Acoustic scene analysis based on time-space acoustic signal modeling and machine learning

• Project/Area Number: 26730100
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Perceptual information processing
• Research Institution: NTT Communication Science Laboratories
• Principal Investigator: Kameoka Hirokazu 日本電信電話株式会社NTTコミュニケーション科学基礎研究所, メディア情報研究部, 主任研究員 (20466402)
• Project Period (FY): 2014-04-01 – 2017-03-31
• Project Status: Completed (Fiscal Year 2016)
• Budget Amount: ¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000); Fiscal Year 2016: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000); Fiscal Year 2015: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000); Fiscal Year 2014: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
• Keywords: 音響情景分析 / 深層学習 / 多重音解析 / 音響イベント検出 / 音源分離 / 到来方向推定 / 残響除去 / 高速学習アルゴリズム

Outline of Final Research Achievements

Humans are able to recognize what kinds of sounds are present and which direction they are emanating from by using their ears. The aim of this work has been to develop a method that let machines imitate this kind of human auditory function through physical modeling of the generative process of acoustic waveforms and probabilistic modeling of human hearing perception.

Research Products

• [Journal Article] Non-negative matrix factorization with basis clustering using cepstral distance regularization (2017)
  • Author(s): Hirokazu Kameoka, Takuya Higuchi, Mikihiro Tanaka, Li Li
  • Journal Title: IEEE/ACM Transactions on Audio, Speech, and Language Processing Volume: 印刷中
  • Peer Reviewed / Acknowledgement Compliant
• [Journal Article] Generative modeling of voice fundamental frequency contours (2015)
  • Author(s): Hirokazu Kameoka, Kota Yoshizato, Tatsuma Ishihara, Kento Kadowaki, Yasunori Ohishi, and Kunio Kashino
  • Journal Title: IEEE/ACM Transactions on Audio, Speech and Language Processing Volume: 23 Issue: 6 Pages: 1042-1053
  • DOI: 10.1109/taslp.2015.2418576
  • Peer Reviewed / Acknowledgement Compliant
• [Journal Article] Multichannel signal separation combining directional clustering and nonnegative matrix factorization with spectrogram restoration (2015)
  • Author(s): Daichi Kitamura, Hiroshi Saruwatari, Hirokazu Kameoka, Yu Takahashi, Kazunobu Kondo, Satoshi Nakamura
  • Journal Title: IEEE/ACM Transactions on Audio, Speech and Language Processing Volume: 23 Issue: 4 Pages: 654-669
  • DOI: 10.1109/taslp.2015.2401425
  • Peer Reviewed
• [Journal Article] Harmonic/Percussive sound separation based on anisotropic smoothness of spectrograms (2015)
  • Author(s): Hideyuki Tachibana, Hirokazu Kameoka, Nobutaka Ono, Shigeki Sagayama
  • Journal Title: IEEE/ACM Transactions on Audio, Speech and Language Processing Volume: 22 Issue: 12 Pages: 2059-2073
  • DOI: 10.1109/taslp.2014.2351131
  • Peer Reviewed
• [Journal Article] 非負値行列因子分解とその音響信号処理への応用 (2014)
  • Author(s): 亀岡弘和
  • Journal Title: 日本統計学会和文誌 Volume: 44 Pages: 383-407
  • NAID: 110009930636
  • Peer Reviewed
• [Presentation] Generative adversarial network-based postfilter for STFT spectrograms (2017)
  • Author(s): Takuhiro Kaneko, Shinji Takaki, Hirokazu Kameoka, Junichi Yamagishi
  • Organizer: 18th Annual Conference of International Speech Communication Association (Interspeech 2017)
  • Place of Presentation: Stockholm, Sweden
  • Year and Date: 2017-08-20
  • Int'l Joint Research
• [Presentation] Sequence-to-sequence voice conversion with similarity metric learned using generative adversarial networks (2017)
  • Author(s): Takuhiro Kaneko, Hirokazu Kameoka, Kaoru Hiramatsu, Kunio Kashino
  • Organizer: 18th Annual Conference of International Speech Communication Association (Interspeech 2017)
  • Place of Presentation: Stockholm, Sweden
  • Year and Date: 2017-08-20
  • Int'l Joint Research
• [Presentation] Physically constrained statistical F0 prediction for electrolaryngeal speech enhancement (2017)
  • Author(s): Kou Tanaka, Hirokazu Kameoka, Tomoki Toda, Satoshi Nakamura
  • Organizer: 18th Annual Conference of International Speech Communication Association (Interspeech 2017)
  • Place of Presentation: Stockholm, Sweden
  • Year and Date: 2017-08-20
  • Int'l Joint Research
• [Presentation] 音響分野におけるブラインド適応信号処理の展開 (2017)
  • Author(s): 亀岡弘和, 小野順貴, 猿渡洋
  • Organizer: 2017年電子情報通信学会総合大会
  • Place of Presentation: 愛知県名古屋市
  • Year and Date: 2017-03-22
  • Invited
• [Presentation] A majorization-minimization algorithm with projected gradient updates for time-domain spectrogram factorization (2017)
  • Author(s): Hideaki Kagami, Hirokazu Kameoka, Masahiro Yukawa
  • Organizer: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2017)
  • Place of Presentation: New Orleans, USA
  • Year and Date: 2017-03-05
  • Int'l Joint Research
• [Presentation] Complex NMF with the generalized Kullback-Leibler divergence (2017)
  • Author(s): Hirokazu Kameoka, Hideaki Kagami, Masahiro Yukawa
  • Organizer: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2017)
  • Place of Presentation: New Orleans, USA
  • Year and Date: 2017-03-05
  • Int'l Joint Research
• [Presentation] Discriminative non-negative matrix factorization with majorization-minimization (2017)
  • Author(s): Li Li, Hirokazu Kameoka, Shoji Makino
  • Organizer: The 5th Joint Workshop on Hands-free Speech Communi- cation and Microphone Arrays (HSCMA2017)
  • Place of Presentation: San Francisco, California, USA
  • Year and Date: 2017-03-01
  • Int'l Joint Research
• [Presentation] Complex non-negative matrix factorization: Phase-aware sparse representation of audio spectrograms (2016)
  • Author(s): Hirokazu Kameoka, Hideaki Kagami
  • Organizer: 5th Joint Meeting of the Acoustical Society of America and the Acoustical Society of Japan
  • Place of Presentation: Honolulu, Hawaii, USA
  • Year and Date: 2016-11-28
  • Int'l Joint Research / Invited
• [Presentation] Semi-supervised joint enhancement of spectral and cepstral sequences of noisy speech (2016)
  • Author(s): Li Li, Hirokazu Kameoka, Takuya Higuchi, Hiroshi Saruwatari
  • Organizer: The 17th Annual Conference of the International Speech Communication Association (Interspeech 2016)
  • Place of Presentation: San Francisco, California, USA
  • Year and Date: 2016-09-08
  • Int'l Joint Research
• [Presentation] Reverberation-robust underdetermined source separation with non-negative tensor double deconvolution (2016)
  • Author(s): Naoki Murata, Hirokazu Kameoka, Keisuke Kinoshita, Shoko Araki, Tomohiro Nakatani, Shoichi Koyama, Hiroshi Saruwatari
  • Organizer: 2016 24th European Signal Processing Conference (EUSIPCO 2016)
  • Place of Presentation: Budapest, Hungary
  • Year and Date: 2016-08-29
  • Int'l Joint Research
• [Presentation] 統計的音響信号処理 (2016)
  • Author(s): 亀岡弘和
  • Organizer: NLP若手の会(YANS)第11回シンポジウム
  • Place of Presentation: 和歌山県西牟婁郡白浜町
  • Year and Date: 2016-08-28
  • Invited
• [Presentation] 音響信号の分解と再構成 (2016)
  • Author(s): 亀岡弘和
  • Organizer: 第19回画像の認識・理解シンポジウム(MIRU2016)
  • Place of Presentation: 静岡県浜松市
  • Year and Date: 2016-08-01
  • Invited
• [Presentation] 音響信号の分解と再構成 (2016)
  • Author(s): 亀岡弘和
  • Organizer: 情報処理学会音学シンポジウム2016
  • Place of Presentation: 東京都港区
  • Year and Date: 2016-05-21
  • Invited
• [Presentation] 非負値行列因子分解を用いた欠損データ補間による超解像声道スペクトル推定 (2016)
  • Author(s): 中村友彦, 亀岡弘和
  • Organizer: 電子情報通信学会音声研究会
  • Place of Presentation: 大分県別府市
  • Year and Date: 2016-03-28
• [Presentation] Shifted and convolutive source-filter non-negative matrix factorization for monaural audio source separation (2016)
  • Author(s): Tomohiko Nakamura, and Hirokazu Kameoka
  • Organizer: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2016)
  • Place of Presentation: Shanghai, China
  • Year and Date: 2016-03-20
  • Int'l Joint Research
• [Presentation] ケプストラム距離正則化半教師ありNMF による音声強調 (2016)
  • Author(s): 李莉, 亀岡弘和, 樋口卓哉，猿渡洋
  • Organizer: 日本音響学会2016年春季研究発表会
  • Place of Presentation: 神奈川県横浜市
  • Year and Date: 2016-03-09
• [Presentation] 高速近似連続ウェーブレット変換による振幅スペクトログラムに対する実時間位相推定法 (2016)
  • Author(s): 中村友彦, 亀岡弘和
  • Organizer: 日本音響学会2016年春季研究発表会
  • Place of Presentation: 神奈川県横浜市
  • Year and Date: 2016-03-09
• [Presentation] 波源拘束差分方程式に基づく音響信号の確率モデル化と複数音源定位アルゴリズム (2016)
  • Author(s): 鈴木惇, 亀岡弘和
  • Organizer: 日本音響学会2016年春季研究発表会
  • Place of Presentation: 神奈川県横浜市
  • Year and Date: 2016-03-09
• [Presentation] 非負値テンソル二重逆畳み込みによる残響環境下の劣決定音源分離 (2016)
  • Author(s): 村田直毅, 亀岡弘和, 木下慶介, 荒木章子, 中谷智広, 小山翔一, 猿渡洋
  • Organizer: 日本音響学会2016年春季研究発表会
  • Place of Presentation: 神奈川県横浜市
  • Year and Date: 2016-03-09
• [Presentation] 非負値行列因子分解に基づく欠損データ補間による声道スペクトル推定法の検討 (2016)
  • Author(s): 中村友彦, 亀岡弘和
  • Organizer: 日本音響学会2016年春季研究発表会
  • Place of Presentation: 神奈川県横浜市
  • Year and Date: 2016-03-09
• [Presentation] Modeling speech parameter sequences with latent trajectory hidden Markov model (2015)
  • Author(s): Hirokazu Kameoka
  • Organizer: The 25th IEEE International Workshop on Machine Learning for Signal Processing (MLSP2015)
  • Place of Presentation: Boston, USA
  • Year and Date: 2015-09-17
  • Int'l Joint Research
• [Presentation] 潜在トラジェクトリ隠れマルコフモデルによる音声特徴量系列モデリング (2015)
  • Author(s): 亀岡弘和
  • Organizer: 日本音響学会2015年秋季研究発表会
  • Place of Presentation: 福島県会津若松市
  • Year and Date: 2015-09-16
• [Presentation] Unified approach for audio source separation with multichannel factorial HMM and DOA mixture model (2015)
  • Author(s): Takuya Higuchi, and Hirokazu Kameoka
  • Organizer: The 2015 European Signal Processing Conference (EUSIPCO 2015)
  • Place of Presentation: Nice, France
  • Year and Date: 2015-08-31
  • Int'l Joint Research
• [Presentation] Efficient multichannel nonnegative matrix factorization exploiting rank-1 spatial model (2015)
  • Author(s): Daichi Kitamura, Nobutaka Ono, Hiroshi Sawada, Hirokazu Kameoka, Hiroshi Saruwatari
  • Organizer: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2015)
  • Place of Presentation: Brisbane, Australia
  • Year and Date: 2015-04-19 – 2015-04-24
• [Presentation] Multi-resolution signal decomposition with time-domain spectrogram factorization (2015)
  • Author(s): Hirokazu Kameoka
  • Organizer: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2015)
  • Place of Presentation: Brisbane, Australia
  • Year and Date: 2015-04-19
  • Int'l Joint Research
• [Presentation] Lp-norm non-negative matrix factorization and its application to singing voice enhancement (2015)
  • Author(s): Tomohiko Nakamura, and Hirokazu Kameoka
  • Organizer: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2015)
  • Place of Presentation: Brisbane, Australia
  • Year and Date: 2015-04-19
  • Int'l Joint Research
• [Presentation] 複合ウェーブレットモデルとF0パターン生成過程の確率モデルを用いたテキスト音声合成 (2015)
  • Author(s): 門脇健人, 北条伸克, 亀岡弘和
  • Organizer: 日本音響学会2015年春季研究発表会
  • Place of Presentation: 中央大学 後楽園キャンパス (東京都文京区)
  • Year and Date: 2015-03-16 – 2015-03-18
• [Presentation] 多チャンネル階乗隠れマルコフモデルによる音源分離・音響イベント検出・残響除去・到来方向推定の統合的アプローチとその性能評価 (2015)
  • Author(s): 樋口卓哉, 亀岡弘和
  • Organizer: 日本音響学会2015年春季研究発表会
  • Place of Presentation: 中央大学 後楽園キャンパス (東京都文京区)
  • Year and Date: 2015-03-16 – 2015-03-18
• [Presentation] 多チャンネル階乗隠れマルコフモデルのスペクトル包絡事前学習によるセミブラインド音源分離 (2015)
  • Author(s): 樋口卓哉, 亀岡弘和
  • Organizer: 日本音響学会2015年春季研究発表会
  • Place of Presentation: 中央大学 後楽園キャンパス (東京都文京区)
  • Year and Date: 2015-03-16 – 2015-03-18
• [Presentation] 優決定条件BSSにおけるランク1空間制約の緩和 (2015)
  • Author(s): 北村大地, 小野順貴, 澤田宏, 亀岡弘和, 猿渡洋
  • Organizer: 日本音響学会2015年春季研究発表会
  • Place of Presentation: 中央大学 後楽園キャンパス (東京都文京区)
  • Year and Date: 2015-03-16 – 2015-03-18
• [Presentation] 多チャンネル階乗隠れマルコフモデルによる音響情景分析のための統合的アプローチ (2015)
  • Author(s): 樋口卓哉, 亀岡弘和
  • Organizer: 日本音響学会電気音響研究会/電子情報通信学会応用音響研究会
  • Place of Presentation: 南の美ら花ホテルミヤヒラ（沖縄県石垣市）
  • Year and Date: 2015-03-02 – 2015-03-03
• [Presentation] 全極スペクトルモデルを用いた調波時間因子分解による多重音解析 (2015)
  • Author(s): 中村 友彦, 亀岡 弘和
  • Organizer: 情報処理学会音楽情報科学研究会
  • Place of Presentation: 甲府富士屋ホテル（山梨県甲府市）
  • Year and Date: 2015-03-02 – 2015-03-03
• [Presentation] Hybrid multichannel signal separation using supervised nonnegative matrix factorization with spectrogram restoration (2014)
  • Author(s): Daichi Kitamura, Hiroshi Saruwatari, Satoshi Nakamura, Yu Takahashi, Kazunobu Kondo, Hirokazu Kameoka
  • Organizer: Asia Pacific Signal and Information Processing Association Annual Summit and Conference 2014 (APSIPA ASC 2014)
  • Place of Presentation: Siem Reap, the city of Angkor Wat, Cambodia
  • Year and Date: 2014-12-09 – 2014-12-12
• [Presentation] Unified approach for underdetermined BSS, VAD, dereverberation and DOA estimation with multichannel factorial HMM (2014)
  • Author(s): Takuya Higuchi, Hirokazu Kameoka
  • Organizer: The 2nd IEEE Global Conference on Signal and Information Processing (GlobalSIP 2014)
  • Place of Presentation: Atlanta, Georgia, USA
  • Year and Date: 2014-12-03 – 2014-12-05
• [Presentation] 音声音響信号処理のための確率モデルと学習アルゴリズム (2014)
  • Author(s): 亀岡弘和
  • Organizer: 第17回情報論的学習理論ワークショップ(IBIS2014)
  • Place of Presentation: 名古屋工業大学 御器所キャンパス（愛知県名古屋市）
  • Year and Date: 2014-11-16 – 2014-11-19
  • Invited
• [Presentation] 補助関数法に基づく制約付きボルツマンマシンの学習アルゴリズム (2014)
  • Author(s): 高宗典玄, 亀岡弘和
  • Organizer: 第17回情報論的学習理論ワークショップ(IBIS2014)
  • Place of Presentation: 名古屋大学 東山キャンパス（愛知県名古屋市）
  • Year and Date: 2014-11-16 – 2014-11-19
• [Presentation] 多チャンネル階乗隠れマルコフモデルによる音響情景分析のための統合的アプローチ (2014)
  • Author(s): 樋口卓哉, 亀岡弘和
  • Organizer: 第17回情報論的学習理論ワークショップ(IBIS2014)
  • Place of Presentation: 名古屋大学 東山キャンパス（愛知県名古屋市）
  • Year and Date: 2014-11-16 – 2014-11-19
• [Presentation] Harmonic-Temporal Factor Decomposition incorporating music prior information for informed monaural source separation (2014)
  • Author(s): Tomohiko Nakamura, Kotaro Shikata, Norihiro Takamune, Hirokazu Kameoka
  • Organizer: The 15th International Society for Music Information Retrieval Conference (ISMIR 2014)
  • Place of Presentation: Taipei, Taiwan
  • Year and Date: 2014-10-27 – 2014-10-31
• [Presentation] Training restricted Boltzmann machines with auxiliary function approach (2014)
  • Author(s): Hirokazu Kameoka, Norihiro Takamune
  • Organizer: The 24th IEEE International Workshop on Machine Learning for Signal Processing (MLSP2014)
  • Place of Presentation: Reims, France
  • Year and Date: 2014-09-21 – 2014-09-24
• [Presentation] Maximum reconstruction probability training of restricted Boltzmann machines with auxiliary function approach (2014)
  • Author(s): Norihiro Takamune, Hirokazu Kameoka
  • Organizer: The 24th IEEE International Workshop on Machine Learning for Signal Processing (MLSP2014)
  • Place of Presentation: Reims, France
  • Year and Date: 2014-09-21 – 2014-09-24
• [Presentation] Joint audio source separation and dereverberation based on multichannel factorial hidden Markov model (2014)
  • Author(s): Takuya Higuchi, Hirokazu Kameoka
  • Organizer: The 24th IEEE International Workshop on Machine Learning for Signal Processing (MLSP2014)
  • Place of Presentation: Reims, France
  • Year and Date: 2014-09-21 – 2014-09-24
• [Presentation] Speech prosody generation for text-to-speech synthesis based on generative model of F0 contours (2014)
  • Author(s): Kento Kadowaki, Tatsuma Ishihara, Nobukatsu Hojo, Hirokazu Kameoka
  • Organizer: The 15th Annual Conference of the International Speech Communication Association (Interspeech 2014)
  • Place of Presentation: Singapore
  • Year and Date: 2014-09-14 – 2014-09-18
• [Presentation] A unified approach for underdetermined blind signal separation and source activity detection by multichannel factorial hidden Markov models (2014)
  • Author(s): Takuya Higuchi, Hirofumi Takeda, Tomohiko Nakamura, Hirokazu Kameoka
  • Organizer: The 15th Annual Conference of the International Speech Communication Association (Interspeech 2014)
  • Place of Presentation: Singapore
  • Year and Date: 2014-09-14 – 2014-09-18
• [Presentation] 補助関数法によるGaussian-Bernoulli RBMの学習アルゴリズム (2014)
  • Author(s): 高宗典玄, 亀岡弘和
  • Organizer: 日本音響学会2014年秋季研究発表会
  • Place of Presentation: 北海学園大学 豊平キャンパス (北海道札幌市)
  • Year and Date: 2014-09-03 – 2014-09-05
• [Presentation] 多チャンネルFactorial hidden Markov modelによる劣決定ブラインド音源分離と音響イベント検出の統合的アプローチ (2014)
  • Author(s): 樋口卓哉, 竹田裕史, 中村友彦, 亀岡弘和
  • Organizer: 日本音響学会2014年秋季研究発表会
  • Place of Presentation: 北海学園大学 豊平キャンパス (北海道札幌市)
  • Year and Date: 2014-09-03 – 2014-09-05
• [Presentation] 多チャンネルFactorial hidden Markov modelによる音源分離・残響除去・音響イベント検出の統合的アプローチ (2014)
  • Author(s): 樋口卓哉, 亀岡弘和
  • Organizer: 日本音響学会2014年秋季研究発表会
  • Place of Presentation: 北海学園大学 豊平キャンパス (北海道札幌市)
  • Year and Date: 2014-09-03 – 2014-09-05
• [Presentation] Efficient multichannel nonnegative matrix factorization with rank-1 spatial model (2014)
  • Author(s): 北村大地, 小野順貴, 澤田宏, 亀岡弘和, 猿渡洋
  • Organizer: 日本音響学会2014年秋季研究発表会
  • Place of Presentation: 北海学園大学 豊平キャンパス (北海道札幌市)
  • Year and Date: 2014-09-03 – 2014-09-05
• [Presentation] 音声F0パターン生成過程の確率モデルによるテキストからの韻律生成及びその評価 (2014)
  • Author(s): 門脇健人, 亀岡弘和
  • Organizer: 日本音響学会2014年秋季研究発表会
  • Place of Presentation: 北海学園大学 豊平キャンパス (北海道札幌市)
  • Year and Date: 2014-09-03 – 2014-09-05
• [Presentation] Fast signal reconstruction from magnitude spectrogram of continuous wavelet transform based on spectrogram consistency (2014)
  • Author(s): Tomohiko Nakamura, Hirokazu Kameoka
  • Organizer: The 17th International Conference on Digital Audio Effects (DAFx-14)
  • Place of Presentation: Erlangen, Germany
  • Year and Date: 2014-09-01 – 2014-09-05
• [Presentation] ケプストラム距離正則化に基づく多重音解析 (2014)
  • Author(s): 樋口卓哉, 亀岡弘和
  • Organizer: 情報処理学会音楽情報科学研究会
  • Place of Presentation: 京都大学 吉田キャンパス（京都府京都市）
  • Year and Date: 2014-08-25 – 2014-08-27
• [Presentation] 調波時間因子分解法に基づく事前情報付き多重音解析 (2014)
  • Author(s): 四方紘太郎, 高宗典玄, 中村友彦, 亀岡弘和
  • Organizer: 情報処理学会音楽情報科学研究会/電子情報通信学会・日本音響学会音声研究会
  • Place of Presentation: 日本大学 文理学部キャンパス（東京都世田谷区）
  • Year and Date: 2014-05-24 – 2014-05-25
• [Presentation] "Experimental evaluation of superresolution-based nonnegative matrix factorization for binaural recording (2014)
  • Author(s): Daichi Kitamura, Hiroshi Saruwatari, Satoshi Nakamura, Yu Takahashi, Kazunobu Kondo, Hirokazu Kameoka
  • Organizer: 情報処理学会音楽情報科学研究会/電子情報通信学会・日本音響学会音声研究会
  • Place of Presentation: 日本大学 文理学部キャンパス（東京都世田谷区）
  • Year and Date: 2014-05-24 – 2014-05-25
• [Presentation] 補助関数法によるGaussian-Bernoulli RBMの学習アルゴリズムの検討 (2014)
  • Author(s): 高宗典玄, 亀岡弘和
  • Organizer: 情報処理学会音楽情報科学研究会/電子情報通信学会・日本音響学会音声研究会
  • Place of Presentation: 日本大学 文理学部キャンパス（東京都世田谷区）
  • Year and Date: 2014-05-24 – 2014-05-25
• [Presentation] 無矛盾性規準に基づく連続ウェーブレット変換スペクトログラムへの位相推定法と高速化 (2014)
  • Author(s): 中村友彦, 亀岡弘和
  • Organizer: 情報処理学会音楽情報科学研究会/電子情報通信学会・日本音響学会音声研究会
  • Place of Presentation: 日本大学 文理学部キャンパス（東京都世田谷区）
  • Year and Date: 2014-05-24 – 2014-05-25
• [Presentation] 確率的モデル化に基づく移動音源の劣決定ブラインド音源分離 (2014)
  • Author(s): 樋口卓哉, 高宗典玄, 中村友彦, 亀岡弘和
  • Organizer: 情報処理学会音楽情報科学研究会/電子情報通信学会・日本音響学会音声研究会
  • Place of Presentation: 日本大学 文理学部キャンパス（東京都世田谷区）
  • Year and Date: 2014-05-24 – 2014-05-25
• [Presentation] 音声F0パターン生成過程の確率モデルによるテキストからの韻律生成 (2014)
  • Author(s): 門脇健人, 北条伸克, 石原達馬, 亀岡弘和
  • Organizer: 情報処理学会音楽情報科学研究会/電子情報通信学会・日本音響学会音声研究会
  • Place of Presentation: 日本大学 文理学部キャンパス（東京都世田谷区）
  • Year and Date: 2014-05-24 – 2014-05-25
• [Presentation] Divergence optimization in nonnegative matrix factorization with spectrogram restoration for multichannel signal separation (2014)
  • Author(s): Daichi Kitamura, Hiroshi Saruwatari, Satoshi Nakamura, Yu Takahashi, Kazunobu Kondo, Hirokazu Kameoka
  • Organizer: The 4th Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA 2014)
  • Place of Presentation: Nancy, France
  • Year and Date: 2014-05-12 – 2014-05-14
• [Presentation] Underdetermined blind separation and tracking of moving sources based on DOA-HMM (2014)
  • Author(s): Takuya Higuchi, Norihiro Takamune, Tomohiko Nakamura, Hirokazu Kameoka
  • Organizer: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2014)
  • Place of Presentation: Florence, Italy
  • Year and Date: 2014-05-04 – 2014-05-09
• [Book] "Gaussian model based multichannel separation" in Audio Source Separation and Speech Enhancement (2017)
  • Author(s): Alexey Ozerov, Hirokazu Kameoka
  • Publisher: Springer
• [Book] "General formulation of multichannel extensions of NMF variants" in Audio Source Separation (2017)
  • Author(s): Hirokazu Kameoka, Hiroshi Sawada, Takuya Higuchi
  • Publisher: Springer
• [Book] Applied Matrix and Tensor Variate Data Analysis (2015)
  • Author(s): Kohei Adachi, Hirokazu Kameoka, Kohei Inoue, Noboru Murata, Deniz Akdemir, Manabu Iwasa, and Toshio Sakata
  • Total Pages: 136
  • Publisher: Springer
• [Book] Speech Prosody in Speech Synthesis: Modeling and generation of prosody for high quality and flexible speech synthesis (2015)
  • Author(s): Hirokazu Kameoka
  • Total Pages: 213
  • Publisher: Springer-Verlag Berlin Heidelberg
• [Patent(Industrial Property Rights)] 信号推定装置、方法、及びプログラム (2017)
  • Inventor(s): 亀岡弘和, 関翔悟, 戸田智基
  • Industrial Property Rights Holder: 亀岡弘和, 関翔悟, 戸田智基
  • Industrial Property Rights Type: 特許
  • Industrial Property Number: 2017-030173
  • Filing Date: 2017-02-21
• [Patent(Industrial Property Rights)] 信号解析装置、方法、及びプログラム (2017)
  • Inventor(s): 亀岡弘和, 李莉
  • Industrial Property Rights Holder: 亀岡弘和, 李莉
  • Industrial Property Rights Type: 特許
  • Industrial Property Number: 2017-028843
  • Filing Date: 2017-02-20
• [Patent(Industrial Property Rights)] 音源定位装置、方法、及びプログラム (2017)
  • Inventor(s): 亀岡弘和, 植野夏樹
  • Industrial Property Rights Holder: 亀岡弘和, 植野夏樹
  • Industrial Property Rights Type: 特許
  • Industrial Property Number: 2017-037404
  • Filing Date: 2017-02-28
• [Patent(Industrial Property Rights)] 声道スペクトル推定装置、方法、及びプログラム (2017)
  • Inventor(s): 亀岡弘和, ゾウユンハン
  • Industrial Property Rights Holder: 亀岡弘和, ゾウユンハン
  • Industrial Property Rights Type: 特許
  • Industrial Property Number: 2017-037402
  • Filing Date: 2017-02-28
• [Patent(Industrial Property Rights)] 基本周波数モデルパラメータ推定装置、方法、及びプログラム (2016)
  • Inventor(s): 亀岡弘和, 平松薫, 柏野邦夫, 佐藤遼太郎
  • Industrial Property Rights Holder: 亀岡弘和, 平松薫, 柏野邦夫, 佐藤遼太郎
  • Industrial Property Rights Type: 特許
  • Industrial Property Number: 2016-240303
  • Filing Date: 2016-12-12
• [Patent(Industrial Property Rights)] 基本周波数モデルパラメータ推定装置、方法、及びプログラム (2016)
  • Inventor(s): 亀岡弘和, 平松薫, 柏野邦夫, 佐藤遼太郎
  • Industrial Property Rights Holder: 亀岡弘和, 平松薫, 柏野邦夫, 佐藤遼太郎
  • Industrial Property Rights Type: 特許
  • Industrial Property Number: 2016-240304
  • Filing Date: 2016-12-12
• [Patent(Industrial Property Rights)] 信号解析装置、方法、及びプログラム (2016)
  • Inventor(s): 亀岡弘和, 岸田拓也
  • Industrial Property Rights Holder: 亀岡弘和, 岸田拓也
  • Industrial Property Rights Type: 特許
  • Industrial Property Number: 2016-168309
  • Filing Date: 2016-08-30
• [Patent(Industrial Property Rights)] 信号解析装置、方法、及びプログラム (2016)
  • Inventor(s): 亀岡弘和, 鏡英章
  • Industrial Property Rights Holder: 亀岡弘和, 鏡英章
  • Industrial Property Rights Type: 特許
  • Industrial Property Number: 2016-168322
  • Filing Date: 2016-08-30
• [Patent(Industrial Property Rights)] 信号解析装置、方法、及びプログラム (2016)
  • Inventor(s): 亀岡弘和, 鏡英章
  • Industrial Property Rights Holder: 亀岡弘和, 鏡英章
  • Industrial Property Rights Type: 特許
  • Industrial Property Number: 2016-168332
  • Filing Date: 2016-08-30
• [Patent(Industrial Property Rights)] 音声合成学習装置、方法、及びプログラム (2016)
  • Inventor(s): 金子卓弘, 亀岡弘和, 平松薫, 柏野邦夫
  • Industrial Property Rights Holder: 金子卓弘, 亀岡弘和, 平松薫, 柏野邦夫
  • Industrial Property Rights Type: 特許
  • Industrial Property Number: 2016-168356
  • Filing Date: 2016-08-30
• [Patent(Industrial Property Rights)] 信号解析装置、方法、及びプログラム (2016)
  • Inventor(s): 亀岡弘和, 田尻祐介, 戸田智基, 中村哲
  • Industrial Property Rights Holder: 亀岡弘和, 田尻祐介, 戸田智基, 中村哲
  • Industrial Property Rights Type: 特許
  • Filing Date: 2016-02-23
• [Patent(Industrial Property Rights)] 信号解析装置、方法、及びプログラム (2016)
  • Inventor(s): 亀岡弘和, 李莉
  • Industrial Property Rights Holder: 亀岡弘和, 李莉
  • Industrial Property Rights Type: 特許
  • Filing Date: 2016-02-23
• [Patent(Industrial Property Rights)] 基本周波数パターン予測装置、方法、及びプログラム (2016)
  • Inventor(s): 亀岡弘和, 田中宏, 戸田智基, 中村哲
  • Industrial Property Rights Holder: 亀岡弘和, 田中宏, 戸田智基, 中村哲
  • Industrial Property Rights Type: 特許
  • Filing Date: 2016-02-23
• [Patent(Industrial Property Rights)] 基本周波数パターン予測装置、方法、及びプログラム (2016)
  • Inventor(s): 亀岡弘和, 田中宏, 戸田智基, 中村哲
  • Industrial Property Rights Holder: 亀岡弘和, 田中宏, 戸田智基, 中村哲
  • Industrial Property Rights Type: 特許
  • Filing Date: 2016-02-23
• [Patent(Industrial Property Rights)] 基本周波数パターン予測装置、方法、及びプログラム (2016)
  • Inventor(s): 亀岡弘和, 田中宏, 戸田智基, 中村哲
  • Industrial Property Rights Holder: 亀岡弘和, 田中宏, 戸田智基, 中村哲
  • Industrial Property Rights Type: 特許
  • Filing Date: 2016-02-23
• [Patent(Industrial Property Rights)] 声道スペクトル推定装置、声道スペクトル推定方法、及びプログラム (2016)
  • Inventor(s): 亀岡弘和, 中村友彦
  • Industrial Property Rights Holder: 亀岡弘和, 中村友彦
  • Industrial Property Rights Type: 特許
  • Filing Date: 2016-02-23
• [Patent(Industrial Property Rights)] 音響信号解析装置、音響信号解析方法、及びプログラム (2016)
  • Inventor(s): 亀岡弘和, 村田直毅
  • Industrial Property Rights Holder: 亀岡弘和, 村田直毅
  • Industrial Property Rights Type: 特許
  • Filing Date: 2016-02-23
• [Patent(Industrial Property Rights)] 音源定位装置、方法、及びプログラム (2016)
  • Inventor(s): 亀岡弘和, 鈴木惇
  • Industrial Property Rights Holder: 亀岡弘和, 鈴木惇
  • Industrial Property Rights Type: 特許
  • Filing Date: 2016-02-23
• [Patent(Industrial Property Rights)] 音源定位装置、方法、及びプログラム (2016)
  • Inventor(s): 亀岡弘和, 鈴木惇
  • Industrial Property Rights Holder: 亀岡弘和, 鈴木惇
  • Industrial Property Rights Type: 特許
  • Filing Date: 2016-02-23
• [Patent(Industrial Property Rights)] 音源定位装置、方法、及びプログラム (2016)
  • Inventor(s): 亀岡弘和, 鈴木惇
  • Industrial Property Rights Holder: 亀岡弘和, 鈴木惇
  • Industrial Property Rights Type: 特許
  • Filing Date: 2016-02-23
• [Patent(Industrial Property Rights)] 信号解析装置、方法、及びプログラム (2014)
  • Inventor(s): 亀岡弘和, 樋口卓哉, 竹田裕史
  • Industrial Property Rights Holder: 亀岡弘和, 樋口卓哉, 竹田裕史
  • Industrial Property Rights Type: 特許
  • Industrial Property Number: 2014-166903
  • Filing Date: 2014-08-19