© 2015 - 2019 by Christopher Kissel. Proudly created with Wix.com

  • Twitter
  • Facebook Social Icon

RESEARCH [D]

Scroll down to find direct links to publicly posted research papers, presentations, etc. in the field of sound source separation and related topics.  I have listed them in alphabetical order by title for ease of browsing and have provided these links, which are available on the web, for your convenience.  I have provided permalinks for those papers available for a fee.  Titles without a link can be found through a web search.  Please use the CONTACT page to notify me of any corrections, to supply suggestions for adding any additional pertinent links, or to notify me if you encounter any dead links in this list.  Thanks!

 

 

DECOMPOSITION OF MONAURAL SOUND WITH UNKNOWN NUMBER OF SOURCES [permalink]

T. Murayama and S. Hashimoto (2006)

 

DEEP CLUSTERING AND CONVENTIONAL NETWORKS FOR MUSIC SEPARATION: STRONGER TOGETHER

Yi Luo, Zhuo Chen, John R. Hershey, Jonathan Le Roux, Nima Mesgarani (2016)

DEEP CLUSTERING AND CONVENTIONAL NETWORKS FOR MUSIC SEPARATION: STRONG TOGETHER [PDF]

Luo, Y.; Chen, Z.; Hershey, J.R.; Le Roux, J.; Mesgarani, N., Mitsubishi Electric Research Laboratories, Cambridge, Massachusetts (2017)

DEEP CLUSTERING: DISCRIMINATIVE EMBEDDINGS FOR SEGMENTATION AND SEPARATION [PDF]

John R. Hershey, MERL, Cambridge, Massachusetts, Jonathan Le Roux, MERL, Cambridge, Massachusetts, Zhuo Chen, Columbia University, New York, New York, Shinji Watanabe, MERL, Cambridge, Massachusetts (2015)

 

DEEP CLUSTERING: DISCRIMINATIVE EMBEDDINGS FOR SEGMENTATION AND SEPARATION (video)

John R. Hershey, MERL, Cambridge, Massachusetts (2016)

DEEP FACTORIZED AND VARIATIONAL LEARNING FOR SOURCE SEPARATION [permalink]

Kuan-Ting Kuo, National Chiao Tung University (2016)

DEEP KARAOKE: EXTRACTING VOCALS FROM MUSICAL MIXTURES USING A CONVOLUTIONAL DEEP NEURAL NETWORK [PDF]

Andrew J.R. Simpson , Gerard Roma , Mark D. Plumbley, Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK (2015)

 

DEEP LEARNING FOR MONAURAL SOURCE SEPARATION (video)

 

DEEP LEARNING FOR MONAURAL SPEECH SEPARATION [PDF]

Po-Sen Huang, Minje Kim, Mark Hasegawa-Johnson, Paris Smaragdis (2014)

 

DEEP LEARNING FOR MONAURAL SPEECH SEPARATION (web page)
Po-Sen Huang, Minje Kim, Mark Hasegawa-Johnson, Paris Smaragdis (2014)

 

DEEP LEARNING FOR MUSIC DATA PROCESSING: A PERSONAL (RE)VIEW OF THE STATE-OF-THE-ART (presentation) [PDF]

Jordi Pons, Music Technology Group, DTIC, Universitat Pompeu Fabra, Barcelona (2017)

DEEP LEARNING MACHINE SOLVES THE COCKTAIL PARTY PROBLEM

Emerging Technology From the arXiv (2015)

 

DEEP LEARNING PROJECT: GROUP 7 (presentation) [PDF]

Alex Holston and Bárður Ísleifsson, School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea, Byunghyun Ban, Bio and Brain Engineering, Systems Biology and Inspired Engineering Laboratory, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea (2016)

DEEP NEURAL NETWORK BASED INSTRUMENT EXTRACTION FROM MUSIC [permalink]

Stefan Uhlich, Franck Giron, Yuki Mitsufuji, Sony Eur. Technol. Center (EuTEC), Stuttgart, Germany (2015)

 

DEEP NEURAL NETWORK FOR MUSIC SOURCE SEPARATION IN TENSORFLOW

Mark Kwon (Co-author), Jeju Machine Learning Camp 2017 (2017)

DEEP NEURAL NETWORKS FOR SINGLE CHANNEL SOURCE SEPARATION [PDF]

Emad M. Grais, Mehmet Umut Sen, Hakan Erdogan, Faculty of Engineering and Natural Sciences, Sabanci University, Orhanli Tuzla, Istanbul (2013)

 

DEEP RECURRENT NEURAL NETWORK BASED MONAURAL SPEECH SEPARATION USING RECURRENT TEMPORAL RESTRICTED BOLTZMANN MACHINES [PDF]

Suman Samui, Indrajit Chakrabarti, Soumya K Ghosh, Indian Institute of Technology, Kharagpur, India (2017)

DEEP RECURRENT NEURAL NETWORK FOR AUDIO SOURCE SEPARATION (MATLAB IMPLEMENTATION)

jordipons, Music Technology Group - UPF, Barcelona, Spain (2016)

 

DEEP REMIX: REMIXING MUSICAL MIXTURES USING A CONVOLUTIONAL DEEP NEURAL NETWORK [PDF]

Andrew J.R. Simpson , Gerard Roma , Mark D. Plumbley, Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK (2015)

 

DEEP REPRESENTATION-DECOUPLING NEURAL NETWORKS FOR MONAURAL MUSIC MIXTURE SEPARATION [PDF]

Zhuo Li1, Hongwei Wang2, Miao Zhao1, Wenjie Li1 and Mini Guo2, 1The Hong Kong Polytechnic University, 2Shanghai Jiao Tong University (2018)

DEEP TRANSFORM: COCKTAIL PARTY SOURCE SEPARATION VIA COMPLEX CONVOLUTION IN A DEEP NEURAL NETWORK [PDF]

Andrew J.R. Simpson, Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK (2015)

 

DEEP TRANSFORM: COCKTAIL PARTY SOURCE SEPARATION VIA PROBABILISTIC RE-SYNTHESIS [PDF]

Andrew J.R. Simpson, Centre for Vision, Speech and Signal Processing, Surrey University, Surrey, UK (2015)

 

DEMIXING COMMERCIAL MUSIC PRODUCTIONS VIA HUMAN-ASSISTED TIME-FREQUENCY MASKING [permalink]

MarC Vinyes, Jordi Bonada, Alex Loscos, Pompeu Fabra University, Audiovisual Institute, Music Technology Group, Barcelona, Spain (2006)

 

DEMIXING COMMERCIAL MUSIC PRODUCTIONS VIA HUMAN-ASSISTED TIME-FREQUENCY MASKING (slides) [PDF]
MarC Vinyes, Jordi Bonada, Alex Loscos, Pompeu Fabra University, Audiovisual Institute, Music Technology Group, Barcelona, Spain (2006)

DEMIXING PROFESSIONALLY PRODUCED MUSIC

SiSEC MUS 2016 (2016)

DEMO AUDIO CLIPS OF HARMONIC-PERCUSSIVE SOUND SEPARATION METHODS

Music and Audio Research Group, Seoul National University, Yeongtong-gu, Suwon-si, Gyeonggi-do, Republic of Korea (2014)

DEMUCS: DEEP EXTRACTOR FOR MUSIC SOURCES WITH EXTRA UNLABELED DATA REMIXED [PDF]

Alexandre Défaussez, Facebook AI Research, INRIA / École Normale Supérieure, PSL Research University, Paris, France, Nicolas Usunier, Facebook AI Research, Paris, France, Léon Bottou, Facebook AI Research, New York, USA, Francis Bach, INRIA / École Normale Supérieure, PSL Research University, Paris, France (2019)

DENOISING AUTO-ENCODER WITH RECURRENT SKIP CONNECTIONS AND RESIDUAL REGRESSION FOR MUSIC SOURCE SEPARATION [PDF]

Jen-Yu Liu, Yi-Hsuan Yang, Research Center for IT Innovation, Academia Sinica, Taipei, Taiwan (2018)

DEPLOYING NONLINEAR IMAGE FILTERS TO SPECTROGRAM FOR HARMONIC/PERCUSSIVE SEPARATION [PDF]

Aggelos Gkiokas, Institute for Language and Speech Processing / “R.C. Athena”, National Technical University of Athens Athens, Greece, Vassilis Katsouros, Institute for Language and Speech Processing / “R.C. Athena”, Athens, Greece, Vassilis Papavassiliou, Institute for Language and Speech Processing / “R.C. Athena”, George Carayannis, National Technical University of Athens Athens, Greece (2012)

DESIGN OF A CONVOLUTIONAL NEURAL NETWORK FOR SEPARATING SINGING VOICE FROM MONAURAL POP MUSIC [PDF]

Kin Wah, Edward Lin. Enyan Koh, David Grunberg, Simon Lui, Information Systems Technology and Design, Singapore University of Technology and Design, Singapore (2017)

DESOLOING MONAURAL AUDIO USING MIXTURE MODELS [PDF]

Yushen Han, Christopher Raphael, School of Informatics, Indiana University (2007)

 

DETAILED GRAPHICAL MODELS FOR SOURCE SEPARATION AND MISSING DATA INTERPOLATION IN AUDIO [PDF]

Manuel J. Reyes-Gomez 1, Nebojsa Jojic 2 and Daniel P.W. Ellis 1, 1 LabROSA, Department of Electrical Engineering, Columbia University, 2 Microsoft Research (2004)

 

DETECTION AND CORRECTION OF PHASE ERRORS IN AUDIO SIGNALS FOR APPLICATION IN BLIND SOURCE SEPARATION [PDF]

Max Blaeser, Julian Becker, Institute of Communications Engineering, RWTH Aachen University, Aachen, Germany (2014)

DETECTION OF SINGING VOICE SIGNALS IN POPULAR MUSIC RECORDINGS [PDF]

Amir Rahimzadeh, Graz University of Technology, Austria (TUG), Institute of Electronic Music and Acoustics (IEM), University of Music and Performing Arts, Graz (KUG) (2009)

DEVELOPMENT OF SOURCE SEPARATION ALGORITHM IN AUDIO APPLICATION [permalink]

Nurul Amiza Binti Amir Hamzah, Fakulti Kejuruteraan Elektronik dan Kejuruteraan Komputer, Universiti Teknikal Malaysia Melaka (2013)

 

DICTIONARY LEARNING AND SOURCE SEPARATION (slides) [PDF]

Stéphane Mallat, Centre de Mathématiques Appliquées, Ecole Polytechnique, Palaiseau, France (2009)

 

DICTIONARY LEARNING FOR AUDIO INPAINTING [PDF]

Corentin Guichaoua, IRISA/INRIA (METISS Research group) (2012)

DICTIONARY LEARNING METHODS AND SINGLE-CHANNEL SOURCE SEPARATION (slides) [PDF]

Augustin Lefèvre, Université catholique de Louvain, Belgium (2012)

 

DICTIONARY LEARNING METHODS FOR SINGLE-CHANNEL AUDIO SOURCE SEPARATION [PDF]

Augustin Lefèvre (2012)

 

DILATED CONVOLUTION WITH DILATED GRU FOR MUSIC SOURCE SEPARATION [PDF]

Jen-YuLiu, Yi-HsuanYang, Research Center for IT Innovation, Academia Sinica (2019)

DISCOVERING AUDITORY OBJECTS THROUGH NON-NEGATIVITY CONSTRAINTS [PDF]

Paris Smaragdis, Mitsubishi Electric Research Laboratories, Cambridge, Massachusetts, USA (2004)

 

DISCRIMINANT APPROACH WITHIN NON-NEGATIVE MATRIX FACTORIZATION FOR MUSICAL COMPONENTS RECOGNITION (poster) [PDF]

Zafar Rafii, Raphaël Blouet & Antoine Liutkus, Mist Technologies R&D, Paris Cybervillage, Paris, France (2007)

DISCRIMINATIVE AND RECONSTRUCTIVE BASIS TRAINING FOR AUDIO SOURCE SEPARATION WITH SEMI-SUPERVISED NONNEGATIVE MATRIX FACTORIZATION [permalink]

Daichi Kitamura (SOKENDAI), Nobutaka Ono (NII/SOKENDAI), Hiroshi Saruwatari (The University of Tokyo), Yu Takahashi (YAMAHA), Kazunobu Kondo (YAMAHA) (2016)

DISCRIMINATIVE AND RECONSTRUCTIVE BASIS TRAINING FOR AUDIO SOURCE SEPARATION WITH SEMI-SUPERVISED NONNEGATIVE MATRIX FACTORIZATION (poster) [PDF]

Daichi Kitamura (SOKENDAI), Nobutaka Ono (NII/SOKENDAI), Hiroshi Saruwatari (The University of Tokyo), Yu Takahashi (YAMAHA), Kazunobu Kondo (YAMAHA) (2016)

DISCRIMINATIVE ENHANCEMENT FOR SINGLE CHANNEL AUDIO SOURCE SEPARATION USING DEEP NEURAL NETWORKS [PDF]

Emad M. Grais, Gerard Roma, Andrew J.R. Simpson, and Mark D. Plumbley, Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK (2016)

DISCRIMINATIVE FRAMEWORK FOR SINGLE CHANNEL AUDIO SOURCE SEPARATION [PDF]

Arpita Gang, Indraprastha Institute of Information Technology, New Delhi, India (2016)

DISCRIMINATIVE NMF AND ITS APPLICATION TO SINGLE-CHANNEL SOURCE SEPARATION [PDF]

Weninger, F.; Le Roux, J.; Hershey, J.R.; Watanabe, S., Mitsubishi Electric Research Laboratories, Inc., Cambridge, Massachusetts, USA (2014)

 

DISCRIMINATIVE NONNEGATIVE DICTIONARY LEARNING USING CROSS-COHERENCE PENALTIES FOR SINGLE CHANNEL SOURCE SEPARATION [PDF]

Emad M. Grais and Hakan Erdogan, Faculty of Engineering and Natural Sciences, Sabanci University, Orhanli Tuzla, Istanbul, Turkey (2013)

 

DISCRIMINATIVE TRAINING OF COMPLEX-VALUED DEEP RECURRENT NEURAL NETWORK FOR SINGING VOICE SEPARATION [permalink]

Yuan-Shan Lee, Sih-Huei Chen, Kuo Yu, Jia-Ching Wang, Department of Computer Science and Information Engineering, National Central University, Taoyuan City, Taiwan (2017)

DISCRIMINATIVELY TRAINED RECURRENT NEURAL NETWORKS FOR SINGLE-CHANNEL SPEECH SEPARATION [permalink]

Felix Weninger∗, John R. Hershey†, Jonathan Le Roux†, Björn Schuller∗, ∗Machine Intelligence & Signal Processing Group (MISP), Technische Universität München, Munich, Germany, †Mitsubishi Electric Research Laboratories (MERL), Cambridge, Massachusetts (2014)

 

DOES K MATTER? K-NN HUBNESS ANALYSIS FOR KERNEL ADDITIVE MODELLING VOCAL SEPARATION [PDF]

Delia Fano Yela, Dan Stowell, and Mark Sandler, Queen Mary University of London, London, UK (2018)

DOES PHASE MATTER FOR MONAURAL SOURCE SEPARATION? [PDF]

Mohit Dubey, Oberlin College and Conservatory, Nils Carlson, New Mexico Institute of Mining and Technology, Garrett Kenyon, Los Alamos National Laboratory, Austin Thresher, New Mexico Consortium (2017)

DOES PHASE MATTER FOR MONAURAL SOURCE SEPARATION? (poster) [PDF]

Mohit Dubey, Oberlin College and Conservatory, Nils Carlson, New Mexico Institute of Mining and Technology, Garrett Kenyon, Los Alamos National Laboratory, Austin Thresher, New Mexico Consortium (2017)

DOWNMMIX-COMPATIBLE CONVERSION FROM MONO TO STEREO IN TIME- AND FREQUENCY-DOMAIN [PDF]

Marco Fink, Sebastian Kraft, Udo Zölzer, Department of Signal Processing and Communications, Helmut-Schmidt University Hamburg, Hamburg, Germany (2015)

 

DOWNMMIX-COMPATIBLE CONVERSION FROM MONO TO STEREO IN TIME- AND FREQUENCY-DOMAIN (audio examples)

Marco Fink, Sebastian Kraft, Udo Zölzer, Department of Signal Processing and Communications, Helmut-Schmidt University Hamburg, Hamburg, Germany (2015)

 

DRUM EXTRACTION FROM POLYPHONIC MUSIC BASED ON A SPECTRO-TEMPORAL MODEL OF PERCUSSIVE SOUNDS [permalink]

François Rigaud, Mathieu Lagrange, Axel Röbel, Geoffroy Peeters, Analysis/Synthesis of Sound Team, IRCAM/CNRS-STMS, Paris, France (2011)

DRUM EXTRACTION IN SINGLE CHANNEL AUDIO SIGNALS USING MULTI-LAYER NON NEGATIVE MATRIX FACTOR DECONVOLUTION [PDF]

Clément Laroche⋆†, Hélène Papadopoulos†, Matthieu Kowalski†‡, Gaël Richard⋆, ⋆ Institut Mines-Telecom, Telecom ParisTech, CNRS-LTCI, Paris, France, † Univ Paris-Sud-CNRS-CentraleSupelec, LSS, Gif-sur-Yvette, France, ‡ Parietal project-team, INRIA, CEA-Saclay, France <hal-01438851> (2017)

DRUM SOURCE SEPARATION USING PERCUSSIVE FEATURE DETECTION AND SPECTRAL MODULATION [PDF]

Dan Barryφ, Derry FitzGerald^, Eugene Coyleφ and Bob Lawlor*, φ Digital Audio Research Group, Dublin Institute of Technology, Kevin St. Dublin, Ireland, ^ Dept. Electrical Engineering, Cork Institute of Technology, Rossa Avenue, Bishopstown, Cork, Ireland, * Dept. of Electronic Engineering, National University of Ireland, Maynooth, Ireland (2005)

 

DYNAMIC GROUP SPARSITY FOR NON-NEGATIVE MATRIX FACTORIZATION WITH APPLICATION TO UNSUPERVISED SOURCE SEPARATION [permalink]

Xu Li, Xiaofei Wang, Qiang Fu, Yonghong Yan, Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China (2016)

DYNAMIC NON-NEGATIVE MODELS FOR AUDIO SOURCE SEPARATION [permalink]

Paris Smaragdis, University of Illinois/Adobe Research, Champaign, USA, Gautham Mysore, Adobe Research, San Francisco, USA, Nasser Mohammadiha, Volvo, Gothenburg, Sweden (2018)