tutorial/book/references.bib at master · source-separation/tutorial

769 lines (666 loc) · 26.3 KB
@misc{ wiki:waveform,
    author = "{Wikipedia contributors}",
    title = "Waveform --- {Wikipedia}{,} The Free Encyclopedia",
    year = "2020",
    url = "https://en.wikipedia.org/w/index.php?title=Waveform&oldid=972248724",
    note = "[Online; accessed 8-September-2020]"
@misc{ wiki:stft,
    author = "{Wikipedia contributors}",
    title = "Short-time Fourier transform --- {Wikipedia}{,} The Free Encyclopedia",
    year = "2020",
    url = "https://en.wikipedia.org/w/index.php?title=Short-time_Fourier_transform&oldid=972218045",
    note = "[Online; accessed 8-September-2020]"
@book{smith2011spectral,
  title={Spectral audio signal processing},
  author={Smith III, Juliu O},
  year={2011},
  publisher={W3K publishing}
@article{lostanlen2018per,
  title={Per-channel energy normalization: Why and how},
  author={Lostanlen, Vincent and Salamon, Justin and Cartwright, Mark and McFee, Brian and Farnsworth, Andrew and Kelling, Steve and Bello, Juan Pablo},
  journal={IEEE Signal Processing Letters},
  volume={26},
  number={1},
  pages={39--43},
  year={2018},
  publisher={IEEE}
@inproceedings{stoter2016common,
  title={Common fate model for unison source separation},
  author={St{\"o}ter, Fabian-Robert and Liutkus, Antoine and Badeau, Roland and Edler, Bernd and Magron, Paul},
  booktitle={2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={126--130},
  year={2016},
  organization={IEEE}
@article{pishdadian2018multi,
  title={Multi-resolution common fate transform},
  author={Pishdadian, Fatemeh and Pardo, Bryan},
  journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
  volume={27},
  number={2},
  pages={342--354},
  year={2018},
  publisher={IEEE}
@inproceedings{seetharaman2017music,
  title={Music/voice separation using the 2d fourier transform},
  author={Seetharaman, Prem and Pishdadian, Fatemeh and Pardo, Bryan},
  booktitle={2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)},
  pages={36--40},
  year={2017},
  organization={IEEE}
@article{brown1991calculation,
  title={Calculation of a constant Q spectral transform},
  author={Brown, Judith C},
  journal={The Journal of the Acoustical Society of America},
  volume={89},
  number={1},
  pages={425--434},
  year={1991},
  publisher={Acoustical Society of America}
@article{brown1992efficient,
  title={An efficient algorithm for the calculation of a constant Q transform},
  author={Brown, Judith C and Puckette, Miller S},
  journal={The Journal of the Acoustical Society of America},
  volume={92},
  number={5},
  pages={2698--2701},
  year={1992},
  publisher={Acoustical Society of America}
@inproceedings{rafii2011degenerate,
  title={Degenerate unmixing estimation technique using the constant Q transform},
  author={Rafii, Zafar and Pardo, Bryan},
  booktitle={2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={217--220},
  year={2011},
  organization={IEEE}
@inproceedings{fuentes2012blind,
  title={Blind harmonic adaptive decomposition applied to supervised source separation},
  author={Fuentes, Benoit and Badeau, Roland and Richard, Ga{\"e}l},
  booktitle={2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO)},
  pages={2654--2658},
  year={2012},
  organization={IEEE}
@inproceedings{jaiswal2011clustering,
  title={Clustering NMF basis functions using shifted NMF for monaural sound source separation},
  author={Jaiswal, Rajesh and FitzGerald, Derry and Barry, Dan and Coyle, Eugene and Rickard, Scott},
  booktitle={2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={245--248},
  year={2011},
  organization={IEEE}
@inproceedings{ganseman2012improving,
  title={Improving plca-based score-informed source separation with invertible constant-q transforms},
  author={Ganseman, Joachim and Scheunders, Paul and Dixon, Simon},
  booktitle={2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO)},
  pages={2634--2638},
  year={2012},
  organization={IEEE}
@article{shi2019cqt,
  title={Is CQT more suitable for monaural speech separation than STFT? An empirical study},
  author={Shi, Ziqiang and Lin, Huibin and Liu, Liu and Liu, Rujie and Han, Jiqing},
  journal={arXiv preprint arXiv:1902.00631},
  year={2019}
@article{lockheart2003history,
  title={A history of early microphone singing, 1925--1939: American mainstream popular singing at the advent of electronic microphone amplification},
  author={Lockheart, Paula},
  journal={Popular music and society},
  volume={26},
  number={3},
  pages={367--385},
  year={2003},
  publisher={Taylor \& Francis}
@article{le2019phasebook,
  title={Phasebook and friends: Leveraging discrete representations for source separation},
  author={Le Roux, Jonathan and Wichern, Gordon and Watanabe, Shinji and Sarroff, Andy and Hershey, John R},
  journal={IEEE Journal of Selected Topics in Signal Processing},
  volume={13},
  number={2},
  pages={370--382},
  year={2019},
  publisher={IEEE}
@article{luo2019conv,
  title={Conv-tasnet: Surpassing ideal time--frequency magnitude masking for speech separation},
  author={Luo, Yi and Mesgarani, Nima},
  journal={IEEE/ACM transactions on audio, speech, and language processing},
  volume={27},
  number={8},
  pages={1256--1266},
  year={2019},
  publisher={IEEE}
@inproceedings{heitkaemper2020demystifying,
  title={Demystifying TasNet: A dissecting approach},
  author={Heitkaemper, Jens and Jakobeit, Darius and Boeddeker, Christoph and Drude, Lukas and Haeb-Umbach, Reinhold},
  booktitle={ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={6359--6363},
  year={2020},
  organization={IEEE}
@article{bahmaninezhad2019comprehensive,
  title={A comprehensive study of speech separation: spectrogram vs waveform separation},
  author={Bahmaninezhad, Fahimeh and Wu, Jian and Gu, Rongzhi and Zhang, Shi-Xiong and Xu, Yong and Yu, Meng and Yu, Dong},
  journal={arXiv preprint arXiv:1905.07497},
  year={2019}
@inproceedings{luo2018tasnet,
  title={Tasnet: time-domain audio separation network for real-time, single-channel speech separation},
  author={Luo, Yi and Mesgarani, Nima},
  booktitle={2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={696--700},
  year={2018},
  organization={IEEE}
@article{cano2018musical,
  title={Musical source separation: An introduction},
  author={Cano, Estefania and FitzGerald, Derry and Liutkus, Antoine and Plumbley, Mark D and St{\"o}ter, Fabian-Robert},
  journal={IEEE Signal Processing Magazine},
  volume={36},
  number={1},
  pages={31--40},
  year={2018},
  publisher={IEEE}
@book{vincent2018audio,
  title={Audio source separation and speech enhancement},
  author={Vincent, Emmanuel and Virtanen, Tuomas and Gannot, Sharon},
  year={2018},
  publisher={John Wiley \& Sons}
@article{plumbley2002automatic,
  title={Automatic music transcription and audio source separation},
  author={Plumbley, Mark D and Abdallah, Samer A and Bello, Juan Pablo and Davies, Mike E and Monti, Giuliano and Sandler, Mark B},
  journal={Cybernetics \&Systems},
  volume={33},
  number={6},
  pages={603--627},
  year={2002},
  publisher={Taylor \& Francis}
@inproceedings{fujihara2006automatic,
  title={Automatic synchronization between lyrics and music CD recordings based on Viterbi alignment of segregated vocal signals},
  author={Fujihara, Hiromasa and Goto, Masataka and Ogata, Jun and Komatani, Kazunori and Ogata, Tetsuya and Okuno, Hiroshi G},
  booktitle={Eighth IEEE International Symposium on Multimedia (ISM'06)},
  pages={257--264},
  year={2006},
  organization={IEEE}
@article{mesaros2010automatic,
  title={Automatic recognition of lyrics in singing},
  author={Mesaros, Annamaria and Virtanen, Tuomas},
  journal={EURASIP Journal on Audio, Speech, and Music Processing},
  volume={2010},
  number={1},
  pages={546047},
  year={2010},
  publisher={Nature Publishing Group}
@inproceedings{weninger2011automatic,
  title={Automatic assessment of singer traits in popular music: Gender, age, height and race},
  author={Weninger, Felix and W{\"o}llmer, Martin and Schuller, Bj{\"o}rn},
  booktitle={Proc. 12th Intern. Society for Music Information Retrieval Conference, ISMIR 2011, Miami, FL, USA},
  year={2011}
@inproceedings{stoller2018jointly,
  title={Jointly detecting and separating singing voice: A multi-task approach},
  author={Stoller, Daniel and Ewert, Sebastian and Dixon, Simon},
  booktitle={International Conference on Latent Variable Analysis and Signal Separation},
  pages={329--339},
  year={2018},
  organization={Springer, Cham}
@inproceedings{heittola2009musical,
  title={Musical instrument recognition in polyphonic audio using source-filter model for sound separation.},
  author={Heittola, Toni and Klapuri, Anssi and Virtanen, Tuomas},
  booktitle={ISMIR},
  pages={327--332},
  year={2009}
@inproceedings{jansson2019joint,
  title={Joint singing voice separation and f0 estimation with deep u-net architectures},
  author={Jansson, Andreas and Bittner, Rachel M and Ewert, Sebastian and Weyde, Tillman},
  booktitle={2019 27th European Signal Processing Conference (EUSIPCO)},
  pages={1--5},
  year={2019},
  organization={IEEE}
@article{haunschmid2020towards,
  title={Towards Musically Meaningful Explanations Using Source Separation},
  author={Haunschmid, Verena and Manilow, Ethan and Widmer, Gerhard},
  journal={arXiv preprint arXiv:2009.02051},
  year={2020}
@article{haunschmid2020audiolime,
  title={audioLIME: Listenable Explanations Using Source Separation},
  author={Haunschmid, Verena and Manilow, Ethan and Widmer, Gerhard},
  journal={13th International Workshop on Machine Learning and Music 2020},
  pages={20},
  year={2020}
@inproceedings{manilow2020simultaneous,
  title={Simultaneous Separation and Transcription of Mixtures with Multiple Polyphonic and Percussive Instruments},
  author={Manilow, Ethan and Seetharaman, Prem and Pardo, Bryan},
  booktitle={ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={771--775},
  year={2020},
  organization={IEEE}
@article{wisdom2020unsupervised,
  title={Unsupervised sound separation using mixtures of mixtures},
  author={Wisdom, Scott and Tzinis, Efthymios and Erdogan, Hakan and Weiss, Ron J and Wilson, Kevin and Hershey, John R},
  journal={arXiv preprint arXiv:2006.12701},
  year={2020}
@inproceedings{seetharaman2019bootstrapping,
  title={Bootstrapping single-channel source separation via unsupervised spatial clustering on stereo mixtures},
  author={Seetharaman, Prem and Wichern, Gordon and Le Roux, Jonathan and Pardo, Bryan},
  booktitle={ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={356--360},
  year={2019},
  organization={IEEE}
@article{jansson2017singing,
  title={Singing voice separation with deep u-net convolutional networks},
  author={Jansson, Andreas and Humphrey, Eric and Montecchio, Nicola and Bittner, Rachel and Kumar, Aparna and Weyde, Tillman},
  year={2017},
  journal={International Society for Music Information Retrieval Conference, 2017}
@inproceedings{choi2018phase,
  title={Phase-aware speech enhancement with deep complex u-net},
  author={Choi, Hyeong-Seok and Kim, Jang-Hyun and Huh, Jaesung and Kim, Adrian and Ha, Jung-Woo and Lee, Kyogu},
  booktitle={International Conference on Learning Representations},
  year={2018}
@article{meseguer2019conditioned,
  title={Conditioned-u-net: Introducing a control mechanism in the u-net for multiple source separations},
  author={Meseguer-Brocal, Gabriel and Peeters, Geoffroy},
  journal={arXiv preprint arXiv:1907.01277},
  year={2019}
@article{petermann2020deep,
  title={Deep Learning Based Source Separation Applied To Choir Ensembles},
  author={Petermann, Darius and Chandna, Pritish and Cuesta, Helena and Bonada, Jordi and Gomez, Emilia},
  journal={arXiv preprint arXiv:2008.07645},
  year={2020}
@article{kadandale2020multi,
  title={Multi-task U-Net for Music Source Separation},
  author={Kadandale, Venkatesh S and Montesinos, Juan F and Haro, Gloria and G{\'o}mez, Emilia},
  journal={arXiv preprint arXiv:2003.10414},
  year={2020}
@article{slizovskaia2020conditioned,
  title={Conditioned Source Separation for Music Instrument Performances},
  author={Slizovskaia, Olga and Haro, Gloria and G{\'o}mez, Emilia},
  journal={arXiv preprint arXiv:2004.03873},
  year={2020}
@inproceedings{sharma2019importance,
  title={On the Importance of Audio-Source Separation for Singer Identification in Polyphonic Music.},
  author={Sharma, Bidisha and Das, Rohan Kumar and Li, Haizhou},
  booktitle={INTERSPEECH},
  pages={2020--2024},
  year={2019}
@article{hung2020multitask,
  title={Multitask learning for instrument activation aware music source separation},
  author={Hung, Yun-Ning and Lerch, Alexander},
  journal={arXiv preprint arXiv:2008.00616},
  year={2020}
@article{hu2015separation,
  title={Separation of singing voice using nonnegative matrix partial co-factorization for singer identification},
  author={Hu, Ying and Liu, Guizhong},
  journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
  volume={23},
  number={4},
  pages={643--653},
  year={2015},
  publisher={IEEE}
@article{stoller2018wave,
  title={Wave-u-net: A multi-scale neural network for end-to-end audio source separation},
  author={Stoller, Daniel and Ewert, Sebastian and Dixon, Simon},
  journal={arXiv preprint arXiv:1806.03185},
  year={2018}
@article{defossez2019music,
  title={Music source separation in the waveform domain},
  author={D{\'e}fossez, Alexandre and Usunier, Nicolas and Bottou, L{\'e}on and Bach, Francis},
  journal={arXiv preprint arXiv:1911.13254},
  year={2019}
@article{defossez2019demucs,
  title={Demucs: Deep Extractor for Music Sources with extra unlabeled data remixed},
  author={D{\'e}fossez, Alexandre and Usunier, Nicolas and Bottou, L{\'e}on and Bach, Francis},
  journal={arXiv preprint arXiv:1909.01174},
  year={2019}
@article{dumoulin2016guide,
  title="{A guide to convolution arithmetic for deep learning}",
  author = {{Dumoulin}, Vincent and {Visin}, Francesco},
  journal = {ArXiv e-prints},
  eprint = {1603.07285},
  year={2016},
  month={mar}
@article{oord2016wavenet,
  title={Wavenet: A generative model for raw audio},
  author={Oord, Aaron van den and Dieleman, Sander and Zen, Heiga and Simonyan, Karen and Vinyals, Oriol and Graves, Alex and Kalchbrenner, Nal and Senior, Andrew and Kavukcuoglu, Koray},
  journal={arXiv preprint arXiv:1609.03499},
  year={2016}
@article{lluis2019end,
  title={End-to-End Music Source Separation: Is it Possible in the Waveform Domain?},
  author={Llu{\'\i}s, Francesc and Pons, Jordi and Serra, Xavier},
  journal={Proc. Interspeech 2019},
  pages={4619--4623},
  year={2019}
@article{seetharaman2020bootstrapping,
  title={Bootstrapping deep music separation from primitive auditory grouping principles},
  author={Seetharaman, Prem and Wichern, Gordon and Roux, Jonathan Le and Pardo, Bryan},
  journal={ICML Workshop on Self-Supervision in Audio and Speech},
  year={2020}
@inproceedings{tzinis2019unsupervised,
  title={Unsupervised deep clustering for source separation: Direct learning from mixtures using spatial information},
  author={Tzinis, Efthymios and Venkataramani, Shrikant and Smaragdis, Paris},
  booktitle={ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={81--85},
  year={2019},
  organization={IEEE}
@article{ulyanov2016instance,
  title={Instance normalization: The missing ingredient for fast stylization},
  author={Ulyanov, Dmitry and Vedaldi, Andrea and Lempitsky, Victor},
  journal={arXiv preprint arXiv:1607.08022},
  year={2016}
@inproceedings{drude2019unsupervised,
  title={Unsupervised training of a deep clustering model for multichannel blind source separation},
  author={Drude, Lukas and Hasenklever, Daniel and Haeb-Umbach, Reinhold},
  booktitle={ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={695--699},
  year={2019},
  organization={IEEE}
@article{zhang2019gradient,
  title={Why gradient clipping accelerates training: A theoretical justification for adaptivity},
  author={Zhang, Jingzhao and He, Tianxing and Sra, Suvrit and Jadbabaie, Ali},
  journal={arXiv preprint arXiv:1905.11881},
  year={2019}
@phdthesis{mikolov2012statistical,
  title={Statistical language models based on neural networks},
  author={Mikolov, Tom{\'a}{\v{s}}},
  school={Brno University of Technology},
  year={2012}
@inproceedings{wu2018group,
  title={Group normalization},
  author={Wu, Yuxin and He, Kaiming},
  booktitle={Proceedings of the European conference on computer vision (ECCV)},
  pages={3--19},
  year={2018}
@article{ioffe2015batch,
  title={Batch normalization: Accelerating deep network training by reducing internal covariate shift},
  author={Ioffe, Sergey and Szegedy, Christian},
  journal={arXiv preprint arXiv:1502.03167},
  year={2015}
@article{bengio1994learning,
  title={Learning long-term dependencies with gradient descent is difficult},
  author={Bengio, Yoshua and Simard, Patrice and Frasconi, Paolo},
  journal={IEEE Transactions on Neural Networks},
  volume={5},
  number={2},
  pages={157--166},
  year={1994},
  publisher={IEEE}
@article{seetharaman2020autoclip,
  title={AutoClip: Adaptive Gradient Clipping for Source Separation Networks},
  author={Seetharaman, Prem and Wichern, Gordon and Pardo, Bryan and Roux, Jonathan Le},
  journal={arXiv preprint arXiv:2007.14469},
  year={2020}
@inproceedings{erdogan2015phase,
  title={Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks},
  author={Erdogan, Hakan and Hershey, John R and Watanabe, Shinji and Le Roux, Jonathan},
  booktitle={2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={708--712},
  year={2015},
  organization={IEEE}
@inproceedings{weninger2014discriminatively,
  title={Discriminatively trained recurrent neural networks for single-channel speech separation},
  author={Weninger, Felix and Hershey, John R and Le Roux, Jonathan and Schuller, Bj{\"o}rn},
  booktitle={2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP)},
  pages={577--581},
  year={2014},
  organization={IEEE}
@article{vincent2006performance,
  title={Performance measurement in blind audio source separation},
  author={Vincent, Emmanuel and Gribonval, R{\'e}mi and F{\'e}votte, C{\'e}dric},
  journal={IEEE transactions on audio, speech, and language processing},
  volume={14},
  number={4},
  pages={1462--1469},
  year={2006},
  publisher={IEEE}
@inproceedings{le2019sdr,
  title={SDR--half-baked or well done?},
  author={Le Roux, Jonathan and Wisdom, Scott and Erdogan, Hakan and Hershey, John R},
  booktitle={ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={626--630},
  year={2019},
  organization={IEEE}
@inproceedings{masuyama2019deep,
  title={Deep griffin--lim iteration},
  author={Masuyama, Yoshiki and Yatabe, Kohei and Koizumi, Yuma and Oikawa, Yasuhiro and Harada, Noboru},
  booktitle={ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={61--65},
  year={2019},
  organization={IEEE}
@article{griffin1984signal,
  title={Signal estimation from modified short-time Fourier transform},
  author={Griffin, Daniel and Lim, Jae},
  journal={IEEE Transactions on Acoustics, Speech, and Signal Processing},
  volume={32},
  number={2},
  pages={236--243},
  year={1984},
  publisher={IEEE}
@inproceedings{perraudin2013fast,
  title={A fast Griffin-Lim algorithm},
  author={Perraudin, Nathana{\"e}l and Balazs, Peter and S{\o}ndergaard, Peter L},
  booktitle={2013 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics},
  pages={1--4},
  year={2013},
  organization={IEEE}
@inproceedings{wichern2018phase,
  title={Phase reconstruction with learned time-frequency representations for single-channel speech separation},
  author={Wichern, Gordon and Le Roux, Jonathan},
  booktitle={2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC)},
  pages={396--400},
  year={2018},
  organization={IEEE}
@article{gunawan2010iterative,
  title={Iterative phase estimation for the synthesis of separated sources from single-channel mixtures},
  author={Gunawan, David and Sen, Deep},
  journal={IEEE Signal Processing Letters},
  volume={17},
  number={5},
  pages={421--424},
  year={2010},
  publisher={IEEE}
@inproceedings{engel2019ddsp,
  title={DDSP: Differentiable Digital Signal Processing},
  author={Engel, Jesse and Gu, Chenjie and Roberts, Adam and others},
  booktitle={International Conference on Learning Representations},
  year={2019}
@inproceedings{engel2018gansynth,
  title={GANSynth: Adversarial Neural Audio Synthesis},
  author={Engel, Jesse and Agrawal, Kumar Krishna and Chen, Shuo and Gulrajani, Ishaan and Donahue, Chris and Roberts, Adam},
  booktitle={International Conference on Learning Representations},
  year={2018}
@article{takahashi2020d3net,
  title={D3Net: Densely Connected MultiDilated DenseNet for Music Source Separation},
  author={Takahashi, Naoya and Mitsufuji, Yuki},
  journal={arXiv preprint arXiv:2010.01733},
  year={2020}
@article{rafii2012repeating,
  title={Repeating pattern extraction technique (REPET): A simple method for music/voice separation},
  author={Rafii, Zafar and Pardo, Bryan},
  journal={IEEE transactions on audio, speech, and language processing},
  volume={21},
  number={1},
  pages={73--84},
  year={2012},
  publisher={IEEE}
@inproceedings{rafii2012music,
  title={Music/Voice Separation Using the Similarity Matrix.},
  author={Rafii, Zafar and Pardo, Bryan},
  booktitle={ISMIR},
  year={2012}
@inproceedings{cartwright2016fast,
  title={Fast and easy crowdsourced perceptual audio evaluation},
  author={Cartwright, Mark and Pardo, Bryan and Mysore, Gautham J and Hoffman, Matt},
  booktitle={2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={619--623},
  year={2016},
  organization={IEEE}
@article{rafii2018overview,
  title={An overview of lead and accompaniment separation in music},
  author={Rafii, Zafar and Liutkus, Antoine and St{\"o}ter, Fabian-Robert and Mimilakis, Stylianos Ioannis and FitzGerald, Derry and Pardo, Bryan},
  journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
  volume={26},
  number={8},
  pages={1307--1335},
  year={2018},
  publisher={IEEE}
@article{schoeffler2018webmushra,
  title={webMUSHRA—A comprehensive framework for web-based listening tests},
  author={Schoeffler, Michael and Bartoschek, Sarah and St{\"o}ter, Fabian-Robert and Roess, Marlene and Westphal, Susanne and Edler, Bernd and Herre, J{\"u}rgen},
  journal={Journal of Open Research Software},
  volume={6},
  number={1},
  year={2018},
  publisher={Ubiquity Press}
@inproceedings{hershey2016deep,
  title={Deep clustering: Discriminative embeddings for segmentation and separation},
  author={Hershey, John R and Chen, Zhuo and Le Roux, Jonathan and Watanabe, Shinji},
  booktitle={2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={31--35},
  year={2016},
  organization={IEEE}
@inproceedings{wang2018alternative,
  title={Alternative objective functions for deep clustering},
  author={Wang, Zhong-Qiu and Le Roux, Jonathan and Hershey, John R},
  booktitle={2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={686--690},
  year={2018},
  organization={IEEE}
@inproceedings{luo2017deep,
  title={Deep clustering and conventional networks for music separation: Stronger together},
  author={Luo, Yi and Chen, Zhuo and Hershey, John R and Le Roux, Jonathan and Mesgarani, Nima},
  booktitle={2017 IEEE international conference on acoustics, speech and signal processing (ICASSP)},
  pages={61--65},
  year={2017},
  organization={IEEE}
@inproceedings{chen2017deep,
  title={Deep attractor network for single-microphone speaker separation},
  author={Chen, Zhuo and Luo, Yi and Mesgarani, Nima},
  booktitle={2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={246--250},
  year={2017},
  organization={IEEE}
@inproceedings{samuel2020meta,
  title={Meta-learning Extractors for Music Source Separation},
  author={Samuel, David and Ganeshan, Aditya and Naradowsky, Jason},
  booktitle={ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={816--820},
  year={2020},
  organization={IEEE}
@article{spleeter2020,
  doi = {10.21105/joss.02154},
  url = {https://doi.org/10.21105/joss.02154},
  year = {2020},
  publisher = {The Open Journal},
  volume = {5},
  number = {50},
  pages = {2154},
  author = {Romain Hennequin and Anis Khlif and Felix Voituret and Manuel Moussallam},
  title = {Spleeter: a fast and efficient music source separation tool with pre-trained models},
  journal = {Journal of Open Source Software},
  note = {Deezer Research}
@misc{musdb18,
  author       = {Rafii, Zafar and
                  Liutkus, Antoine and
                  Fabian-Robert St{\"o}ter and
                  Mimilakis, Stylianos Ioannis and
                  Bittner, Rachel},
  title        = {The {MUSDB18} corpus for music separation},
  month        = dec,
  year         = 2017,
  doi          = {10.5281/zenodo.1117372},
  url          = {https://doi.org/10.5281/zenodo.1117372}
@misc{musdb18-hq,
  author       = {Rafii, Zafar and
                  Liutkus, Antoine and
                  Stöter, Fabian-Robert and
                  Mimilakis, Stylianos Ioannis and
                  Bittner, Rachel},
  title        = {MUSDB18-HQ - an uncompressed version of MUSDB18},
  month        = aug,
  year         = 2019,
  doi          = {10.5281/zenodo.3338373},
  url          = {https://doi.org/10.5281/zenodo.3338373}
@inproceedings {nussl
    author = {Ethan Manilow and Prem Seetharaman and Bryan Pardo},
    title = {"The Northwestern University Source Separation Library"},
    booktitle = {"Proceedings of the 19th International Society of Music Information Retrieval
        Conference ({ISMIR} 2018), Paris, France, September 23-27"},
    year = {2018}
Provide feedback

Saved searches

Use saved searches to filter your results more quickly

FilesExpand file tree

references.bib

Latest commit

History

references.bib

File metadata and controls
