bibliography.bib

@book{mcgrain1990music,
    title={Music Notation: Theory and Technique for Music Notation},
    author={McGrain, M.},
    isbn={9780793508471},
    lccn={90191598},
    series={Berklee guide},
    url={https://books.google.cz/books?id=S\_y7JAZqx6QC},
    year={1990},
    publisher={Berklee Press}
}

@misc{an-explanation-of-clefs,
    author = {{Making Music}},
    title = "An Explanation of Clefs: Treble, Bass, Alto, Tenor",
    url = "https://makingmusicmag.com/explanation-clefs-treble-bass-alto-tenor/",
    type = "web page",
    note = "[Cited 2019-10-05]"
}

@online{time-signature,
    author = {{Encyclopædia Britannica, inc.}},
    title = "Time signature",
    url = "https://www.britannica.com/art/time-signature",
    year = 2017,
    month = 11,
    day = 17,
    type = "web page",
    note = "[Cited 2019-10-23]"
}

@misc{key-signature,
    title = "Key signature and music staff",
    url = "https://www.aboutmusictheory.com/key-signature.html",
    year = 2012,
    month = 4,
    day = 19,
    type = "web page",
    note = "[Cited 2019-10-23]"
}

@article{melody-transcription-from-music-audio,
    author = {Poliner, G.E. and Ellis, D.P.W. and Ehmann, A.F. and Gómez, Emilia and Streich, Sebastian and Ong, Beesuan},
    year = {2007},
    month = {06},
    pages = {1247 - 1256},
    title = {Melody Transcription From Music Audio: Approaches and Evaluation},
    volume = {15},
    journal = {Audio, Speech, and Language Processing, IEEE Transactions on},
    doi = {10.1109/TASL.2006.889797}
}

@misc{digital-audio-basics,
    title = "Digital Audio Basics: Sample Rate and Bit Depth",
    url = "https://www.izotope.com/en/learn/digital-audio-basics-sample-rate-and-bit-depth.html",
    year = 2019,
    month = 7,
    day = 15,
    type = "web page",
    note = "[Cited 2019-11-24]"
}

@book{signals-and-systems,
    title={Signals and Systems},
    author={Ghosh, S.},
    isbn={9788177583809},
    series={Always Learning},
    url={https://books.google.com.ua/books?id=Sg6y\_EBYCEsC},
    year={2005},
    publisher={Pearson Education Canada}
}

@book{roots-of-modern-technology,
    title={Roots of Modern Technology: An Elegant Survey of the Basic Mathematical and Scientific Concepts},
    author={Wendt, S.},
    isbn={9783642120626},
    url={https://books.google.com.ua/books?id=c8TdQmtOD-AC},
    year={2010},
    publisher={Springer Berlin Heidelberg}
}

@misc{spleeter2019,
    title={Spleeter: A Fast And State-of-the Art Music Source Separation Tool With Pre-trained Models},
    author={Romain Hennequin and Anis Khlif and Felix Voituret and Manuel Moussallam},
    howpublished={Late-Breaking/Demo ISMIR 2019},
    month={November},
    note={{Deezer Research}},
    year={2019}
}

@misc{stter20182018,
    title={The 2018 Signal Separation Evaluation Campaign},
    author={Fabian-Robert Stöter and Antoine Liutkus and Nobutaka Ito},
    year={2018},
    eprint={1804.06267},
    archivePrefix={arXiv},
    primaryClass={eess.AS}
}

@misc{singing-voice-separation,
    title = {Singing voice separation with deep U-Net convolutional networks},
    month = {October},
    author = {A. Jansson and E. Humphrey and N. Montecchio and R. Bittner and A. Kumar and T. Weyde},
    year = {2017},
    url = {https://openaccess.city.ac.uk/id/eprint/19289/},
}

@article{singing-voice-separation-article,
    title={Singing Voice Separation: A Study on Training Data},
    ISBN={9781479981311},
    url={http://dx.doi.org/10.1109/ICASSP.2019.8683555},
    DOI={10.1109/icassp.2019.8683555},
    journal={ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
    publisher={IEEE},
    author={Pretet, Laure and Hennequin, Romain and Royo-Letelier, Jimena and Vaglio, Andrea},
    year={2019},
    month={May}
}

@inproceedings{SiSEC16,
    Title = {The 2016 Signal Separation Evaluation Campaign},
    Address = {Cham},
    Author = {Liutkus, Antoine and St{\"o}ter, Fabian-Robert and Rafii, Zafar and Kitamura, Daichi and Rivet, Bertrand and Ito, Nobutaka and Ono, Nobutaka and Fontecave, Julie},
    Editor = {Tichavsk{\'y}, Petr and Babaie-Zadeh, Massoud and Michel, Olivier J.J. and Thirion-Moreau, Nad{\`e}ge},
    Pages = {323--332},
    Publisher = {Springer International Publishing},
    Year = {2017},
    booktitle = {Latent Variable Analysis and Signal Separation - 12th International Conference, {LVA/ICA} 2015, Liberec, Czech Republic, August 25-28, 2015, Proceedings},
}

@misc{dumoulin2016guide,
    title={A guide to convolution arithmetic for deep learning},
    author={Vincent Dumoulin and Francesco Visin},
    year={2016},
    eprint={1603.07285},
    archivePrefix={arXiv},
    primaryClass={stat.ML}
}

@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{pitch-salience-function,
    author = {A. Degani, R. Leonardi, P. Migliorati},
    title = {A pitch salience function derived from harmonic frequency deviations for polyphonic music analysis},
    month = sep,
    year = 2014,
    url = {http://www.cmap.polytechnique.fr/~bacry/MVA/getpapers.php?file=multipitch_2.pdf&type=pdf}
}

@INPROCEEDINGS{fundamental-frequency-estimation,
    author={ {Chunghsin Yeh} and A. {Robel} and X. {Rodet}},
    booktitle={Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.},
    title={Multiple fundamental frequency estimation of polyphonic music signals},
    year={2005},
    volume={3},
    pages={iii/225-iii/228 Vol. 3},
    keywords={frequency estimation;music;audio signal processing;sequences;multiple fundamental frequency estimation;polyphonic music signals;harmonicity;spectral smoothness;synchronous amplitude evolution;generative quasiharmonic model;hypothetical partial sequences;score function;Frequency estimation;Multiple signal classification;Noise generators;Signal analysis;Testing;Rhythm;Music information retrieval;Instruments;Interference;Reverberation},
    doi={10.1109/ICASSP.2005.1415687},
    ISSN={2379-190X},
    month={March}
}

@article{dressler2012multiple,
    title={Multiple fundamental frequency extraction for MIREX},
    author={Dressler, Karin},
    journal={Eighth Music Information Retrieval Evaluation eXchange (MIREX)},
    year={2012}
}

@inproceedings{pertusa2008multiple,
    title={Multiple fundamental frequency estimation using Gaussian smoothness},
    author={Pertusa, Antonio and Inesta, Jos{\'e} M},
    booktitle={2008 IEEE International Conference on Acoustics, Speech and Signal Processing},
    pages={105--108},
    year={2008},
    organization={IEEE}
}

@inproceedings{reis2008hybrid,
    title={Hybrid genetic algorithm based on gene fragment competition for polyphonic music transcription},
    author={Reis, Gustavo and Fonseca, Nuno and De Vega, Francisco Fern{\'a}ndez and Ferreira, Anibal},
    booktitle={Workshops on Applications of Evolutionary Computation},
    pages={305--314},
    year={2008},
    organization={Springer}
}

@article{grosche2012automatic,
    title={Automatic transcription of recorded music},
    author={Grosche, Peter and Schuller, Bj{\"o}rn and M{\"u}ller, Meinard and Rigoll, Gerhard},
    journal={Acta Acustica united with Acustica},
    volume={98},
    number={2},
    pages={199--215},
    year={2012},
    publisher={S. Hirzel Verlag}
}

@inproceedings{nam2011classification,
    title={A Classification-Based Polyphonic Piano Transcription Approach Using Learned Feature Representations.},
    author={Nam, Juhan and Ngiam, Jiquan and Lee, Honglak and Slaney, Malcolm},
    booktitle={Ismir},
    pages={175--180},
    year={2011}
}

@article{humphrey2013feature,
    title={Feature learning and deep architectures: new directions for music informatics},
    author={Humphrey, Eric J and Bello, Juan P and LeCun, Yann},
    journal={Journal of Intelligent Information Systems},
    volume={41},
    number={3},
    pages={461--481},
    year={2013},
    publisher={Springer}
}

@ARTICLE{proba-spectral-smoothness,
    author = {V. { Emiya } and R. { Badeau } and B. { David }},
    journal = {IEEE Transactions on Audio, Speech, and Language Processing},
    title = {Multipitch Estimation of Piano Sounds Using a New Probabilistic Spectral Smoothness Principle},
    year = {2010},
    volume = {18},
    number = {6},
    pages = {1643-1654},
    keywords = {acoustic signal processing;autoregressive processes;musical instruments;probability;smoothing methods;spectral analysis;multipitch estimation;piano sounds;probabilistic spectral smoothness principle;piano recordings;overlapping overtones;spectral envelope modeling;smooth autoregressive model;moving-average model;piano overtone series;homemade database;MAPS;Instruments;Signal processing;Background noise;Testing;Databases;Audio recording;Signal analysis;Pattern matching;Image analysis;Acoustic signal analysis;audio processing;multipitch estimation (MPE);piano;transcription;spectral smoothness},
    doi = {10.1109/TASL.2009.2038819},
    ISSN = {1558-7924},
    month = {Aug}
}

@article{predominant-f0-estimation,
    title = "A real-time music-scene-description system: predominant-F0 estimation for detecting melody and bass lines in real-world audio signals",
    journal = "Speech Communication",
    volume = "43",
    number = "4",
    year = "2004",
    note = "Special Issue on the Recognition and Organization of Real-World Sound",
    issn = "0167-6393",
    doi = "https://doi.org/10.1016/j.specom.2004.07.001",
    url = "http://www.sciencedirect.com/science/article/pii/S0167639304000640",
    author = "Masataka Goto",
    keywords = "F0 estimation, MAP estimation, EM algorithm, Music understanding, Computational auditory scene analysis, Music information retrieval",
    abstract = "In this paper, we describe the concept of music scene description and address the problem of detecting melody and bass lines in real-world audio signals containing the sounds of various instruments. Most previous pitch-estimation methods have had difficulty dealing with such complex music signals because these methods were designed to deal with mixtures of only a few sounds. To enable estimation of the fundamental frequency (F0) of the melody and bass lines, we propose a predominant-F0 estimation method called PreFEst that does not rely on the unreliable fundamental component and obtains the most predominant F0 supported by harmonics within an intentionally limited frequency range. This method estimates the relative dominance of every possible F0 (represented as a probability density function of the F0) by using MAP (maximum a posteriori probability) estimation and considers the F0’s temporal continuity by using a multiple-agent architecture. Experimental results with a set of ten music excerpts from compact-disc recordings showed that a real-time system implementing this method was able to detect melody and bass lines about 80% of the time these existed."
}

@ARTICLE{harmonic-temporal-structured-clustering,
author={H. {Kameoka} and T. {Nishimoto} and S. {Sagayama}},
journal={IEEE Transactions on Audio, Speech, and Language Processing},
title={A Multipitch Analyzer Based on Harmonic Temporal Structured Clustering},
year={2007},
volume={15},
number={3},
pages={982-994},
keywords={audio signal processing;Gaussian processes;time series;time-frequency analysis;multipitch analyzer;harmonic temporal structured clustering method;multipitch audio signal;energy patterns;time-frequency space;power spectrum time series;superimposed HTC source models;Gaussian kernel representation;Harmonic analysis;Music;Signal analysis;Time frequency analysis;Image analysis;Power harmonic filters;Acoustic applications;Speech analysis;Acoustic signal detection;Spectrogram;Computational acoustic scene analysis;harmonic temporal structured clustering (HTC);multipitch analyzer},
doi={10.1109/TASL.2006.885248},
ISSN={1558-7924},
month={March}
}

@article{peeling2011multiple,
    title={Multiple pitch estimation using non-homogeneous Poisson processes},
    author={Peeling, Paul H and Godsill, Simon J},
    journal={IEEE Journal of Selected Topics in Signal Processing},
    volume={5},
    number={6},
    pages={1133--1143},
    year={2011},
    publisher={IEEE}
}

@article{koretz2011maximum,
    title={Maximum a posteriori probability multiple-pitch tracking using the harmonic model},
    author={Koretz, Amitai and Tabrikian, Joseph},
    journal={IEEE Transactions on Audio, Speech, and Language Processing},
    volume={19},
    number={7},
    pages={2210--2221},
    year={2011},
    publisher={IEEE}
}

@inproceedings{smaragdis2003non,
    title={Non-negative matrix factorization for polyphonic music transcription},
    author={Smaragdis, Paris and Brown, Judith C},
    booktitle={2003 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (IEEE Cat. No. 03TH8684)},
    pages={177--180},
    year={2003},
    organization={IEEE}
}

@inproceedings{cont2006realtime,
    title={Realtime multiple pitch observation using sparse non-negative constraints},
    author={Cont, Arshia},
    year={2006}
}

@article{kumar2007hierarchical,
    title={Hierarchical processing of auditory objects in humans},
    author={Kumar, Sukhbinder and Stephan, Klaas E and Warren, Jason D and Friston, Karl J and Griffiths, Timothy D},
    journal={PLoS computational biology},
    volume={3},
    number={6},
    pages={e100},
    year={2007},
    publisher={Public Library of Science}
}

@article{vincent2009adaptive,
    title={Adaptive harmonic spectral decomposition for multiple pitch estimation},
    author={Vincent, Emmanuel and Bertin, Nancy and Badeau, Roland},
    journal={IEEE Transactions on Audio, Speech, and Language Processing},
    volume={18},
    number={3},
    pages={528--537},
    year={2009},
    publisher={IEEE}
}

@article{bertin2010enforcing,
    title={Enforcing harmonicity and smoothness in Bayesian non-negative matrix factorization applied to polyphonic music transcription},
    author={Bertin, Nancy and Badeau, Roland and Vincent, Emmanuel},
    journal={IEEE Transactions on Audio, Speech, and Language Processing},
    volume={18},
    number={3},
    pages={538--549},
    year={2010},
    publisher={IEEE}
}

@inproceedings{ochiai2012explicit,
    title={Explicit beat structure modeling for non-negative matrix factorization-based multipitch analysis},
    author={Ochiai, Kazuki and Kameoka, Hirokazu and Sagayama, Shigeki},
    booktitle={2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
    pages={133--136},
    year={2012},
    organization={IEEE}
}

@article{grindlay2011transcribing,
    title={Transcribing multi-instrument polyphonic music with hierarchical eigeninstruments},
    author={Grindlay, Graham and Ellis, Daniel PW},
    journal={IEEE Journal of Selected Topics in Signal Processing},
    volume={5},
    number={6},
    pages={1159--1169},
    year={2011},
    publisher={IEEE}
}

@inproceedings{dessein2010real,
    title={Real-time polyphonic music transcription with non-negative matrix factorization and beta-divergence},
    author={Dessein, Arnaud and Cont, Arshia and Lemaitre, Guillaume},
    year={2010}
}

@article{bello2006automatic,
    title={Automatic piano transcription using frequency and time-domain information},
    author={Bello, Juan Pablo and Daudet, Laurent and Sandler, Mark B},
    journal={IEEE Transactions on Audio, Speech, and Language Processing},
    volume={14},
    number={6},
    pages={2242--2251},
    year={2006},
    publisher={IEEE}
}

@article{poliner2006discriminative,
    title={A discriminative model for polyphonic piano transcription},
    author={Poliner, Graham E and Ellis, Daniel PW},
    journal={EURASIP Journal on Advances in Signal Processing},
    volume={2007},
    number={1},
    pages={048317},
    year={2006},
    publisher={Springer}
}

@inproceedings{ryynanen2005polyphonic,
    title={Polyphonic music transcription using note event modeling},
    author={Ryynanen, Matti P and Klapuri, Anssi},
    booktitle={IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, 2005.},
    pages={319--322},
    year={2005},
    organization={IEEE}
}

@inproceedings{raczynski2009note,
    title={Note detection with dynamic bayesian networks as a postanalysis step for NMF-based multiple pitch estimation techniques},
    author={Raczy{\'n}ski, Stanislaw A and Ono, Nobutaka and Sagayama, Shigeki},
    booktitle={2009 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics},
    pages={49--52},
    year={2009},
    organization={IEEE}
}

@article{gouyon2005review,
    title={A review of automatic rhythm description systems},
    author={Gouyon, Fabien and Dixon, Simon},
    journal={Computer music journal},
    volume={29},
    number={1},
    pages={34--54},
    year={2005},
    publisher={MIT Press}
}

@article{desain1999computational,
    title={Computational models of beat induction: The rule-based approach},
    author={Desain, Peter and Honing, Henkjan},
    journal={Journal of new music research},
    volume={28},
    number={1},
    pages={29--42},
    year={1999},
    publisher={Taylor \& Francis}
}

@article{large1994resonance,
    title={Resonance and the perception of musical meter},
    author={Large, Edward W and Kolen, John F},
    journal={Connection science},
    volume={6},
    number={2-3},
    pages={177--208},
    year={1994},
    publisher={Taylor \& Francis}
}

@article{dixon2001automatic,
    title={Automatic extraction of tempo and beat from expressive performances},
    author={Dixon, Simon},
    journal={Journal of New Music Research},
    volume={30},
    number={1},
    pages={39--58},
    year={2001},
    publisher={Taylor \& Francis}
}

@article{cemgil2011monte,
    title={Monte carlo methods for tempo tracking and rhythm quantization},
    author={Cemgil, Ali Taylan and Kappen, Bert},
    journal={arXiv preprint arXiv:1106.4863},
    year={2011}
}

@book{dregvaite2015information,
    title={Information and Software Technologies: 21st International Conference, ICIST 2015, Druskininkai, Lithuania, October 15-16, 2015, Proceedings},
    author={Dregvaite, G. and Damasevicius, R.},
    isbn={9783319247700},
    series={Communications in Computer and Information Science},
    url={https://books.google.com.ua/books?id=-pLDCgAAQBAJ},
    year={2015},
    publisher={Springer International Publishing}
}


@misc{sound-envelope,
    author={Meinard Müller and Tim Zunner},
    title = "Envelope and ADSR Model",
    url = "https://www.audiolabs-erlangen.de/resources/MIR/FMP/C1/C1S3_Timbre.html",
    type = "web page",
    note = "[Cited 2019-11-28]"
}

@misc{nsynth2017,
    Author = {Jesse Engel and Cinjon Resnick and Adam Roberts and
              Sander Dieleman and Douglas Eck and Karen Simonyan and
              Mohammad Norouzi},
    Title = {Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders},
    Year = {2017},
    Eprint = {arXiv:1704.01279},
}


@misc{perfect-pitch,
    author="Jann Ingmire",
    title = "Acquiring ‘perfect’ pitch may be possible for some adults.",
    url = "https://news.uchicago.edu/story/acquiring-perfect-pitch-may-be-possible-some-adults",
    type = "web page",
    year = 2015,
    month = May,
    note = "[Cited 2019-12-23]"
}

@misc{comb-filter,
    author="Roger Russell",
    title = "Hearing, Columns and Comb Filtering",
    url = "http://www.roger-russell.com/columns/combfilter2.htm",
    type = "web page",
    year = 2006,
    note = "[Cited 2019-12-23]"
}

@inproceedings{madmom,
    Title = {{madmom: a new Python Audio and Music Signal Processing Library}},
    Author = {B{\"o}ck, Sebastian and Korzeniowski, Filip and Schl{\"u}ter, Jan and Krebs, Florian and Widmer, Gerhard},
    Booktitle = {Proceedings of the 24th ACM International Conference on Multimedia},
    Month = {10},
    Year = {2016},
    Pages = {1174--1178},
    Address = {Amsterdam, The Netherlands},
    Doi = {10.1145/2964284.2973795}
}


@misc{mixed-in-keys,
    author="Yakov Vorobyev",
    url = "https://mixedinkey.com/",
    type = "web page",
    year = 2005,
    note = "[Cited 2019-12-23]"
}

@misc{key-finder,
    author="Ibrahim Sha'ath",
    url = "http://www.ibrahimshaath.co.uk/keyfinder/",
    type = "web page",
    year = 2011,
    note = "[Cited 2019-12-23]"
}

@misc{mirex,
    author="Cameron Jones",
    title = "Music Information Retrieval Evaluation eXchange(MIREX)",
    url = "https://www.music-ir.org/mirex/wiki/MIREX_HOME",
    type = "web page",
    year = 2010,
    note = "[Cited 2020-01-05]"
}

@misc{lilypond,
    title = "LilyPond - music notation for everyone",
    url = "http://lilypond.org/",
    type = "web page",
    year = 2019,
    note = "[Cited 2020-01-05]"
}

@article{vincent2006performance,
    title={Performance measurement in blind audio source separation},
    author={ 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}
}

@article{stoter19,
    author        = {F.-R. St\\"oter and
    S. Uhlich and
    A. Liutkus and
    Y. Mitsufuji},
    title         = {Open-Unmix - A Reference Implementation
    for Music Source Separation},
    journal       = {Journal of Open Source Software},
    year          = 2019,
    doi           = {10.21105/joss.01667},
    url           = {https://doi.org/10.21105/joss.01667}
}

@inproceedings{fma_dataset,
    title = {FMA: A Dataset for Music Analysis},
    author = {Defferrard, Micha\"el and Benzi, Kirell and Vandergheynst, Pierre and Bresson, Xavier},
    booktitle = {18th International Society for Music Information Retrieval Conference},
    year = {2017},
    url = {https://arxiv.org/abs/1612.01840},
}

@inproceedings{cancela2009efficient,
    title={An Efficient Multi-Resolution Spectral Transform for Music Analysis.},
    author={Cancela, Pablo and Rocamora, Mart{\'\i}n and L{\'o}pez, Ernesto},
    booktitle={ISMIR},
    pages={309--314},
    year={2009}
}