literatura.bib

@ARTICLE{benetos2019overview,
  author={Benetos, Emmanouil and Dixon, Simon and Duan, Zhiyao and Ewert, Sebastian},
  journal={IEEE Signal Processing Magazine}, 
  title={Automatic Music Transcription: An Overview}, 
  year={2019},
  volume={36},
  number={1},
  pages={20-30},
  doi={10.1109/MSP.2018.2869928}
}

@misc{kelz2016potential,
  title={On the Potential of Simple Framewise Approaches to Piano Transcription}, 
  author={Rainer Kelz and Matthias Dorfer and Filip Korzeniowski and Sebastian Böck and Andreas Arzt and Gerhard Widmer},
  year={2016},
  eprint={1612.05153},
  archivePrefix={arXiv},
  primaryClass={cs.SD}
}

@article{smaragdis2003nmf,
  author = {Smaragdis, Paris and Brown, Judith},
  year = {2003},
  month = {11},
  pages = {177 - 180},
  title = {Non-negative matrix factorization for polyphonic music transcription},
  isbn = {0-7803-7850-4},
  journal = {Proceedings of IEEE Workshop on Applications of Signal Processing to Audio and Acoustics},
  doi = {10.1109/ASPAA.2003.1285860}
}

@article{lee1999learning,
  author = {Lee, D. and Seung, H.},
  year = {1999},
  month = {10},
  pages = {788-791},
  title = {Learning the parts of objects by non-negative matrix factorization},
  journal = {Nature},
  volume = {401},
  doi = {10.1038/44565}
}

@article{sigtia2016endtoend,
  author = {Sigtia, Siddharth and Benetos, Emmanouil and Dixon, Simon},
  journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
  title = {An End-to-End Neural Network for Polyphonic Piano Music Transcription},
  year = {2016},
  volume = {24},
  number = {5},
  pages = {927-939},
  doi = {10.1109/TASLP.2016.2533858}
}

@INPROCEEDINGS{schluter2014onsetcnn,
  author={Schlüter, Jan and Böck, Sebastian},
  booktitle={2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, 
  title={Improved musical onset detection with Convolutional Neural Networks}, 
  year={2014},
  volume={},
  number={},
  pages={6979-6983},
  doi={10.1109/ICASSP.2014.6854953}
}

@INPROCEEDINGS{humphrey2012rethinking,
  author={Humphrey, Eric J. and Bello, Juan P.},
  booktitle={2012 11th International Conference on Machine Learning and Applications},
  title={Rethinking Automatic Chord Recognition with Convolutional Neural Networks},
  year={2012},
  volume={2},
  number={},
  pages={357-362},
  doi={10.1109/ICMLA.2012.220}
}

@ARTICLE{su2015spectral,
  author={Su, Li and Yang, Yi-Hsuan},
  journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing}, 
  title={Combining Spectral and Temporal Representations for Multipitch Estimation of Polyphonic Music}, 
  year={2015},
  volume={23},
  number={10},
  pages={1600-1612},
  doi={10.1109/TASLP.2015.2442411}
}

@misc{hawthorne2018onsets,
  title={Onsets and Frames: Dual-Objective Piano Transcription}, 
  author={Curtis Hawthorne and Erich Elsen and Jialin Song and Adam Roberts and Ian Simon and Colin Raffel and Jesse Engel and Sageev Oore and Douglas Eck},
  year={2018},
  eprint={1710.11153},
  archivePrefix={arXiv},
  primaryClass={cs.SD}
}

@online{mirex,
  title = {MIREX Wiki},
  date = {2021-06},
  url = {https://www.music-ir.org/mirex/wiki/MIREX_HOME},
  urldate = {2021-08-04}
}

@article{maps_orig,
  author = {Emiya, Valentin and Bertin, Nancy and David, Bertrand and Badeau, Roland},
  year = {2010},
  month = {07},
  pages = {11},
  title = {MAPS - A piano database for multipitch estimation and automatic transcription of music}
}
@article{maps,
  author = {Emiya, Valentin and Badeau, Roland and David, Bertrand},
  year = {2010},
  month = {09},
  pages = {1643 - 1654},
  title = {Multipitch Estimation of Piano Sounds Using a New Probabilistic Spectral Smoothness Principle},
  volume = {18},
  journal = {Audio, Speech, and Language Processing, IEEE Transactions on},
  doi = {10.1109/TASL.2009.2038819}
}

@article{brown1991cqt,
  author = {Brown, Judith C.},
  title = {Calculation of a constant Q spectral transform},
  journal = {The Journal of the Acoustical Society of America},
  volume = {89},
  number = {1},
  pages = {425-434},
  year = {1991},
  doi = {10.1121/1.400476},
  URL = {https://doi.org/10.1121/1.400476},
  eprint = {https://doi.org/10.1121/1.400476}
}

@misc{choi2021comparison,
  title={A Comparison of Audio Signal Preprocessing Methods for Deep Neural Networks on Music Tagging}, 
  author={Keunwoo Choi and György Fazekas and Kyunghyun Cho and Mark Sandler},
  year={2021},
  eprint={1709.01922},
  archivePrefix={arXiv},
  primaryClass={cs.SD}
}

@book{moore2012psy,
  author = {Brian C. J. Moore},
  title = {An Introduction to the Psychology of Hearing},
  year = {2012},
  publisher = {Brill}
}

@inproceedings{mcfee2015librosa,
  author = {McFee, Brian and Raffel, Colin and Liang, Dawen and Ellis, Daniel and Mcvicar, Matt and Battenberg, Eric and Nieto, Oriol},
  year = {2015},
  month = {01},
  pages = {18-24},
  title = {librosa: Audio and Music Signal Analysis in Python},
  publisher = {Proceedings of the 14th python in science conference},
  doi = {10.25080/Majora-7b98e3ed-003}
}

@article{raffael2014pretty_midi,
  author = {Raffel, Colin and Ellis, Daniel P. W.},
  title = {Intuitive Analysis, Creation and Manipulation of MIDI Data with pretty\_midi},
  journal = {Proceedings of the 15th International Conference on Music Information Retrieval Late Breaking and Demo Papers},
  year = {2014},
  pages = {84-93}
}

@misc{tensorflow2015whitepaper,
  title={TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems},
  url={https://www.tensorflow.org/},
  note={Software available from tensorflow.org},
  author={Mart\'in~Abadi and Ashish~Agarwal and Paul~Barham and Eugene~Brevdo and Zhifeng~Chen and Craig~Citro and Greg~S.~Corrado and Andy~Davis and Jeffrey~Dean and Matthieu~Devin and Sanjay~Ghemawat and Ian~Goodfellow and Andrew~Harp and Geoffrey~Irving and Michael~Isard and Yangqing Jia and Rafal~Jozefowicz and Lukasz~Kaiser and Manjunath~Kudlur and Josh~Levenberg and Dandelion~Man\'e and Rajat~Monga and Sherry~Moore and Derek~Murray and Chris~Olah and Mike~Schuster and Jonathon~Shlens and Benoit~Steiner and Ilya~Sutskever and Kunal~Talwar and Paul~Tucker and Vincent~Vanhoucke and Vijay~Vasudevan and Fernanda~Vi\'egas and Oriol~Vinyals and Pete~Warden and Martin~Wattenberg and Martin~Wicke and Yuan~Yu and Xiaoqiang~Zheng},
  year={2015},
  urldate = {2021-08-04}
}

@article{nitish2014dropout,
  author = {Nitish Srivastava and Geoffrey Hinton and Alex Krizhevsky and Ilya Sutskever and Ruslan Salakhutdinov},
  title = {Dropout: A Simple Way to Prevent Neural Networks from Overfitting},
  journal = {Journal of Machine Learning Research},
  year = {2014},
  volume = {15},
  number = {56},
  pages = {1929-1958},
  url = {http://jmlr.org/papers/v15/srivastava14a.html}
}

@inproceedings{monti2000monophonic,
  author = {Giuliano Monti and Mark Sandler},
  title = {Monophonic transcription with autocorrelation},
  booktitle = {Proceedings of the COST G-6 Conference on digital audio effects (DAFX-00},
  year = {2000},
  pages = {2000--257}
}

@misc{kingma2017adam,
  title={Adam: A Method for Stochastic Optimization}, 
  author={Diederik P. Kingma and Jimmy Ba},
  year={2017},
  eprint={1412.6980},
  archivePrefix={arXiv}
}

@phdthesis{moorer1975digital,
  title = {On the Segmentation and Analysis of Continuous Musical Sound by Digital Computer},
  volume = {Ph.D.},
  number = {STAN-M-3},
  year = {1975},
  school = {Stanford University},
  address = {Stanford, CA},
  keywords = {analysis, continuous musical sound, digital computer, segmentation},
  url = {https://ccrma.stanford.edu/files/papers/stanm3.pdf},
  author = {Moorer, James A.},
  urldate = {2021-08-08}
}

@article{katayose1989kensei,
  ISSN = {01489267, 15315169},
  URL = {http://www.jstor.org/stable/3679555},
  author = {Haruhiro Katayose and Seiji Inokuchi},
  journal = {Computer Music Journal},
  number = {4},
  pages = {72--77},
  publisher = {The MIT Press},
  title = {The Kansei Music System},
  volume = {13},
  year = {1989}
}

@phdthesis{hawley1993structure,
  title = {Structure out of sound},
  volume = {Ph.D.},
  number = {},
  year = {1993},
  school = {Massachusetts Institute of Technology},
  address = {},
  keywords = {Architecture. Program in Media Arts and Sciences},
  url = {http://hdl.handle.net/1721.1/29068},
  author = {Hawley, Michael Jerome},
  urldate = {2021-08-08}
}

@article{marolt2004sonic,
  title={A connectionist approach to automatic transcription of polyphonic piano music},
  author={Marolt, Matija},
  journal={IEEE Transactions on Multimedia},
  volume={6},
  number={3},
  pages={439--449},
  year={2004},
  publisher={IEEE}
}

@INPROCEEDINGS{bock2012rnn,
  author={Böck, Sebastian and Schedl, Markus},
  booktitle={2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, 
  title={Polyphonic piano note transcription with recurrent neural networks}, 
  year={2012},
  volume={},
  number={},
  pages={121-124},
  doi={10.1109/ICASSP.2012.6287832}
}

@inproceedings{sigtia2015hybrid,
  author = {Sigtia, Siddharth and Benetos, Emmanouil and Boulanger-Lewandowski, Nicolas and Weyde, Tillman and Garcez, Artur and Dixon, Simon},
  year = {2015},
  month = {04},
  pages = {2061--2065},
  title = {A hybrid recurrent neural network for music transcription},
  doi = {10.1109/ICASSP.2015.7178333}
}

@article{poliner2007melody,
  author = {Poliner, Graham and Ellis, Daniel and Ehmann, Andreas 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}
}

@inproceedings{dressler2005extraction,
  title={Extraction of the melody pitch contour from polyphonic audio},
  author={Dressler, Karin},
  booktitle={Proc. 6th International Conference on Music Information Retrieval},
  volume={110},
  year={2005},
  organization={Citeseer},
  doi = {10.1.1.122.7773}
}

@misc{kwon2020polyphonic,
  title={Polyphonic Piano Transcription Using Autoregressive Multi-State Note Model}, 
  author={Taegyun Kwon and Dasaem Jeong and Juhan Nam},
  year={2020},
  eprint={2010.01104},
  archivePrefix={arXiv},
  primaryClass={eess.AS}
}

@inproceedings{kelz2019deep,
  title={Deep polyphonic ADSR piano note transcription},
  author={Kelz, Rainer and Böck, Sebastian and Widmer, Gerhard},
  booktitle={ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={246--250},
  year={2019},
  organization={IEEE}
}