Daichi Kitamura, Nobutaka Ono, Hiroshi Sawada, Hirokazu Kameoka, and Hiroshi Saruwatari,
"Determined blind source separation with independent low-rank matrix analysis,"
Audio Source Separation. Signals and Communication Technology., Shoji Makino, Ed. Springer, Cham, pp. 125–155, March 2018.
(Springer Link)
Daichi Kitamura,
"Q11 What is beamforming?,"
Acousticpedia for Beginners, Acoustical Society of Japan, Eds. Corona Publishing, pp. 44–47, March 2017 (in Japanese).
Journal Papers
Naoki Makishima, Yoshiki Mitsui, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo,
"Independent deeply learned matrix analysis with automatic selection of stable microphone-wise update and fast sourcewise update of demixing matrix,"
Signal Processing, vol. 178, 107753, Jan 2021 (corresponding author).
(ELSEVIER)
Yuki Kubo, Norihiro Takamune, Daichi Kitamura, and Hiroshi Saruwatari,
"Blind speech extraction based on rank-constrained spatial covariance matrix estimation with multivariate generalized Gaussian distribution,"
IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 28, pp. 1948–1963, June 2020.
(IEEE Xplore)
Shinnosuke Takamichi, Yuki Saito, Norihiro Takamune, Daichi Kitamura, and Hiroshi Saruwatari,
"Phase reconstruction from amplitude spectrograms based on directional-statistics deep neural networks,"
Signal Processing, vol. 169, 107368, April 2020.
(ELSEVIER)
Shinichi Mogami, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, Kazunobu Kondo, and Nobutaka Ono,
"Independent low-rank matrix analysis based on time-variant sub-Gaussian source model for determined blind source separation,"
IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 28, pp. 503–518, December 2019 (corresponding author).
(IEEE Xplore)
Yuki Mitsufuji, Stefan Uhlich, Norihiro Takamune, Daichi Kitamura, Shoichi Koyama, and Hiroshi Saruwatari,
"Multichannel non-negative matrix factorization using banded spatial covariance matrices in wavenumber domain,"
IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 28, pp.49–60, October 2019.
(IEEE Xplore)
Naoki Makishima, Shinichi Mogami, Norihiro Takamune, Daichi Kitamura, Hayato Sumino, Shinnosuke Takamichi, Hiroshi Saruwatari, and Nobutaka Ono,
"Independent deeply learned matrix analysis for determined audio source separation,"
IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 27, no. 10, pp. 1601–1615, October 2019.
(IEEE Xplore)
Hiroaki Nakajima, Daichi Kitamura, Norihiro Takamune, Hiroshi Saruwatari, and Nobutaka Ono,
"Bilevel optimization using stationary point of lower-level objective function for discriminative basis learning in nonnegative matrix factorization,"
IEEE Signal Processing Letters, vol. 26, no. 6, pp. 818–822, June 2019.
(IEEE Xplore)
Hiroshi Sawada, Nobutaka Ono, Hirokazu Kameoka, Daichi Kitamura, and Hiroshi Saruwatari,
"A Review of Blind Source Separation Methods: Two Converging Routes to ILRMA Originating from ICA and NMF,"
APSIPA Transactions on Signal and Information Processing, vol. 8, no. e12, pp. 1–14, May 2019.
(APSIPA Trans. Signal and Info. Proc.)
Shinichi Mogami, Yoshiki Mitsui, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, Kazunobu Kondo, Hiroaki Nakajima, and Hirokazu Kameoka,
"Independent low-rank matrix analysis based on generalized Kullback-Leibler divergence,"
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, vol. E102-A, no. 2, pp. 458–463, February 2019.
(IEICE, PDF, IEICE Transactions Online, Copyright (c) 2019 IEICE)
Daichi Kitamura, Shinichi Mogami, Yoshiki Mitsui, Norihiro Takamune, Hiroshi Saruwatari, Nobutaka Ono, Yu Takahashi, and Kazunobu Kondo,
"Generalized independent low-rank matrix analysis using heavy-tailed distributions for blind source separation,"
EURASIP Journal on Advances in Signal Processing, vol. 2018, no. 1, p. 28, May 2018.
(EURASIP JASP)
Yoshiaki Bando, Hiroshi Saruwatari, Nobutaka Ono, Shoji Makino, Katsutoshi Itoyama, Daichi Kitamura, Masaru Ishimura, Moe Takakusaki, Narumi Mae, Kouei Yamaoka, Yutaro Matsui, Yuichi Ambe, Masashi Konyo, Satoshi Tadokoro, Kazuyoshi Yoshii, and Hiroshi G. Okuno,
"Low-latency and high-quality two-stage human-voice-enhancement system for a hose-shaped rescue robot,"
Journal of Robotics and Mechatronics, vol. 29, no. 1, pp.198–212, February 2017.
(Fuji Technology Press Ltd.)
Daichi Kitamura, Nobutaka Ono, Hiroshi Sawada, Hirokazu Kameoka, and Hiroshi Saruwatari,
"Determined blind source separation unifying independent vector analysis and nonnegative matrix factorization,"
IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 24, no. 9, pp. 1626–1641, September 2016 (ACM Computing Reviews Annual Best of Computing Notable Books and Articles in Computing, IEEE SPS Japan Best Paper Award).
(IEEE Xplore, Supporting document)
Daichi Kitamura, Hiroshi Saruwatari, Hirokazu Kameoka, Yu Takahashi, Kazunobu Kondo, and Satoshi Nakamura,
"Multichannel signal separation combining directional clustering and nonnegative matrix factorization with spectrogram restoration,"
IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 23, no. 4, pp. 654–669, April 2015 (TAF The Telecom System Technology Student Award).
(IEEE Xplore)
Tomo Miyauchi, Daichi Kitamura, Hiroshi Saruwatari, and Satoshi Nakamura,
"Depth estimation of sound images using directional clustering and activation-shared nonnegative matrix factorization,"
Journal of Signal Processing, vol. 18, no. 4, pp. 217–220, July 2014 (corresponding author).
(J-STAGE)
Daichi Kitamura, Hiroshi Saruwatari, Kosuke Yagi, Kiyohiro Shikano, Yu Takahashi, and Kazunobu Kondo,
"Music signal separation based on supervised nonnegative matrix factorization with orthogonality and maximum-divergence penalties,"
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, vol. E97-A, no. 5, pp. 1113–1118, May 2014.
(IEICE, PDF, IEICE Transactions Online, Copyright (c) 2014 IEICE)
Masahiro Harazono, Daichi Kitamura, and Masashi Nakayama,
"Humbucking pickup response excited by string vibration,"
Acoustical Science and Technology, vol. 33, no. 5, pp. 301–309, September 2012.
(J-STAGE)
Review Articles & Invited Reviews
Daichi Kitamura,
"Nonnegative matrix factorization based on complex generative model,"
Acoustical Science and Technology, vol. 40, no. 3, pp. 155–161, May 2019.
(J-STAGE)
Daichi Kitamura,
"Nonnegative matrix factorization based on complex generative model and its application to audio source separation,"
The Journal of The Acoustical Society of Japan, vol. 75, no. 3, pp. 130–138, March 2019 (in Japanese).
Peer-Reviewed International Conference Proceedings
Shuhei Yamaji and Daichi Kitamura,
"DNN-based permutation solver for frequency-domain independent component analysis in two-source mixture case,"
Proceedings of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2020), pp. ???–???, Auckland, New Zealand, December 2020 (accepted).
Keigo Kamo, Yuki Kubo, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo,
"Joint-diagonalizability-constrained multichannel nonnegative matrix factorization based on multivariate complex Student's t-distribution,"
Proceedings of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2020), pp. ???–???, Auckland, New Zealand, December 2020 (accepted).
Rui Watanabe, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo,
"DNN-based frequency component prediction for frequency-domain audio source separation,"
Proceedings of European Signal Processing Conference (EUSIPCO 2020), pp. 805–809, Amsterdam, Netherlands, January 2021.
Keigo Kamo, Yuki Kubo, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, Kazunobu Kondo,
"Joint-diagonalizability-constrained multichannel nonnegative matrix factorization based on multivariate complex sub-Gaussian distribution,"
Proceedings of European Signal Processing Conference (EUSIPCO 2020), pp. 890–894, Amsterdam, Netherlands, January 2021.
Masakazu Une, Yuki Kubo, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, and Shoji Makino,
"Multichannel hearing-aid system based on basis-shared semi-supervised independent low-rank matrix analysis,"
Proceedings of Forum Acusticum, pp. ???–???, Lyon, France, December 2020.
Keigo Kamo, Yuki Kubo, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo,
"Regularized fast multichannel nonnegative matrix factorization with ILRMA-based prior distribution of joint-diagonalization process,"
Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2020), pp. 606–610, Barcelona, Spain, May 2020.
Tatsuki Kondo, Kanta Fukushige, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Rintaro Ikeshita, and Tomohiro Nakatani,
"Convergence-guaranteed independent positive semidefinite tensor analysis based on Student's t distribution,"
Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2020), pp. 681–685, Barcelona, Spain, May 2020.
Naoki Makishima, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo,
"Robust demixing filter update algorithm based on microphone-wise coordinate descent for independent deeply learned matrix analysis,"
Proceedings of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2019), pp. 1868–1873, Lanzhou, China, November 2019.
Yuki Kubo, Norihiro Takamune, Daichi Kitamura, and Hiroshi Saruwatari,
"Acceleration of rank-constrained spatial covariance matrix estimation for blind speech extraction,"
Proceedings of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2019), pp. 332–338, Lanzhou, China, November 2019.
Masakazu Une, Yuki Kubo, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, and Shoji Makino,
"Evaluation of multichannel hearing aid system using rank-constrained spatial covariance matrix estimation,"
Proceedings of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2019), pp. 1874–1879, Lanzhou, China, November 2019.
Naoki Makishima, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo,
"Column-wise update algorithm for independent deeply learned matrix analysis,"
Proceedings of International Congress on Acoustics (ICA 2019), pp. 2805–2812, Aachen, Germany, September 2019.
Yuki Kubo, Norihiro Takamune, Daichi Kitamura, and Hiroshi Saruwatari,
"Efficient full-rank spatial covariance estimation using independent low-rank matrix analysis for blind source separation,"
Proceedings of European Signal Processing Conference (EUSIPCO 2019), A Coruña, Spain, September 2019.
Naoki Makishima, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, Kazunobu Kondo, and Hiroaki Nakajima,
"Generalized-Gaussian-distribution-based independent deeply learned matrix analysis for multichannel audio source separation,"
Proceedings of International Congress and Exhibition on Noise Control Engineering (INTERNOISE 2019), Madrid, Spain, June 2019.
Kohei Yatabe and Daichi Kitamura,
"Time-frequency-masking-based determined BSS with application to sparse IVA,"
Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2019), pp. 715–719, Brighton, U.K., May 2019.
Shinichi Mogami, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, Kazunobu Kondo, Hiroaki Nakajima, and Nobutaka Ono,
"Independent low-rank matrix analysis based on time-variant sub-Gaussian source model,"
Proceedings of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2018), pp. 1684–1691, November 2018 (Best Paper Award).
Masakazu Une, Yuki Saito, Shinnosuke Takamichi, Daichi Kitamura, Ryoichi Miyazaki, and Hiroshi Saruwatari,
"Generative approach using the noise generation models for DNN-based speech synthesis trained from noisy speech,"
Proceedings of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2018), pp. 340–344, November 2018 (Invited Special Session).
Shinnosuke Takamichi, Yuki Saito, Norihiro Takamune, Daichi Kitamura, and Hiroshi Saruwatari,
"Phase reconstruction from amplitude spectrograms based on von-Mises-distribution deep neural network,"
Proceedings of International Workshop on Acoustic Signal Enhancement (IWAENC 2018), pp. 286–290, Tokyo, Japan, September 2018.
Shinichi Mogami, Hayato Sumino, Daichi Kitamura, Norihiro Takamune, Shinnosuke Takamichi, Hiroshi Saruwatari, and Nobutaka Ono,
"Independent deeply learned matrix analysis for multichannel audio source separation,"
Proceedings of European Signal Processing Conference (EUSIPCO 2018), pp. 1571–1575, Roma, Italy, September 2018.
Kohei Yatabe and Daichi Kitamura,
"Determined blind source separation via proximal splitting algorithm,"
Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2018), pp. 776–780, Calgary, Canada, April 2018.
(Preprint PDF)
Yoshiki Mitsui, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo,
"Vectorwise coordinate descent algorithm for spatially regularized independent low-rank matrix analysis,"
Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2018), pp. 746–750, Calgary, Canada, April 2018.
Narumi Mae, Koei Yamaoka, Yoshiki Mitsui, Mitsuo Matsumoto, Shoji Makino, Daichi Kitamura, Nobutaka Ono, Takeshi Yamada, and Hiroshi Saruwatari,
"Ego noise reduction and sound localization adapted to human ears using hose-shaped rescue robot,"
Proceedings of RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP 2018), pp. 371–374, Hawaii, USA, March 2018.
Moe Takakusaki, Daichi Kitamura, Nobutaka Ono, Shoji Makino, Takeshi Yamada, and Hiroshi Saruwatari,
"Ego-noise reduction for hose-shaped rescue robot using basis-shared semi-supervised independent low-rank matrix analysis,"
Proceedings of RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP 2018), pp. 351–354, Hawaii, USA, March 2018 (Student Paper Award).
Narumi Mae, Yoshiki Mitsui, Shoji Makino, Daichi Kitamura, Nobutaka Ono, Takeshi Yamada, and Hiroshi Saruwatari,
"Sound source localization using binaural different for hose-shaped rescue robot,"
Proceedings of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2017), Kuala Lumpur, Malaysia, December 2017.
Yoshiki Mitsui, Daichi Kitamura, Norihiro Takamune, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo,
"Independent low-rank matrix analysis based on parametric majorization-equalization algorithm,"
Proceedings of IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP 2017), pp. 98–102, Curaçao, Dutch Antilles, December 2017.
Shinichi Mogami, Daichi Kitamura, Yoshiki Mitsui, Norihiro Takamune, Hiroshi Saruwatari, and Nobutaka Ono,
"Independent low-rank matrix analysis based on complex Student's t-distribution for blind audio source separation,"
Proceedings of IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2017), Tokyo, Japan, September 2017.
Daichi Kitamura, Nobutaka Ono, and Hiroshi Saruwatari,
"Experimental analysis of optimal window length for independent low-rank matrix analysis,"
Proceedings of European Signal Processing Conference (EUSIPCO 2017), pp. 1210–1214, Kos, Greece, August 2017 (Invited Special Session).
(PDF, Slide)
Yoshiki Mitsui, Daichi Kitamura, Shinnosuke Takamichi, Nobutaka Ono, and Hiroshi Saruwatari,
"Blind source separation based on independent low-rank matrix analysis with sparse regularization for time-series activity,"
Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017), pp. 21–25, New Orleans, U.S.A., March 2017 (ICASSP Student Paper Contest Finalist, IEEE SPS Japan Student Conference Paper Award).
Antoine Liutkus, Fabian-Robert Stöter, Zafar Rafii, Daichi Kitamura, Bertrand Rivet, Nobutaka Ito, Nobutaka Ono, and Julie Fontecave,
"The 2016 signal separation evaluation campaign,"
Proceedings of International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA 2017), pp. 323–332, Grenoble, France, February 2017.
(Springer Link, PDF)
Narumi Mae, Masaru Ishimura, Daichi Kitamura, Nobutaka Ono, Takeshi Yamada, Shoji Makino, and Hiroshi Saruwatari,
"Ego noise reduction for hose-shaped rescue robot combining independent low-rank matrix analysis and multichannel noise cancellation,"
Proceedings of International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA 2017), pp. 141–151, Grenoble, France, February 2017.
(Springer Link)
Narumi Mae, Daichi Kitamura, Masaru Ishimura, Takeshi Yamada, and Shoji Makino,
"Ego noise reduction for hose-shaped rescue robot combining independent low-rank matrix analysis and noise cancellation,"
Proceedings of Asia-Pacific Signal and Information Process Processing Association Annual Summit and Conference (APSIPA ASC 2016), Jeju, Korea, December 2016.
(IEEE Xplore)
Hiroaki Nakajima, Daichi Kitamura, Norihiro Takamune, Shoichi Koyama, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo,
"Audio signal separation using supervised NMF with time-variant all-pole-model-based basis deformation,"
Proceedings of Asia-Pacific Signal and Information Process Processing Association Annual Summit and Conference (APSIPA ASC 2016), Jeju, Korea, December 2016.
(IEEE Xplore)
Daichi Kitamura and Nobutaka Ono,
"Efficient initialization for nonnegative matrix factorization based on nonnegative independent component analysis,"
Proceedings of International Workshop on Acoustic Signal Enhancement (IWAENC 2016), Xi'an, China, September 2016 (IWAENC Student Paper Competition Finalist).
(IEEE Xplore, Slide)
Daichi Kitamura, Nobutaka Ono, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo,
"Discriminative and reconstructive basis training for audio source separation with semi-supervised nonnegative matrix factorization,"
Proceedings of International Workshop on Acoustic Signal Enhancement (IWAENC 2016), Xi'an, China, September 2016.
(IEEE Xplore, Poster)
Moe Takakusaki, Daichi Kitamura, Nobutaka Ono, Takeshi Yamada, Shoji Makino, and Hiroshi Saruwatari,
"Ego-noise reduction for a hose-shaped rescue robot using determined rank-1 multichannel nonnegative matrix factorization,"
Proceedings of International Workshop on Acoustic Signal Enhancement (IWAENC 2016), Xi'an, China, September 2016.
(IEEE Xplore)
Hiroaki Nakajima, Daichi Kitamura, Norihiro Takamune, Shoichi Koyama, Hiroshi Saruwatari, Nobutaka Ono, Yu Takahashi, and Kazunobu Kondo,
"Music signal separation using supervised NMF with all-pole-model-based discriminative basis deformation,"
Proceedings of European Signal Processing Conference (EUSIPCO 2016), pp.1143–1147, Budapest, Hungary, August 2016.
(PDF, Poster)
Daichi Kitamura, Nobutaka Ono, Hiroshi Sawada, Hirokazu Kameoka, and Hiroshi Saruwatari,
"Relaxation of rank-1 spatial constraint in overdetermined blind source separation,"
Proceedings of European Signal Processing Conference (EUSIPCO 2015), pp. 1271–1275, Nice, France, August 2015 (Invited Special Session).
(PDF, Slide)
Nobutaka Ono, Zafar Rafii, Daichi Kitamura, Nobutaka Ito, and Antoine Liutkus,
"The 2015 signal separation evaluation campaign,"
Proceedings of International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA 2015), Liberec, Czech, August 2015.
(ACM Digital Library, PDF)
Daichi Kitamura, Nobutaka Ono, Hiroshi Sawada, Hirokazu Kameoka, and Hiroshi Saruwatari,
"Efficient multichannel nonnegative matrix factorization exploiting rank-1 spatial model,"
Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2015), pp. 276–280, Brisbane, Australia, April 2015 (IEEE SPS Japan Student Conference Paper Award).
(IEEE Xplore, Poster)
Yuki Murota, Daichi Kitamura, Shoichi Koyama, Hiroshi Saruwatari, and Satoshi Nakamura,
"Statistical modeling of binaural signal and its application to binaural source separation,"
Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2015), pp. 494–498, Brisbane, Australia, April 2015.
(IEEE Xplore)
Daichi Kitamura, Hiroshi Saruwatari, Satoshi Nakamura, Yu Takahashi, Kazunobu Kondo, and Hirokazu Kameoka,
"Hybrid multichannel signal separation using supervised nonnegative matrix factorization with spectrogram restoration,"
Proceedings of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2014), Siem Reap, Cambodia, December 2014 (Invited Special Session).
(IEEE Xplore, Slide)
Daichi Kitamura, Hiroshi Saruwatari, Satoshi Nakamura, Yu Takahashi, Kazunobu Kondo, and Hirokazu Kameoka,
"Divergence optimization in nonnegative matrix factorization with spectrogram restoration for multichannel signal separation,"
Proceedings of Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA 2014), pp. 92–96, Nancy, France, May 2014.
(IEEE Xplore, Slide)
Yuki Murota, Daichi Kitamura, Hiroshi Saruwatari, Satoshi Nakamura, Yu Takahashi, and Kazunobu Kondo,
"Music signal separation based on Bayesian spectral amplitude estimator with automatic target prior adaptation,"
Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014), pp. 7540–7544, Florence, Italy, May 2014.
(IEEE Xplore, Poster)
Daichi Kitamura, Hiroshi Saruwatari, Satoshi Nakamura, Yu Takahashi, Kazunobu Kondo, and Hirokazu Kameoka,
"Online divergence switching for superresolution-based nonnegative matrix factorization,"
Proceedings of RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP 2014), pp. 485–488, Hawaii, U.S.A., March 2014 (NCSP Student Paper Award).
(Slide)
Tomo Miyauchi, Daichi Kitamura, Hiroshi Saruwatari, and Satoshi Nakamura,
"Depth estimation of sound images using directional clustering and activation-shared nonnegative matrix factorization,"
Proceedings of RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP 2014), pp. 437–440, Hawaii, U.S.A., March 2014 (NCSP Student Paper Award).
(Slide)
Daichi Kitamura, Hiroshi Saruwatari, Kosuke Yagi, Kiyohiro Shikano, Yu Takahashi, and Kazunobu Kondo,
"Robust music signal separation based on supervised nonnegative matrix factorization with prevention of basis sharing,"
Proceedings of IEEE International Symposium on Signal Processing and Information Technology (ISSPIT 2013), pp. 392–397, Athens, Greece, December 2013.
(IEEE Xplore, Slide)
Daichi Kitamura, Hiroshi Saruwatari, Kiyohiro Shikano, Kazunobu Kondo, and Yu Takahashi,
"Music signal separation by supervised nonnegative matrix factorization with basis deformation,"
Proceedings of IEEE International Conference on Digital Signal Processing (DSP 2013), Santorini, Greece, July 2013.
(IEEE Xplore, Poster)
Daichi Kitamura, Hiroshi Saruwatari, Yusuke Iwao, Kiyohiro Shikano, Kazunobu Kondo, and Yu Takahashi,
"Superresolution-based stereo signal separation via supervised nonnegative matrix factorization,"
Proceedings of IEEE International Conference on Digital Signal Processing (DSP 2013), Santorini, Greece, July 2013.
(IEEE Xplore, Slide)
Daichi Kitamura, Hiroshi Saruwatari, Kiyohiro Shikano, Kazunobu Kondo, and Yu Takahashi,
"Regularized superresolution-based binaural signal separation with nonnegative matrix factorization,"
Proceedings of International Conference on 3D Systems and Applications (3DSA 2013), Osaka, Japan, June 2013.
(PDF, Slide)
Non-Reviewed Domestic Conference Proceedings
Rui Watanabe, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo,
"Fast audio source separation using bandwidth expansion based on deep neural networks,"
Proceedings of 2020 Autumn Meeting of Acoustical Society of Japan, 1-1-7, pp. 131–134, Miyagi, September 2020 (in Japanese).
Yuto Kondo, Yuki Kubo, Norihiro Takamune, Daichi Kitamura, and Hiroshi Saruwatari,
"Deficient basis estimation of noise spatial covariance matrix for rank-constrained spatial covariance matrix estimation method in blind speech extraction,"
Proceedings of 2020 Autumn Meeting of Acoustical Society of Japan, 1-1-8, pp. 135–138, Miyagi, September 2020 (in Japanese).
Keigo Kamo, Yuki Kubo, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo,
"Experimental evaluation of joint-diagonalizability-constrained multichannel nonnegative matrix factorization based on multivariate complex sub-Gaussian distribution under variously reverberant conditions,"
Proceedings of 2020 Autumn Meeting of Acoustical Society of Japan, 1-1-8, pp. 147–150, Miyagi, September 2020 (in Japanese).
Shuhei Yamaji and Daichi Kitamura,
"Experimental evaluation of deep permutation solver based on local time-frequency structure,"
Proceedings of 2020 Autumn Meeting of Acoustical Society of Japan, 2-R1-5, pp. 265–268, Miyagi, September 2020 (in Japanese).
Fuga Oshima, Masaki Nakano, and Daichi Kitamura,
"Independent low-rank matrix analysis informed by user annotation,"
Proceedings of 2020 Autumn Meeting of Acoustical Society of Japan, 2-R1-6, pp. 269–272, Miyagi, September 2020 (in Japanese).
Soichiro Oyabu, Daichi Kitamura, and Kohei Yatabe,
"Blind source separation based on exclusive mask obtained by harmonic/percussive source separation,"
Proceedings of 2020 Autumn Meeting of Acoustical Society of Japan, 2-R1-11, pp. 283–286, Miyagi, September 2020 (in Japanese).
Nao Toshima, Daichi Kitamura, and Kohei Yatabe,
"Independent low-rank matrix analysis based on spectrogram consistency,"
Proceedings of 2020 Autumn Meeting of Acoustical Society of Japan, 2-R1-13, pp. 291–294, Miyagi, September 2020 (in Japanese).
Naoki Narisawa, Norihiro Takamune, Daichi Kitamura, Tomohiko Nakamura, and Hiroshi Saruwatari,
"Estimation of frequency-covariance matrix based on multivariate complex Gaussian distribution by deep neural networks for audio source separation,"
Proceedings of 2020 Autumn Meeting of Acoustical Society of Japan, 3-U1-5, pp. 315–318, Miyagi, September 2020 (in Japanese).
Masahiro Kamitaka, Kazuhiko Hayashi, Yuki Hasegawa, Masayuki Matsumoto, Daichi Kitamura, Takashi Yoshioka, and Yoshiki Uno,
"Investigation of quality evaluation for concretes based on impact elastic wave method using impactor,"
Proceedings of Japan Society of Civil Engineers Shikoku Branch 2020 Technical Meeting, jsce7-136-2020, Kagawa, May 2020 (in Japanese).
Shinobu Mukai and Daichi Kitamura,
"Ideathon-based free development training with FPGA in education of logic circuit design,"
Proceedings of Workshop for Experimental Training 2020, P1-05, p. 116, Kagoshima, March 2020 (in Japanese).
Yuta Iwase and Daichi Kitamura,
"Semi-supervised nonnegative matrix factorization with cosine similarity penalty,"
Proceedings of 2020 Spring Meeting of Acoustical Society of Japan, 2-P-39, pp. 425–428, Saitama, September 2019 (in Japanese).
Soichiro Oyabu, Daichi Kitamura, and Kohei Yatabe,
"Linear blind source separation using time-frequency mask obtained by harmonic/percussive source separation,"
Proceedings of 2020 Spring Meeting of Acoustical Society of Japan, 3-1-16, pp. 313–316, Saitama, September 2019 (in Japanese).
Masaki Nakano and Daichi Kitamura,
"Interactive audio source separation informed by user annotation,"
Proceedings of 2020 Spring Meeting of Acoustical Society of Japan, 2-P-38, pp. 421–424, Saitama, September 2019 (in Japanese).
Rui Watanabe and Daichi Kitamura,
"Bandwidth expansion based on deep neural networks for audio source separation,"
Proceedings of 2020 Spring Meeting of Acoustical Society of Japan, 1-1-23, pp. 221–224, Saitama, September 2019 (in Japanese).
Shuhei Yamaji and Daichi Kitamura,
"Deep permutation solver based on local time-frequency structure,"
Proceedings of 2020 Spring Meeting of Acoustical Society of Japan, 3-1-17, pp. 317–320, Saitama, September 2019 (in Japanese).
Naoki Makishima, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo,
"Automatic selection of frequency-wise demixing matrix update rule based on microphone-wise or sourcewise coordinate descent for independent deeply learned matrix analysis,"
Proceedings of 2020 Spring Meeting of Acoustical Society of Japan, 3-1-18, pp. 321–324, Saitama, September 2019 (in Japanese).
Yuki Kubo, Norihiro Takamune, Daichi Kitamura, and Hiroshi Saruwatari,
"Blind multiple directional source separation in diffuse noise environments based on rank-constrained spatial covariance matrix estimation,"
Proceedings of 2020 Spring Meeting of Acoustical Society of Japan, 3-1-13, pp. 301–304, Saitama, September 2019 (in Japanese).
Tatsuki Kondo, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Rintaro Ikeshita, and Tomohiro Nakatani,
"Independent positive semidefinite tensor analysis using tridiagonal frequency-covariance matrix for blind source separation,"
Proceedings of 2020 Spring Meeting of Acoustical Society of Japan, 3-1-11, pp. 293–296, Saitama, September 2019 (in Japanese).
Keigo Kamo, Yuki Kubo, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo,
"Fast multichannel nonnegative matrix factorization with prior distribution of joint-diagonalization matrix for blind source separation,"
Proceedings of 2020 Spring Meeting of Acoustical Society of Japan, 3-1-12, pp. 297–300, Saitama, September 2019 (in Japanese).
Masakzu Une, Yuki Kubo, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, and Shoji Makino,
"Multichannel hearing-aid system biased on basis-shared semi-supervised independent low-rank matrix analysis,"
Proceedings of 2020 Spring Meeting of Acoustical Society of Japan, 1-1-22, pp. 217–220, Saitama, September 2019 (in Japanese).
Kohei Yatabe and Daichi Kitamura,
"HVA: harmonic vector analysis,"
Proceedings of 2020 Spring Meeting of Acoustical Society of Japan, 1-1-16, pp. 199–200, Saitama, September 2019 (in Japanese).
Keigo Kamo, Yuki Kubo, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo,
"Multichannel NMF with joint-diagonalizable constraint based on generalized Gaussian distribution for blind source separation,"
IEICE Technical Report, EA2019-103, vol. 119, no. 439, pp. 13–19, Okinawa, March 2020 (in Japanese).
Yuki Kubo, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari,
"Rank-constrained spatial covariance matrix estimation based on multivariate complex generalized Gaussian distribution and its acceleration for blind speech extraction,"
IEICE Technical Report, EA2019-78, vol. 119, no. 334, pp. 85–92, Fukuoka, December 2019 (in Japanese).
Yuki Kawanabe, Daichi Kitamura, and Takeshi Kakimoto,
"Applying of nonnegative matrix factorization for missing imputation in software development data,"
Proceedings of 26th Special Interest Group on Foundation of Software Engineering (FOSE 2019), pp. 175–176, Gifu, November 2019.
Keigo Kamo, Yuki Kubo, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo,
"FastMNMF based on multivariant complex Student’s t distribution for blind source separation,"
IEICE Technical Report, EA2019-40, vol. 119, no. 253, pp. 23–29, Tokyo, October 2019 (in Japanese).
Naoki Makishima, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo,
"Update of demixing filter based on microphone-wise coordinate descent algorithm for independent deeply learned matrix analysis,"
Proceedings of 2019 Autumn Meeting of Acoustical Society of Japan, 1-1-2, pp. 157–160, Shiga, September 2019 (in Japanese).
Tatsuki Kondo, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Rintaro Ikeshita, and Tomohiro Nakatani,
"Independent positive semidefinite tensor analysis based on multivariate complex Student's t distribution for blind source separation,"
Proceedings of 2019 Autumn Meeting of Acoustical Society of Japan, 1-1-1, pp. 153–156, Shiga, September 2019 (in Japanese).
Yuki Kubo, Norihiro Takamune, Daichi Kitamura, and Hiroshi Saruwatari,
"Acceleration of rank-constrained spatial covariance model estimation by expanding matrix inversion,"
Proceedings of 2019 Autumn Meeting of Acoustical Society of Japan, 1-Q-23, pp. 287–290, Shiga, September 2019 (in Japanese).
Masakazu Une, Yuki Kubo, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, and Shoji Makino,
"Evaluation of multichannel hearing aid system using rank-constrained spatial covariance matrix estimation,"
Proceedings of 2019 Autumn Meeting of Acoustical Society of Japan, 1-1-3, pp. 161–164, Shiga, September 2019 (in Japanese).
Masahiro Kamitaka, Kazuhiko Hayashi, Yuki Hasegawa, Daichi Kitamura, and Yoshiki Uno,
"Propagation velocity estimation of elastic wave in concretes for impact elastic wave method,"
Proceedings of Japan Society of Civil Engineers 2019 Annual Meeting, V-581, Kagawa, September 2019 (in Japanese).
Kanta Fukushige, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Rintaro Ikeshita, and Tomohiro Nakatani,
"Convergence-guaranteed independent positive semidefinite tensor analysis for blind source separation,"
IEICE Technical Report, EA2018-127, vol. 118, no. 496, pp. 167–172, Nagasaki, March 2019 (in Japanese).
Yuki Kubo, Norihiro Takamune, Daichi Kitamura, and Hiroshi Saruwatari,
"Estimation of rank-constrained spatial covariance model based on multivariate complex Student's t-distribution for blind source separation,"
IEICE Technical Report, EA2018-128, vol. 118, no. 496, pp. 173–178, Nagasaki, March 2019 (in Japanese).
Naoki Makishima, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, Kazunobu Kondo, and Hiroaki Nakajima,
"Independent deeply learned matrix analysis based on time-varying complex generalized Gaussian distribution,"
Proceedings of 2019 Spring Meeting of Acoustical Society of Japan, 1-6-7, pp. 189–192, Tokyo, March 2019 (in Japanese).
Yuki Kubo, Norihiro Takamune, Daichi Kitamura, and Hiroshi Saruwatari,
"Estimation of rank-constrained spatial covariance model based on multiplicative update rule,"
Proceedings of 2019 Spring Meeting of Acoustical Society of Japan, 2-6-1, pp. 245–248, Tokyo, March 2019 (in Japanese).
Shinichi Mogami, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, Kazunobu Kondo, and Hiroaki Nakajima,
"Acceleration of independent low-rank matrix analysis based on generalized Gaussian distribution using majorization-equalization algorithm,"
Proceedings of 2019 Spring Meeting of Acoustical Society of Japan, 2-6-2, pp. 249–252, Tokyo, March 2019 (in Japanese).
Kohei Yatabe and Daichi Kitamura,
"Sparse independent vector analysis considering side effect of whitening,"
Proceedings of 2019 Spring Meeting of Acoustical Society of Japan, 2-6-5, pp. 259–260, Tokyo, March 2019 (in Japanese).
Naoki Makishima, Shinichi Mogami, Norihiro Takamune, Shinnosuke Takamichi, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, Kazunobu Kondo, and Hiroaki Nakajima,
"Experimental evaluation of independent deeply learned matrix analysis under supervised and semi-supervised conditions,"
Proceedings of 2019 Spring Meeting of Acoustical Society of Japan, 2-Q-28, pp. 385–388, Tokyo, March 2019 (in Japanese).
Naoki Makishima, Shinichi Mogami, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, Kazunobu Kondo, and Hiroaki Nakajima,
"Multichannel audio source separation using independent deeply learned matrix analysis based on heavy-tailed generative model,"
Proceedings of 33th Signal Processing Symposium (SIP Symposium), B2-3, pp. 202–207, Tokyo, November 2018 (in Japanese).
(Paper)
Shinnosuke Takamichi, Yuki Saito, Norihiro Takamune, Daichi Kitamura, and Hiroshi Saruwatari,
"Phase reconstruction from amplitude spectrograms based on directional-statistics DNNs,"
Proceedings of 2018 Autumn Meeting of Acoustical Society of Japan, 2-4-2, pp. 1127–1130, Oita, September 2018 (in Japanese).
Shinichi Mogami, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, Kazunobu Kondo, Hiroaki Nakajima, and Nobutaka Ono,
"Time-variant sub-Gaussian independent low-rank matrix analysis based on generalized iterative projection,"
Proceedings of 2018 Autumn Meeting of Acoustical Society of Japan, 3-1-10, pp. 215–218, Oita, September 2018 (in Japanese).
Yuki Kubo, Norihiro Takamune, Daichi Kitamura, and Hiroshi Saruwatari,
"Blind source separation based on full-rank spatial covariance model using independent low-rank matrix analysis,"
Proceedings of 2018 Autumn Meeting of Acoustical Society of Japan, 3-1-9, pp. 211–214, Oita, September 2018 (in Japanese).
Naoki Makishima, Norihiro Takamune, Shinnosuke Takamichi, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, Kazunobu Kondo, and Hiroaki Nakajima,
"Source model adaptation based on data augmentation in semi-supervised independent deeply learned matrix analysis,"
Proceedings of 2018 Autumn Meeting of Acoustical Society of Japan, 2-1-8, pp. 181–184, Oita, September 2018 (in Japanese).
Kohei Yatabe and Daichi Kitamura,
"Independent vector analysis based on general time-frequency masking,"
Proceedings of 2018 Autumn Meeting of Acoustical Society of Japan, 3-1-11, pp. 219–220, Oita, September 2018 (in Japanese).
Akihito Aiba, Minoru Yoshida, Satoru Goto, Daichi Kitamura, Shinnosuke Takamichi, and Hiroshi Saruwatari,
"NMF source extraction as pre-processing of anomaly detection under the noise environment,"
Proceedings of 119th IPSJ Special Interest Group on Music and Computer (IPSJ-SIGMUS), vol. 2018-MUS-119, no. 33, Tokyo, Jun 2018 (in Japanese).
Shinnosuke Takamichi, Yuki Saito, Norihiro Takamune, Daichi Kitamura, and Hiroshi Saruwatari,
"Phase reconstruction from amplitude spectrograms based on von-Mises-distribution DNN,"
Proceedings of 119th IPSJ Special Interest Group on Music and Computer (IPSJ-SIGMUS), vol. 2018-MUS-119, no. 54, Tokyo, Jun 2018 (in Japanese).
Daichi Kitamura, Hayato Sumino, Norihiro Takamune, Shinnosuke Takamichi, Hiroshi Saruwatari, and Nobutaka Ono,
"Experimental evaluation of multichannel audio source separation based on IDLMA,"
IEICE Technical Report, EA2017-104, vol. 117, no. 515, pp. 13–20, Okinawa, March 2018 (in Japanese).
(PDF, IEICE Transactions Online, Copyright (c) 2017 IEICE, Slide)
Daichi Kitamura, Norihiro Takamune, Shinichi Mogami, Yoshiki Mitsui, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo,
"Sparse noise reduction using nonnegative matrix factorization based on heavy-tailed distributions,"
Proceedings of 2018 Spring Meeting of Acoustical Society of Japan, 1-4-14, pp. 441–444, Saitama, March 2018 (in Japanese).
(Slide)
Hayato Sumino, Daichi Kitamura, Norihiro Takamune, Shinnosuke Takamichi, Hiroshi Saruwatari, and Nobutaka Ono,
"Multichannel audio source separation based on independent deeply learned matrix analysis,"
Proceedings of 2018 Spring Meeting of Acoustical Society of Japan, 1-4-16, pp. 449–452, Saitama, March 2018 (in Japanese).
Yoshiki Mitsui, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, Kazunobu Kondo, and Hiroaki Nakajima,
"Blind source separation based on independent low-rank matrix analysis with spatial-model-based regularization,"
Proceedings of 2018 Spring Meeting of Acoustical Society of Japan, 1-4-15, pp. 445–448, Saitama, March 2018 (in Japanese).
Kohei Yatabe and Daichi Kitamura,
"Blind source separation via proximal splitting algorithm,"
Proceedings of 2018 Spring Meeting of Acoustical Society of Japan, 1-4-10, pp. 431–434, Saitama, March 2018 (in Japanese).
(Slide)
Shinichi Mogami, Yoshiki Mitsui, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, Kazunobu Kondo, Hiroaki Nakajima, and Hirokazu Kameoka,
"Experimental evaluation of independent low-rank matrix analysis based on I divergence,"
Proceedings of 2018 Spring Meeting of Acoustical Society of Japan, 1-4-8, pp. 423–426, Saitama, March 2018 (in Japanese).
Masakazu Une, Yuki Saito, Shinnosuke Takamichi, Daichi Kitamura, Ryoichi Miyazaki, and Hiroshi Saruwatari,
"Generative approach using the noise generation models for DNN-based speech synthesis trained from noisy speech,"
Proceedings of 2018 Spring Meeting of Acoustical Society of Japan, 3-8-8, pp. 243–244, Saitama, March 2018.
Shinichi Mogami, Yoshiki Mitsui, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo,
"ILRMA using I divergence criterion,"
Proceedings of 32th Signal Processing Symposium (SIP Symposium), B8-1, pp. 354–359, Iwate, November 2017 (in Japanese).
(Paper)
Yoshiki Mitsui, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo,
"ILRMA incorporating with a priori spatial information,"
Proceedings of 32th Signal Processing Symposium (SIP Symposium), B8-2, pp. 360–365, Iwate, November 2017 (in Japanese).
(Paper)
Daichi Kitamura, Nobutaka Ono, Hiroshi Sawada, Hirokazu Kameoka, and Hiroshi Saruwatari,
"Blind source separation based on independent low-rank matrix analysis,"
IEICE Technical Report, EA2017-56, vol. 117, no. 255, pp. 73–80, Toyama, October 2017 (in Japanese, Invited talk).
(PDF, IEICE Transactions Online, Copyright (c) 2017 IEICE, Slide)
Masakazu Une, Yuki Saito, Shinnosuke Takamichi, Daichi Kitamura, Ryoichi Miyazaki, and Hiroshi Saruwatari,
"Generative adversarial training of the noise generation model for speech synthesis using speech in noise,"
IPSJ SIG Technical Report, 2017-SLP-118, no. 1, pp. 1–6, October 2017 (in Japanese).
Yoshiki Mitsui, Daichi Kitamura, Norihiro Takamune, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo,
"Blind source separation based on independent low-rank matrix analysis with parametric auxiliary function method,"
Proceedings of 2017 Autumn Meeting of Acoustical Society of Japan, 3-12-13, pp. 519–522, Ehime, September 2017 (in Japanese).
Shinichi Mogami, Daichi Kitamura, Norihiro Takamune, Yoshiki Mitsui, Hiroshi Saruwatari, Nobutaka Ono, Yu Takahashi, and Kazunobu Kondo,
"Experimental evaluation of independent low-tank matrix analysis based on complex Student's t-distribution,"
Proceedings of 2017 Autumn Meeting of Acoustical Society of Japan, 3-12-12, pp. 515–518, Ehime, September 2017 (in Japanese).
Shinichi Mogami, Daichi Kitamura, Norihiro Takamune, Yoshiki Mitsui, Hiroshi Saruwatari, Nobutaka Ono, Yu Takahashi, and Kazunobu Kondo,
"ILRMA with complex Student's t source model,"
IEICE Technical Report, EA2017-23, vol. 117, no. 138, pp. 131–136, Hokkaido, July 2017 (in Japanese).
Norihiro Takamune, Daichi Kitamura, Nobutaka Ono, and Hiroshi Saruwatari,
"Fast optimization in Cauchy NMF Based on a new auxiliary function,"
Proceedings of 115th IPSJ Special Interest Group on Music and Computer (IPSJ-SIGMUS), vol. 2017-MUS-115, no. 48, Tokyo, June 2017 (in Japanese).
Yoshiki Mitsui, Satoshi Mizoguchi, Hiroshi Saruwatari, Daichi Kitamura, Nobutaka Ono, Masaru Ishimura, Narumi Mae, Moe Takakusaki, Yutaro Matsui, Kouei Yamaoka, and Shoji Makino,
"Development of high quality blind source separation based on independent low-rank matrix analysis and statistical speech enhancement for flexible hose-shaped robot,"
Proceedings of The 2016 JSME Conference on Robotics and Mechatronics (ROBOMECH 2017), no. 17-2, 1P2-P04, Fukushima, May 2017 (in Japanese).
Yoshiki Mitsui, Satoshi Mizoguchi, Hiroshi Saruwatari, Daichi Kitamura, Nobutaka Ono, Masaru Ishimura, Narumi Mae, Moe Takakusaki, Yutaro Matsui, Kouei Yamaoka, and Shoji Makino,
"Development of blind source separation system for flexible hose-shaped robot using independent low-rank matrix analysis and statistical speech enhancement,"
Proceedings of 2017 Spring Meeting of Acoustical Society of Japan, 1-P-3, pp. 517–518, Kanagawa, March 2017 (in Japanese).
Yoshiki Mitsui, Daichi Kitamura, Shinnosuke Takamichi, Nobutaka Ono, and Hiroshi Saruwatari,
"Study on efficient solver for independent low-rank matrix analysis with sparse time-series-activity regularization,"
IEICE Technical Report, EA2016-72, vol. 116, no. 420, pp. 25--30, Kyoto, January 2017 (in Japanese).
Yoshiki Mitsui, Daichi Kitamura, Shinnosuke Takamichi, and Hiroshi Saruwatari,
"Blind source separation using independent low-rank matrix analysis with sparse regularization for time-series activations,"
Proceedings of 2016 Autumn Meeting of Acoustical Society of Japan, 1-7-3, pp. 325–328, Toyama, September 2016 (in Japanese).
(J-GLOBAL, PDF)
Moe Takakusaki, Daichi Kitamura, Nobutaka Ono, Takeshi Yamada, Shoji Makino, and Hiroshi Saruwatari,
"Noise reduction for a hose-shaped rescue robot using rank-1 multichannel NMF,"
Proceedings of The 2016 JSME Conference on Robotics and Mechatronics (ROBOMECH 2016), no. 16-2, 1A2-10a3, Kanagawa, June 2016 (in Japanese).
Daichi Kitamura, Nobutaka Ono, Hiroshi Saruwatari, Yu Takahashi, and Kazunobu Kondo,
"Effective basis learning for sound source separation by semi-supervised nonnegative matrix factorization,"
IEICE Technical Report, EA2015-130, vol. 115, no. 521, pp. 355–360, Oita, March 2016 (in Japanese).
(CiNii, Slide)
Moe Takakusaki, Daichi Kitamura, Nobutaka Ono, Takeshi Yamada, Shoji Makino, and Hiroshi Saruwatari,
"Noise reduction using rank-1 multichannel NMF for a hose-shaped rescue robot,"
Proceedings of 2016 IEICE General Conference, A-5-1, Fukuoka, March 2016 (in Japanese).
(CiNii)
Daichi Kitamura and Nobutaka Ono,
"Statistical-independence-based effective initialization for nonnegative matrix factorization,"
Proceedings of 2016 Spring Meeting of Acoustical Society of Japan, 3-3-5, pp. 619–622, Kanagawa, March 2016 (in Japanese).
(J-GLOBAL, PDF, Slide)
Kazuma Takata, Daichi Kitamura, Hiroaki Nakajima, Shoichi Koyama, Hiroshi Saruwatari, Nobutaka Ono, and Shoji Makino,
"Source separation with supervised multichannel NMF and statistical speech enhancement method for hose-shaped rescue robot,"
Proceedings of 2016 Spring Meeting of Acoustical Society of Japan, 3-3-2, pp. 609–612, Kanagawa, March 2016 (in Japanese).
(J-GLOBAL, PDF)
Hiroaki Nakajima, Daichi Kitamura, Norihiro Takamune, Shoichi Koyama, Hiroshi Saruwatari, Nobutaka Ono, Yu Takahashi, and Kazunobu Kondo,
"Music signal separation using supervised NMF with time-valiant all-pole-model-based basis deformation,"
Proceedings of 2016 Spring Meeting of Acoustical Society of Japan, 3-3-11, pp. 635–638, Kanagawa, March 2016 (in Japanese).
(J-GLOBAL, PDF)
Hiroaki Nakajima, Daichi Kitamura, Norihiro Takamune, Shoichi Koyama, Hiroshi Saruwatari, Nobutaka Ono, Yu Takahashi, and Kazunobu Kondo,
"Analysis on degree of freedom for supervised NMF with all-pole-model-based basis deformation,"
IEICE Technical Report, EA2015-42, vol. 115, no. 359, pp. 13–18, Kanazawa, December 2015 (in Japanese).
(CiNii, Poster)
Daichi Kitamura, Hiroshi Saruwatari, Nobutaka Ono, Hiroshi Sawada, and Hirokazu Kameoka,
"Study on source and spatial models for BSS with rank-1 spatial approximation,"
Proceedings of 2015 Autumn Meeting of Acoustical Society of Japan, 3-6-10, pp. 583–586, Fukushima, September 2015 (in Japanese).
(J-GLOBAL, PDF, Slide)
Hiroaki Nakajima, Daichi Kitamura, Norihiro Takamune, Shoichi Koyama, Hiroshi Saruwatari, Nobutaka Ono, Yu Takahashi, and Kazunobu Kondo,
"Music signal separation using supervised NMF with all-pole-model-based basis deformation,"
Proceedings of 2015 Autumn Meeting of Acoustical Society of Japan, 3-6-7, pp. 573–576, Fukushima, September 2015 (in Japanese, ASJ Student Presentation Award).
(J-GLOBAL, PDF)
Daichi Kitamura, Nobutaka Ono, Hiroshi Sawada, Hirokazu Kameoka, and Hiroshi Saruwatari,
"Performance evaluation of source separation in multichannel nonnegative matrix factorization with rank-1 spatial model,"
Proceedings of 107th IPSJ Special Interest Group on Music and Computer (IPSJ-SIGMUS), vol. 2015-MUS-107, no. 31, Tokyo, May 2015 (in Japanese).
(IPSJ, Poster)
Daichi Kitamura, Nobutaka Ono, Hiroshi Sawada, Hirokazu Kameoka, and Hiroshi Saruwatari,
"Relaxation of rank-1 spatial model in overdetermined BSS,"
Proceedings of 2015 Spring Meeting of Acoustical Society of Japan, 3-10-11, pp. 629–632, Tokyo, March 2015 (in Japanese).
(J-GLOBAL, PDF, Slide)
Yuki Murota, Daichi Kitamura, Shoichi Koyama, Hiroshi Saruwatari, and Satoshi Nakamura,
"Experimental evaluation of simultaneous adaption method of time-series a priori statistical model and spectral basis for binaural source separation,"
Proceedings of 2015 Spring Meeting of Acoustical Society of Japan, 1-10-12, pp. 549–552, Tokyo, March 2015 (in Japanese).
(J-GLOBAL, PDF)
Yuki Murota, Daichi Kitamura, Shoichi Koyama, Hiroshi Saruwatari, and Satoshi Nakamura,
"Simultaneous adaptation of time-series a priori statistical model and spectral basis for binaural source separation,"
IEICE Technical Report, EA2014-64, vol. 114, no. 423, pp. 27–32, Kyoto, January 2015 (in Japanese).
(CiNii)
Yuki Murota, Daichi Kitamura, Shoichi Koyama, Hiroshi Saruwatari, and Satoshi Nakamura,
"Localization-preserved binaural source separation using channel-wise target prior estimation and equi-binaural spectral gain,"
Proceedings of 29th Signal Processing Symposium (SIP Symposium), P5-6, pp. 486–491, Kyoto, November 2014.
(Paper)
Daichi Kitamura, Nobutaka Ono, Hiroshi Sawada, Hirokazu Kameoka, and Hiroshi Saruwatari,
"Efficient multichannel nonnegative matrix factorization with rank-1 spatial model,"
Proceedings of 2014 Autumn Meeting of Acoustical Society of Japan, 2-1-11, pp. 579–582, Hokkaido, September 2014 (in Japanese, ASJ Awaya Prize Young Researcher Award).
(J-GLOBAL, PDF, Slide)
Yuki Murota, Daichi Kitamura, Shoichi Koyama, Hiroshi Saruwatari, and Satoshi Nakamura,
"Study on a priori statistical model of target signal for binaural signal source separation,"
Proceedings of 2014 Autumn Meeting of Acoustical Society of Japan, 1-1-3, pp. 595–598, Hokkaido, September 2014 (in Japanese, ASJ Student Presentation Award).
(J-GLOBAL, PDF)
Daichi Kitamura, Hiroshi Saruwatari, Satoshi Nakamura, Yu Takahashi, Kazunobu Kondo, and Hirokazu Kameoka,
"Experimental evaluation of superresolution-based nonnegative matrix factorization for binaural recording,"
Proceedings of 103th IPSJ Special Interest Group on Music and Computer (IPSJ-SIGMUS), vol. 2014-MUS-103, no. 38, Tokyo, May 2014.
(IPSJ, Poster)
Daichi Kitamura, Hiroshi Saruwatari, Satoshi Nakamura, Kazunobu Kondo, Yu Takahashi, and Hirokazu Kameoka,
"Optimal divergence diversity for superresolution-based nonnegative matrix factorization,"
Proceedings of 2014 Spring Meeting of Acoustical Society of Japan, 3-2-9, pp. 727–730, Tokyo, March 2014.
(J-GLOBAL, PDF, Slide)
Tomo Miyauchi, Daichi Kitamura, Hiroshi Saruwatari, and Satoshi Nakamura,
"Depth estimation of sound images using direction of arrival distribution and activation-shared nonnegative matrix factorization,"
Proceedings of 2014 Spring Meeting of Acoustical Society of Japan, 1-1-5, pp. 947–950, Tokyo, March 2014 (ASJ Student Presentation Award).
(J-GLOBAL, PDF)
Yuki Murota, Daichi Kitamura, Shunsuke Nakai, Hiroshi Saruwatari, Satoshi Nakamura, Yu Takahashi, and Kazunobu Kondo,
"Experimental evaluation of postfilter-based nonnegative matrix factorization with statistical model parameter estimation,"
Proceedings of 2014 Spring Meeting of Acoustical Society of Japan, 2-1-5, pp. 677–680, Tokyo, March 2014.
(J-GLOBAL, PDF)
Tomo Miyauchi, Daichi Kitamura, Hiroshi Saruwatari, and Satoshi Nakamura,
"Depth estimation of sound images in mixed source using activation-shared nonnegative matrix factorization,"
IEICE Technical Report, EA2013-117, vol. 113, no. 413, pp. 81–86, Osaka, January 2014 (in Japanese).
(CiNii)
Yuki Murota, Daichi Kitamura, Shunsuke Nakai, Hiroshi Saruwatari, Satoshi Nakamura, Yu Takahashi, and Kazunobu Kondo,
"Postfilter-based nonnegative matrix factorization with statistical model parameter estimation,"
IEICE Technical Report, EA2013-116, vol. 113, no. 413, pp. 75–80, Osaka, January 2014.
(CiNii)
Daichi Kitamura, Hiroshi Saruwatari, Kosuke Yagi, Kiyohiro Shikano, Yu Takahashi, and Kazunobu Kondo,
"Music signal separation using supervised nonnegative matrix factorization with orthogonality and maximum-divergence penalties,"
Proceedings of 28th Signal Processing Symposium (SIP Symposium), C1-4, pp. 539–544, Yamaguchi, November 2013 (SIP Young Researcher's Award).
(Slide)
Daichi Kitamura, Hiroshi Saruwatari, Satoshi Nakamura, Kazunobu Kondo, and Yu Takahashi,
"Divergence optimization based on trade-off between separation and extrapolation abilities in superresolution-based nonnegative matrix factorization,"
Proceedings of 2013 Autumn Meeting of Acoustical Society of Japan, 1-1-6, pp. 583–586, Aichi, September 2013 (ASJ Student Presentation Award).
(J-GLOBAL, PDF, Slide)
Tomo Miyauchi, Daichi Kitamura, Hiroshi Saruwatari, and Satoshi Nakamura,
"Automatic depth estimation of sound images using directional clustering and nonnegative matrix factorization,"
Proceedings of 2013 Autumn Meeting of Acoustical Society of Japan, 2-1-19, pp. 673–676, Aichi, September 2013 (in Japanese).
(J-GLOBAL, PDF, Slide)
Daichi Kitamura, Hiroshi Saruwatari, Kiyohiro Shikano, Kazunobu Kondo, and Yu Takahashi,
"Study on optimal divergence for superresolution-based supervised nonnegative matrix factorization,"
IEICE Technical Report, EA2013-14, vol. 113, no. 27, pp. 79–84, Okayama, May 2013.
(CiNii, Slide)
Daichi Kitamura, Hiroshi Saruwatari, Kiyohiro Shikano, Kazunobu Kondo, and Yu Takahashi,
"Importance of regularization in superresolution-based multichannel signal separation with nonnegative matrix factorization,"
Proceedings of 99th IPSJ Special Interest Group on Music and Computer (IPSJ-SIGMUS), vol. 2013-MUS-99, no. 14, pp. 1–6, Tokyo, May 2013 (in Japanese).
(IPSJ, Poster)
Daichi Kitamura, Hiroshi Saruwatari, Kiyohiro Shikano, Kazunobu Kondo, and Yu Takahashi,
"Evaluation of separation accuracy for various real instruments based on supervised NMF with basis deformation,"
Proceedings of 2013 Spring Meeting of Acoustical Society of Japan, 3-1-11, pp. 1057–1060, Tokyo, March 2013.
(J-GLOBAL, PDF, Slide)
Daichi Kitamura, Hiroshi Saruwatari, Kiyohiro Shikano, Kazunobu Kondo, and Yu Takahashi,
"Signal Separation for real instruments based on supervised NMF with basis deformation,"
IEICE Technical Report, EA2012-121, vol. 112, no. 388, pp. 13–18, Kyoto, January 2013 (in Japanese).
(CiNii, Slide)
Daichi Kitamura and Masahiro Harazono,
"String vibration response of improvised hum-backing pickup,"
Proceedings of the IEICE General Conference, vol. 2011, A-10-6, p. 170, Tokyo, March 2011 (in Japanese).
(CiNii, Slide)
Daichi Kitamura and Masahiro Harazono,
"String vibration response of pseudo hum-backing pickup,"
Proceedings of the 2010 IEICE Shikoku Section Convention Record, vol. 2010, 16-13, Ehime, September 2010 (in Japanese).
(J-GLOBAL, Slide)
Daichi Kitamura and Masahiro Harazono,
"Simulation of electric guitar response,"
Proceedings of the 2010 IEICE Shikoku Section Convention Record, vol. 2009, 16-5, Ehime, September 2009 (in Japanese, IEICE Shikoku Section Convention Encouragement Award).
(J-GLOBAL, Slide)
Patents
Patent pending
Patent pending
Daichi Kitamura, Hiroaki Nakajima, Hiroshi Saruwatari, Nobutaka Ono, Yu Takahashi, Kazunobu Kondo, "音信号処理方法および音信号処理装置," Japanese Unexamined Patent, Application No. 2016-032489 (submitted on February 23rd, 2016), and Publication No. 2017-151228 (published on August 31st, 2017).
Daichi Kitamura, Hiroshi Saruwatari, and Yu Takahashi, "音響処理装置," Japanese Unexamined Patent, Application No. 2013-094475 (submitted on April 26th, 2013), and Publication No. 2014-215544 (published on November 17th, 2014).
(J-GLOBAL)
Daichi Kitamura, Hiroshi Saruwatari, and Yu Takahashi, "音響解析装置," Japanese Unexamined Patent, Application No. 2013-004375 (submitted on January 15th, 2013), and Publication No. 2014-137389 (published on July 28th, 2014).
(J-GLOBAL)
Miscellaneous Works
Hiroshi Sawada, Nobutaka Ono, Hirokazu Kameoka, and Daichi Kitamura,
"T-1 Blind audio source separation on tensor representation,"
2018 IEEE International Conference on Acoustics, Speech and Signal Processing, April 16th, 2018.
(HP)
Daichi Kitamura,
"Blind source separation based on independent low-rank matrix analysis and its extensions,"
Ohio State University, Invited Lecture, December 15th, 2017.
(Slide)
Daichi Kitamura,
"Dataset: songKitamura,"
Dataset for Evaluation of Music Source Separation, October 13th, 2017.
(Details)
Daichi Kitamura,
"Acoustic modeling in audio source separation,"
The Acoustical Society of Japan, Summer Seminar, Invited Talk, September 11th, 2017.
(Slide)
Daichi Kitamura,
"Blind source separation based on independent low-rank matrix analysis and its extension to Student's t-distribution,"
Télécom ParisTech, Invited Lecture, September 4th, 2017.
(Slide)
Daichi Kitamura,
"Q. Why does a pickup affect on the tone of electric guitars?,"
The Journal of the Acoustical Society of Japan (ASJ), Coffee Break, Q&A Corner, vol. 73, no. 9, September 2017 (in Japanese).
Daichi Kitamura,
"Audio source separation based on low-rank structure and statistical independence,"
Nagoya University, Invited Lecture, May 30th, 2017.
(Slide)
Daichi Kitamura,
"Effective optimization algorithms for blind and supervised music source separation with nonnegative matrix factorization,"
SOKENDAI (The Graduate University for Advanced Studies), Doctoral Dissertation, March 2017 (SOKENDAI, Nagakura Research Incentive Award).
(PDF)
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, Invited Talk, Tokyo, February 27th, 2017.
(Slide)
Daichi Kitamura,
"Blind source separation based on statistical independence and low-rank matrix decomposition –Independent low-rank matrix analysis–,"
University of Tsukuba, Graduate School of Systems and Information Engineering, Multimedia Laboratory, Invited Talk, Ibaraki, September 26th, 2016.
(Slide)
Daichi Kitamura,
"Algorithms for independent low-rank matrix analysis,"
Supporting document, August 2016 (PDF).
Daichi Kitamura,
"Blind music separation based on independent low-rank matrix analysis,"
Speech PhD Summit 2016, Google Inc., Invited Talk, London, UK, June 15th, 2016.
Daichi Kitamura and Nobutaka Ono,
"How can we listen only vocal or guitar sound from music? Mechanism in source separation and its capability,"
2016 National Institute of Informatics (NII) Open House, no. E02, Tokyo, May 2016.
Daichi Kitamura,
"History of independent component analysis for sound media signal processing and its applications,"
Hitotsubashi University, Graduate School of International Corporate Strategy, MBA Program in Financial Strategy, Faculty Seminar, Invited Talk, Tokyo, February 8th, 2016.
(HP, Slide)
Daichi Kitamura,
"Sound media signal processing for music,"
7th Hokuriku Union Acoustic Seminar, Beginner's Meeting, Invited Talk, Ishikawa, December 13th, 2015.
(HP)
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 24th, 2015.
(Slide)
Daichi Kitamura, Nobutaka Ono, Hiroshi Sawada, Hirokazu Kameoka, and Hiroshi Saruwatari,
"How can we listen only vocal or guitar sound from music? Music source separation using nonnegative matrix factorization,"
2015 National Institute of Informatics (NII) Open House, no. E02, Tokyo, June 2015.
(Poster)
Daichi Kitamura,
"Music signal separation combining directional clustering and nonnegative matrix factorization with spectrogram restoration,"
Nara Institute of Science and Technology, Master Thesis, March 2014.
(PDF)