Tatsuki Kondo, Kanta Fukushige, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Rintaro Ikeshita, Tomohiro Nakatani
    • Organizer
      The 45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP2020)
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] Regularized Fast Multichannel Nonnegative Matrix Factorization with ILRMA-based Prior Distribution of Joint-Diagonalization Process2020

    • Author(s)
      Keigo Kamo, Yuki Kubo, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi and Kazunobu Kondo
    • Organizer
      The 45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP2020)
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] 多変量複素Sub-Gauss分布に基づく同時対角化制約付き多チャネル非負値行列因子分解の様々な残響条件下における実験的評価2020

    • Author(s)
      加茂佳吾,久保優騎,高宗典玄,北村大地,猿渡洋,高橋祐,近藤多伸
    • Organizer
      日本音響学会 2020年秋季研究発表会講演論文集
    • Related Report
      2020 Research-status Report
  • [Presentation] 音源分離のための周波数間相関を考慮した多変量複素Gauss分布に基づく深層学習による分散共分散行列推定の検討2020

    • Author(s)
      成澤直輝,高宗典玄,北村大地,中村友彦,猿渡洋
    • Organizer
      日本音響学会2020秋季研究発表会
    • Related Report
      2020 Research-status Report
  • [Presentation] ブラインド音声抽出のためのランク制約付き空間共分散行列推定法における雑音欠落ランク空間基底推定2020

    • Author(s)
      近藤祐斗, 久保優騎, 高宗典玄, 北村大地, 猿渡洋
    • Organizer
      日本音響学会2020秋季研究発表会
    • Related Report
      2020 Research-status Report
  • [Presentation] ユーザーからの補助情報を用いる独立低ランク行列分析2020

    • Author(s)
      大島風雅,中野将生,北村大地
    • Organizer
      日本音響学会2020秋季研究発表会
    • Related Report
      2020 Research-status Report
  • [Presentation] 深層学習に基づく音響帯域拡張による音源分離処理の高速化2020

    • Author(s)
      渡辺瑠伊,北村大地,猿渡洋,高橋祐,近藤多伸
    • Organizer
      日本音響学会2020秋季研究発表会
    • Related Report
      2020 Research-status Report
  • [Presentation] 局所時間周波数構造に基づく深層パーミュテーション解決法の実験的評価2020

    • Author(s)
      山地修平,北村大地
    • Organizer
      日本音響学会2020秋季研究発表会
    • Related Report
      2020 Research-status Report
  • [Presentation] 調波打撃音分離の排他的マスキングに基づくブラインド音源分離2020

    • Author(s)
      大藪宗一郎,北村大地,矢田部浩平
    • Organizer
      日本音響学会2020秋季研究発表会
    • Related Report
      2020 Research-status Report
  • [Presentation] 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2020

    • Author(s)
      豊島直, 北村大地, 矢田部浩平
    • Organizer
      日本音響学会2020秋季研究発表会
    • Related Report
      2020 Research-status Report
  • [Presentation] Multichannel Hearing-aid System Based on Basis-Shared Semi-Supervised Independent Low-Rank Matrix Analysis2020

    • Author(s)
      Masakazu Une, Yuki Kubo, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, and Shoji Makino
    • Organizer
      Forum Acusticum 2020
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] Regularized fast multichannel nonnegative matrix factorization with ILRMA-based prior distribution of joint-diagonalization process2020

    • Author(s)
      Keigo Kamo, Yuki Kubo, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo
    • Organizer
      IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2020)
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] Convergence-guaranteed independent positive semidefinite tensor analysis based on Student's t distribution2020

    • Author(s)
      Tatsuki Kondo, Kanta Fukushige, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Rintaro Ikeshita, and Tomohiro Nakatani
    • Organizer
      IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2020)
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] Multichannel hearing-aid system based on basis-shared semi-supervised independent low-rank matrix analysis2020

    • Author(s)
      Masakazu Une, Yuki Kubo, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, and Shoji Makino
    • Organizer
      Forum Acusticum
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] コサイン類似度罰則条件付き半教師あり非負値行列因子分解2020

    • Author(s)
      岩瀬佑太, 北村大地
    • Organizer
      日本音響学会 2020年春季研究発表会
    • Related Report
      2019 Research-status Report
  • [Presentation] 調波打撃音分離の時間周波数マスクを用いた線形ブラインド音源分離2020

    • Author(s)
      大藪宗一郎, 北村大地, 矢田部浩平
    • Organizer
      日本音響学会 2020年春季研究発表会
    • Related Report
      2019 Research-status Report
  • [Presentation] ユーザーからの補助情報を用いるインタラクティブ音源分離システム2020

    • Author(s)
      中野将生, 北村大地
    • Organizer
      日本音響学会 2020年春季研究発表会
    • Related Report
      2019 Research-status Report
  • [Presentation] 音源分離のための深層学習に基づく音響帯域拡張2020

    • Author(s)
      渡辺瑠伊, 北村大地
    • Organizer
      日本音響学会 2020年春季研究発表会
    • Related Report
      2019 Research-status Report
  • [Presentation] 局所時間周波数構造に基づく深層パーミュテーション解決法2020

    • Author(s)
      山地修平, 北村大地
    • Organizer
      日本音響学会 2020年春季研究発表会
    • Related Report
      2019 Research-status Report
  • [Presentation] 独立深層学習行列分析におけるマイクロホン毎及び音源毎の座標降下法 に基づく分離行列更新法の周波数別自動選択法2020

    • Author(s)
      牧島直輝, 高宗典玄, 北村大地, 猿渡洋, 高橋祐, 近藤多伸
    • Organizer
      日本音響学会 2020年春季研究発表会
    • Related Report
      2019 Research-status Report
  • [Presentation] ランク制約付き空間共分散行列推定法に基づく拡散性雑音存在下でのブラインド複数方向性音源分離2020

    • Author(s)
      久保優騎, 高宗典玄, 北村大地, 猿渡洋
    • Organizer
      日本音響学会 2020年春季研究発表会
    • Related Report
      2019 Research-status Report
  • [Presentation] 三重対角型周波数共分散行列を用いた独立半正定値テンソル分析によるブラインド音源分離2020

    • Author(s)
      近藤樹, 高宗典玄, 北村大地, 猿渡洋, 池下林太郎, 中谷智広
    • Organizer
      日本音響学会 2020年春季研究発表会
    • Related Report
      2019 Research-status Report
  • [Presentation] 同時対角化行列の事前分布を用いた高速多チャネル非負値行列因子分解によるブラインド音源分離2020

    • Author(s)
      加茂佳吾, 久保優騎, 高宗典玄, 北村大地, 猿渡洋, 高橋祐, 近藤多伸
    • Organizer
      日本音響学会 2020年春季研究発表会
    • Related Report
      2019 Research-status Report
  • [Presentation] 基底共有型半教師あり独立低ランク行列分析に基づく多チャネル補聴器システム2020

    • Author(s)
      宇根昌和, 久保優騎, 高宗典玄, 北村大地, 猿渡洋, 牧野 昭二
    • Organizer
      日本音響学会 2020年春季研究発表会
    • Related Report
      2019 Research-status Report
  • [Presentation] HVA:調波ベクトル分析2020

    • Author(s)
      矢田部浩平, 北村大地
    • Organizer
      日本音響学会 2020年春季研究発表会
    • Related Report
      2019 Research-status Report
  • [Presentation] 一般化Gauss分布に基づく同時対角化制約付き多チャネルNMFを用いたブラインド音源分離2020

    • Author(s)
      加茂佳吾, 久保優騎, 高宗典玄, 北村大地, 猿渡洋, 高橋祐, 近藤多伸
    • Organizer
      IEICE Technical Report
    • Related Report
      2019 Research-status Report
  • [Presentation] ブラインド音声抽出のための多変量複素一般化Gauss分布に基づくランク制約付き空間共分散行列推定法及びその高速化2020

    • Author(s)
      久保優騎, 高宗典玄, 北村大地, 猿渡洋
    • Organizer
      IEICE Technical Report
    • Related Report
      2019 Research-status Report
  • [Presentation] Robust demixing filter update algorithm based on microphone-wise coordinate descent for independent deeply learned matrix analysis2019

    • Author(s)
      Naoki Makishima, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo
    • Organizer
      Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2019)
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] Acceleration of rank-constrained spatial covariance matrix estimation for blind speech extraction2019

    • Author(s)
      Yuki Kubo, Norihiro Takamune, Daichi Kitamura, and Hiroshi Saruwatari
    • Organizer
      Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2019)
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] Evaluation of multichannel hearing aid system using rank-constrained spatial covariance matrix estimation2019

    • Author(s)
      Masakazu Une, Yuki Kubo, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, and Shoji Makino
    • Organizer
      Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2019)
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] Column-wise update algorithm for independent deeply learned matrix analysis2019

    • Author(s)
      Naoki Makishima, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo
    • Organizer
      International Congress on Acoustics (ICA 2019)
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] Efficient full-rank spatial covariance estimation using independent low-rank matrix analysis for blind source separation2019

    • Author(s)
      Yuki Kubo, Norihiro Takamune, Daichi Kitamura, and Hiroshi Saruwatari
    • Organizer
      European Signal Processing Conference (EUSIPCO 2019)
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] 多変量複素Student’s t分布に基づくFastMNMF を用いたブラインド音源分離2019

    • Author(s)
      加茂佳吾, 久保優騎, 高宗典玄, 北村大地, 猿渡洋, 高橋祐, 近藤多伸
    • Organizer
      IEICE Technical Report
    • Related Report
      2019 Research-status Report
  • [Presentation] 独立深層学習行列分析におけるマイクロホン毎の座標降下法に基づく分離行列更新2019

    • Author(s)
      牧島直輝, 高宗典玄, 北村大地, 猿渡洋, 高橋祐, 近藤多伸
    • Organizer
      日本音響学会 2019年秋季研究発表会
    • Related Report
      2019 Research-status Report
  • [Presentation] 多変量複素Student's t分布に基づく独立半正定値テンソル分析によるブラインド音源分離2019

    • Author(s)
      近藤樹, 高宗典玄, 北村大地, 猿渡洋, 池下林太郎, 中谷智広
    • Organizer
      日本音響学会 2019年秋季研究発表会
    • Related Report
      2019 Research-status Report
  • [Presentation] ランク制約付き空間共分散モデル推定法の逆行列展開による高速化2019

    • Author(s)
      久保優騎, 高宗典玄, 北村大地, 猿渡洋
    • Organizer
      日本音響学会 2019年秋季研究発表会
    • Related Report
      2019 Research-status Report
  • [Presentation] ランク制約付き空間共分散モデル推定を用いた多チャネル補聴器システムの評価2019

    • Author(s)
      宇根昌和, 久保優騎, 高宗典玄, 北村大地, 猿渡洋, 牧野昭二
    • Organizer
      日本音響学会 2019年秋季研究発表会
    • Related Report
      2019 Research-status Report
  • [Remarks] 調波ベクトル分析(HVA)に基づく多チャネルブラインド音源分離

    • URL

      http://d-kitamura.net/demo-HVA.html

    • Related Report
      2020 Research-status Report
  • [Remarks] Blind audio source separation based on HVA

    • URL

      http://d-kitamura.net/demo-HVA_en.html

    • Related Report
      2020 Research-status Report
  • [Patent(Industrial Property Rights)] 信号処理装置2020

    • Inventor(s)
      北村大地,渡辺瑠伊
    • Industrial Property Rights Holder
      北村大地,渡辺瑠伊
    • Industrial Property Rights Type
      特許
    • Industrial Property Number
      2020-033347
    • Filing Date
      2020
    • Related Report
      2019 Research-status Report
  • [Patent(Industrial Property Rights)] ランク制約付き空間共分散行列の高速推定法2019

    • Inventor(s)
      猿渡洋,久保優騎,高宗典玄,北村だいいt
    • Industrial Property Rights Holder
      猿渡洋,久保優騎,高宗典玄,北村だいいt
    • Industrial Property Rights Type
      特許
    • Industrial Property Number
      2019-220584
    • Filing Date
      2019
    • Related Report
      2019 Research-status Report

URL: 

Published: 2019-04-18   Modified: 2023-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi