UvicThesis.bib

@misc{musdb18-hq,
  author       = {Rafii, Zafar and
                  Liutkus, Antoine and
                  Fabian-Robert St{\"o}ter and
                  Mimilakis, Stylianos Ioannis and
                  Bittner, Rachel},
  title        = {{MUSDB18-HQ} - an uncompressed version of MUSDB18},
  month        = dec,
  year         = 2019,
  doi          = {10.5281/zenodo.3338373},
  note          = {\url{https://doi.org/10.5281/zenodo.3338373}}
}

@techreport{kabal2002examination,
  title={{An examination and interpretation of ITU-R BS. 1387: Perceptual evaluation of audio quality}},
  author={Kabal, Peter and others},
  institution={TSP Lab, Dept. Electrical \& Computer Engineering, McGill University},
  pages={1--89},
  year={2002}
}

@ARTICLE{Rafii2013repet,
    author={Rafii, Zafar and Pardo, Bryan},  
    journal={IEEE Transactions on Audio, Speech, and Language Processing},   
    title={{REpeating Pattern Extraction Technique (REPET): A Simple Method for Music/Voice Separation}},   
    year={2013},  
    volume={21},  
    number={1},  
    pages={73-84},  
    note={\url{https://doi.org/10.1109/TASL.2012.2213249}}
}

@article{Ahmed1974DCT,
  author={Ahmed, N. and Natarajan, T. and Rao, K.R.},
  journal={IEEE Transactions on Computers}, 
  title={{Discrete Cosine Transform}}, 
  year={1974},
  volume={C-23},
  number={1},
  pages={90-93},
  note={\url{https://doi.org/10.1109/T-C.1974.223784}}
}

@inproceedings{mcfee2015librosa,
  title={librosa: Audio and music signal analysis in python},
  author={McFee, Brian and Raffel, Colin and Liang, Dawen and Ellis, Daniel PW and McVicar, Matt and Battenberg, Eric and Nieto, Oriol},
  booktitle={Proceedings of the 14th python in science conference},
  volume={8},
  year={2015}
}

@techreport{Deutsch1996rfc1951,
	series =	{Request for Comments},
	number =	1951,
	howpublished =	{RFC 1951},
	institution =	{RFC Editor},
	doi =		{10.17487/RFC1951},
	note =		{\url{https://www.rfc-editor.org/info/rfc1951}},
        author =	{L. Peter Deutsch},
	title =		{{DEFLATE Compressed Data Format Specification version 1.3}},
	pagetotal =	17,
	year =		1996,
	month =		may,
	doi =       {10.17487/RFC1951},
	abstract =	{This specification defines a lossless compressed data format that compresses data using a combination of the LZ77 algorithm and Huffman coding, with efficiency comparable to the best currently available general-purpose compression methods. This memo provides information for the Internet community. This memo does not specify an Internet standard of any kind.},
}

@ARTICLE{Princen1986TDAC,
    author={Princen, J. and Bradley, A.}, 
    journal={IEEE Transactions on Acoustics, Speech, and Signal Processing},
    title={Analysis/Synthesis filter bank design based on time domain aliasing cancellation},
    year={1986},
    volume={34},
    number={5},
    pages={1153-1161},
    note={\url{https://doi.org/10.1109/TASSP.1986.1164954}}
}

@misc{christopher_montgomery_next_2013,
	title = {next generation video: {Introducing} {Daala}},
	howpublished = {\url{https://people.xiph.org/~xiphmont/demo/daala/demo1.shtml}},
	note = "Online; Accessed: 2022-06-12",
	journal = {Xiph.org},
	author = {Montgomery, Christopher},
	day = 30,
	month = jun,
	year = {2013},
}

@misc{werner2020mdct,
  author = {Werner, Nils},
  title = {{MDCT Python Package}},
  year = {2020},
  publisher = {GitHub},
  journal = {GitHub Repository},
  howpublished = {\url{http://github.com/nils-werner/mdct}},
  note = {GitHub Repository; commit: 3eb8915}
}

@Article{         harris2020array,
 title         = {Array programming with {NumPy}},
 author        = {Charles R. Harris and K. Jarrod Millman and St{\'{e}}fan J.
                 van der Walt and Ralf Gommers and Pauli Virtanen and David
                 Cournapeau and Eric Wieser and Julian Taylor and Sebastian
                 Berg and Nathaniel J. Smith and Robert Kern and Matti Picus
                 and Stephan Hoyer and Marten H. van Kerkwijk and Matthew
                 Brett and Allan Haldane and Jaime Fern{\'{a}}ndez del
                 R{\'{i}}o and Mark Wiebe and Pearu Peterson and Pierre
                 G{\'{e}}rard-Marchant and Kevin Sheppard and Tyler Reddy and
                 Warren Weckesser and Hameer Abbasi and Christoph Gohlke and
                 Travis E. Oliphant},
 year          = {2020},
 month         = sep,
 journal       = {Nature},
 volume        = {585},
 number        = {7825},
 pages         = {357--362},
 doi           = {10.1038/s41586-020-2649-2},
 publisher     = {Springer Science and Business Media {LLC}},
 note = {\url{https://doi.org/10.1038/s41586-020-2649-2}}
}


@misc{michael_jackson_billie_1982,
	title = {Billie {Jean}, {Thriller Album}},
	howpublished = {\url{https://www.youtube.com/watch?v=OZGtRvYF-A4}},
	note = {YouTube Video; Accessed: 2022-06-20},
	author = {Michael Jackson},
	year = {1982},
}

@ARTICLE{Shannon1948Bell,
  author={Shannon, C. E.},
  journal={The Bell System Technical Journal}, 
  title={A mathematical theory of communication}, 
  year={1948},
  volume={27},
  number={3},
  pages={379-423},
  note={\url{https://doi.org/10.1002/j.1538-7305.1948.tb01338.x}}
}

@ARTICLE{Huffman1952IRE,
  author={Huffman, David A.},
  journal={Proceedings of the IRE}, 
  title={{A Method for the Construction of Minimum-Redundancy Codes}}, 
  year={1952},
  volume={40},
  number={9},
  pages={1098-1101},
  note={\url{https://doi.org/10.1109/JRPROC.1952.273898}}
}

@misc{FCC_broadband_2011,
	title = {Broadband {Speed} {Guide}},
	howpublished = "\url{https://www.fcc.gov/consumers/guides/broadband-speed-guide}",
	abstract = {Compare typical online activities with the minimum download speed (Megabits per second, or Mbps) needed for adequate performance for each application.},
	language = {en},
	note = "Online; Accessed: 2022-06-27",
	month = aug,
	year = {2011},
	author = {Federal Communications Commission}
}

@misc{speedtest,
	title = {Speedtest {Global} {Index} – {Internet} {Speed} around the world},
	howpublished = "\url{https://www.speedtest.net/global-index}",
	abstract = {Find out which countries have the fastest internet speeds in the world. View global monthly comparisons of fixed and mobile internet speeds.},
	language = {en},
	note = "Online; Accessed: 2022-06-27",
	author = {Speedtest\textsuperscript{\textcopyright} by Ookla\textsuperscript{\textcopyright}}
}


@article{ravelli_union_2008,
	title = {Union of {MDCT} {Bases} for {Audio} {Coding}},
	volume = {16},
	issn = {1558-7924},
	doi = {10.1109/TASL.2008.2004290},
	abstract = {This paper investigates the use of sparse overcomplete decompositions for audio coding. Audio signals are decomposed over a redundant union of modified discrete cosine transform (MDCT) bases having eight different scales. This approach produces a sparser decomposition than the traditional MDCT-based orthogonal transform and allows better coding efficiency at low bitrates. Contrary to state-of-the-art low bitrate coders, which are based on pure parametric or hybrid representations, our approach is able to provide transparency. Moreover, we use a bitplane encoding approach, which provides a fine-grain scalable coder that can seamlessly operate from very low bitrates up to transparency. Objective evaluation, as well as listening tests, show that the performance of our coder is significantly better than a state-of-the-art transform coder at very low bitrates and has similar performance at high bitrates. We provide a link to test soundfiles and source code to allow better evaluation and reproducibility of the results.},
	number = {8},
	journal = {IEEE Transactions on Audio, Speech, and Language Processing},
	author = {Ravelli, Emmanuel and Richard, Gal and Daudet, Laurent},
	month = nov,
	year = {2008},
	note = {Conference Name: IEEE Transactions on Audio, Speech, and Language Processing. \url{https://doi.org/10.1109/TASL.2008.2004290}},
	keywords = {Acoustic testing, Audio coding, Bit rate, Discrete cosine transforms, Discrete transforms, matching pursuit, Matching pursuit algorithms, MPEG 4 Standard, Parametric statistics, Reproducibility of results, scalable coding, signal representations, Signal representations, sparse representations},
	pages = {1361--1372}
}

@article{ravelli_audio_2010,
	title = {Audio {Signal} {Representations} for {Indexing} in the {Transform} {Domain}},
	volume = {18},
	issn = {1558-7924},
	doi = {10.1109/TASL.2009.2025099},
	abstract = {Indexing audio signals directly in the transform domain can potentially save a significant amount of computation when working on a large database of signals stored in a lossy compression format, without having to fully decode the signals. Here, we show that the representations used in standard transform-based audio codecs (e.g., MDCT for AAC, or hybrid PQF/MDCT for MP3) have a sufficient time resolution for some rhythmic features, but a poor frequency resolution, which prevents their use in tonality-related applications. Alternatively, a recently developed audio codec based on a sparse multi-scale MDCT transform has a good resolution both for time- and frequency-domain features. We show that this new audio codec allows efficient transform-domain audio indexing for three different applications, namely beat tracking, chord recognition, and musical genre classification. We compare results obtained with this new audio codec and the two standard MP3 and AAC codecs, in terms of performance and computation time.},
	number = {3},
	journal = {IEEE Transactions on Audio, Speech, and Language Processing},
	author = {Ravelli, Emmanuel and Richard, Gaël and Daudet, Laurent},
	month = mar,
	year = {2010},
	note = {Conference Name: IEEE Transactions on Audio, Speech, and Language Processing. \url{https://doi.org/10.1109/TASL.2009.2025099}},
	keywords = {Audio coding, Signal representations, sparse representations, Audio databases, audio indexing, Code standards, Codecs, Decoding, Digital audio players, Frequency, Indexing, Signal resolution, Spatial databases, time–frequency representations},
	pages = {434--446},
}

@article{sinha_audio_1996,
	title = {Audio compression at low bit rates using a signal adaptive switched filterbank},
	volume = {2},
	doi = {10.1109/ICASSP.1996.543544},
	abstract = {A perceptual audio coder typically consists of a filter-bank which breaks the signal into its frequency components. These components are then quantized using a perceptual masking model. Previous efforts have indicated that a high resolution filter-bank, e.g., the modified discrete cosine transform (MDCT) with 1024 subbands, is able to minimize the bit rate requirements for most of the music samples. The high resolution MDCT, however, is not suitable for the encoding of non-stationary segments of music. A long/short resolution or "window" switching scheme has been employed to overcome this problem but it has certain inherent disadvantages which become prominent at lower bit rates ({\textless}64 kbps for stereo). We propose a novel switched filter-bank scheme which switches between a MDCT and a wavelet filter-bank based on the signal characteristics. A tree structured wavelet filter-bank with properly designed filters offers natural advantages for the representation of non-stationary segments such as attacks. Furthermore, it allows for the optimum exploitation of perceptual irrelevancies.},
	journal = {1996 {IEEE} {International} {Conference} on {Acoustics}, {Speech}, and {Signal} {Processing} {Conference} {Proceedings}},
	author = {Sinha, D. and Johnston, J.D.},
	month = may,
	year = {1996},
	note = {ISSN: 1520-6149, \url{https://doi.org/10.1109/ICASSP.1996.543544}},
	keywords = {Bit rate, Discrete cosine transforms, Frequency, Signal resolution, Audio compression, Energy states, Filter bank, PAC, Signal design, Switches, Wideband},
	pages = {1053--1056 vol. 2}
}


@inproceedings{seetharaman_musicvoice_2017,
	title = {Music/{Voice} separation using the {2D} fourier transform},
	doi = {10.1109/WASPAA.2017.8169990},
	abstract = {Audio source separation is the act of isolating sound sources in an audio scene. One application of source separation is singing voice extraction. In this work, we present a novel approach for music/voice separation that uses the 2D Fourier Transform (2DFT). Our approach leverages how periodic patterns manifest in the 2D Fourier Transform and is connected to research in biological auditory systems as well as image processing. We find that our system is very simple to describe and implement and competitive with existing unsupervised source separation approaches that leverage similar assumptions.},
	booktitle = {2017 {IEEE} {Workshop} on {Applications} of {Signal} {Processing} to {Audio} and {Acoustics} ({WASPAA})},
	author = {Seetharaman, Prem and Pishdadian, Fatemeh and Pardo, Bryan},
	month = oct,
	year = {2017},
	note = {ISSN: 1947-1629, \url{https://doi.org/10.1109/WASPAA.2017.8169990}},
	keywords = {2DFT, Audio source separation, auditory scene analysis, automatic karaoke, foreground/background separation, Fourier transforms, image processing, Image processing, singing voice extraction, Source separation, Spectrogram, Time-frequency analysis, Two dimensional displays},
	pages = {36--40}
}

@inproceedings{rafii_musicvoice_2012,
  title={{Music/Voice Separation Using the Similarity Matrix.}},
  author={Rafii, Zafar and Pardo, Bryan},
  booktitle={ISMIR},
  pages={583--588},
  year={2012}
}

@article{van2016snare,
  title={Snare Drum Performance Motion Analysis},
  author={Van Rooyen, Robert and Schloss, Andrew and Tzanetakis, George},
  journal={New Instruments for Musical Expression},
  year={2016}
}

@article{mokry2020audio,
  title={Audio inpainting: Revisited and reweighted},
  author={Mokr{\`y}, Ond{\v{r}}ej and Rajmic, Pavel},
  journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
  volume={28},
  pages={2906--2918},
  year={2020},
  publisher={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, \url{https://doi.org/10.21105/joss.02154}}
}

@article{yan2017learning,
  title={Learning networking by reproducing research results},
  author={Yan, Lisa and McKeown, Nick},
  journal={ACM SIGCOMM Computer Communication Review},
  volume={47},
  number={2},
  pages={19--26},
  year={2017},
  publisher={ACM New York, NY, USA}
}

@article{lantz2015mininet,
  title={A mininet-based virtual testbed for distributed SDN development},
  author={Lantz, Bob and O'Connor, Brian},
  journal={ACM SIGCOMM Computer Communication Review},
  volume={45},
  number={4},
  pages={365--366},
  year={2015},
  publisher={ACM New York, NY, USA}
}

@book{heller2013reproducible,
  title={Reproducible network research with high-fidelity emulation},
  author={Heller, Brandon},
  year={2013},
  publisher={Stanford University}
}

@inproceedings{handigol2012reproducible,
  title={Reproducible network experiments using container-based emulation},
  author={Handigol, Nikhil and Heller, Brandon and Jeyakumar, Vimalkumar and Lantz, Bob and McKeown, Nick},
  booktitle={Proceedings of the 8th international conference on Emerging networking experiments and technologies},
  pages={253--264},
  year={2012}
}

@inproceedings{lantz2010network,
  title={A network in a laptop: rapid prototyping for software-defined networks},
  author={Lantz, Bob and Heller, Brandon and McKeown, Nick},
  booktitle={Proceedings of the 9th ACM SIGCOMM Workshop on Hot Topics in Networks},
  pages={1--6},
  year={2010}
}

@inproceedings{chafe2004effect,
  title={Effect of time delay on ensemble accuracy},
  author={Chafe, Chris and Gurevich, Michael and Leslie, Grace and Tyan, Sean},
  booktitle={Proceedings of the international symposium on musical acoustics},
  volume={31},
  pages={46},
  year={2004},
  organization={ISMA Nara}
}

@article{rottondi2016overview,
  title={An overview on networked music performance technologies},
  author={Rottondi, Cristina and Chafe, Chris and Allocchio, Claudio and Sarti, Augusto},
  journal={IEEE Access},
  volume={4},
  pages={8823--8843},
  year={2016},
  publisher={IEEE}
}

@article{bosi1997aac,
author={bosi, marina and brandenburg, karlheinz and quackenbush, schuyler and fielder, louis and akagiri, kenzo and fuchs, hendrik and dietz, martin},
journal={journal of the audio engineering society},
title={{ISO/IEC MPEG-2 Advanced Audio Coding}},
year={1997},
volume={45},
number={10},
pages={789-814},
doi={},
month={october},}

@article{brinker2002parametric,
author={Brinker, Den and Albertus, C. and Schuijers, Erik and Oomen, Werner},
journal={Journal of the audio engineering society},
title={Parametric coding for high-quality audio},
year={2002},
month={april},
}

@inproceedings{dietz2002SBR,
  title={Spectral Band Replication, a novel approach in audio coding},
  author={Dietz, Martin and Liljeryd, Lars and Kjorling, Kristofer and Kunz, Oliver},
  booktitle={Audio Engineering Society Convention 112},
  year={2002},
  organization={Audio Engineering Society}
}

@article{MUSHRA,
  title={{1534-1: Method for the subjective assessment of intermediate quality levels of coding systems (MUSHRA)}},
  author={ITU-R},
  journal={International Telecommunication Union},
  year={2003}
}

@article{chafe2010effect,
  title={Effect of temporal separation on synchronization in rhythmic performance},
  author={Chafe, Chris and Caceres, Juan-Pablo and Gurevich, Michael},
  journal={Perception},
  volume={39},
  number={7},
  pages={982--992},
  year={2010},
  publisher={SAGE Publications Sage UK: London, England}
}

@article{bartlette2006effect,
  title={Effect of network latency on interactive musical performance},
  author={Bartlette, Christopher and Headlam, Dave and Bocko, Mark and Velikic, Gordana},
  journal={Music Perception},
  volume={24},
  number={1},
  pages={49--62},
  year={2006},
  publisher={University of California Press USA}
}

@ARTICLE{RLE,
  author={Robinson, A.H. and Cherry, C.},
  journal={Proceedings of the IEEE}, 
  title={Results of a prototype television bandwidth compression scheme}, 
  year={1967},
  volume={55},
  number={3},
  pages={356-364},
  note={\url{https://doi.org/10.1109/PROC.1967.5493}}
}

@article{rissanen1976arithmetic,
  title={Generalized Kraft inequality and arithmetic coding},
  author={Rissanen, Jorma J},
  journal={IBM Journal of research and development},
  volume={20},
  number={3},
  pages={198--203},
  year={1976},
  publisher={IBM}
}

@ARTICLE{LZ77,
  author={Ziv, J. and Lempel, A.},
  journal={IEEE Transactions on Information Theory}, 
  title={A universal algorithm for sequential data compression}, 
  year={1977},
  volume={23},
  number={3},
  pages={337-343},
  note={\url{https://doi.org/10.1109/TIT.1977.1055714}}
}

@ARTICLE{LZ78,  author={Ziv, J. and Lempel, A.},  journal={IEEE Transactions on Information Theory},   title={Compression of individual sequences via variable-rate coding},   year={1978},  volume={24},  number={5},  pages={530-536},
  note={\url{https://doi.org/10.1109/TIT.1978.1055934}}
}

@ARTICLE{LZW,  author={Welch},  journal={Computer},   title={A Technique for High-Performance Data Compression},   year={1984},  volume={17},  number={6},  pages={8-19},
  note={\url{https://doi.org/10.1109/MC.1984.1659158}}
}

@article{burrows1994block,
  title={A block-sorting lossless data compression algorithm},
  author={Burrows, Michael and Wheeler, David J},
  year={1994},
  journal={Citeseer}
}

@misc{igor_pavlov_1998_lzma,
	title = {{LZMA} {SDK} ({Software} {Development} {Kit})},
	howpublished = {\url{https://www.7-zip.org/sdk.html}},
	author = {{Igor Pavlov}},
	year = 1998,
	note = {Online; Accessed: 2022-06-30}
}

@techreport{mpeg1-1993,
	type = {Standard},
	title = {Information technology — {Coding} of moving pictures and associated audio for digital storage media at up to about 1,5 {Mbit}/s — {Part} 3: {Audio}},
	shorttitle = {{ISO}/{IEC} 11172-3},
	language = {en},
	number = {35.040.40},
	institution = {International Organization for Standardization},
	author = {{ISO/IEC JTC 1/SC 29}},
	month = aug,
	year = {1993},
}

@techreport{mpeg2-1995,
	type = {Standard},
	title = {Information technology — {Generic} coding of moving pictures and associated audio information — {Part} 3: {Audio}},
	shorttitle = {{ISO}/{IEC} 13818-3},
	language = {en},
	number = {35.040.40},
	institution = {International Organization for Standardization},
	author = {{ISO/IEC JTC 1/SC 29}},
	month = may,
	year = {1995},
}

@techreport{mpeg4-2001,
	type = {Standard},
	title = {Information technology — {Coding} of audio-visual objects — {Part} 3: {Audio}},
	shorttitle = {{ISO}/{IEC} 14496-3},
	language = {en},
	number = {35.040.40},
	institution = {International Organization for Standardization},
	author = {{ISO/IEC JTC 1/SC 29}},
	month = dec,
	year = {2001},
}

@techreport{meares_report_1998,
	title = {Report on the {MPEG}-2 {AAC} {Stereo} {Verification} {Tests}},
	language = {en},
	author = {Meares, David and Watanabe, Kaoru and Scheirer, Eric},
	month = feb,
	year = {1998},
	pages = {48},
    institution = {International Organization for Standardization},
}

@misc{coalson_2001_flac,
	title = {{FLAC} - documentation},
	howpublished = {\url{https://xiph.org/flac/documentation_format_overview.html}},
	note = {Online; Accessed: 2022-06-30},
	author = {Coalson, Josh and {Xiph.Org Foundation}},
	year = {2001}
}

@article{liebchen_2005_ALC,
	title = {The {MPEG}-4 {Audio} {Lossless} {Coding} ({ALS}) {Standard} - {Technology} and {Applications}},
	language = {en},
	journal = {New York},
	author = {Liebchen, Tilman and Moriya, Takehiro and Harada, Noboru and Kamamoto, Yutaka and Reznik, Yuriy A},
	year = {2005},
	pages = {14},
}

@article{PEAQ,
  title={{1387: Method for objective measurements of perceived audio quality (PEAQ)}},
  author={ITU-R},
  journal={International Telecommunication Union},
  volume={1387},
  year={2001}
}

@article{huber2006pemo,
  title={{PEMO-Q—A new method for objective audio quality assessment using a model of auditory perception}},
  author={Huber, Rainer and Kollmeier, Birger},
  journal={IEEE Transactions on audio, speech, and language processing},
  volume={14},
  number={6},
  pages={1902--1911},
  year={2006},
  publisher={IEEE}
}

@article{pesq,
	title = {{P}.862 : {Perceptual} evaluation of speech quality ({PESQ}): {An} objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs},
	author = {ITU-T},
    journal = {International Telecommunication Union},
	year = {2001},
}

@article{psqm,
	title = {{P}.861 : {Objective} quality measurement of telephone-band (300-3400 {Hz}) speech codecs},
	language = {en},
	author = {ITU-T},
    journal = {International Telecommunication Union},
	year = {1996},
	pages = {34},
}

@inproceedings{nmf,
	title = {Algorithms for {Non}-negative {Matrix} {Factorization}},
	volume = {13},
	booktitle = {Advances in {Neural} {Information} {Processing} {Systems}},
	publisher = {MIT Press},
	author = {Lee, Daniel and Seung, H. Sebastian},
	year = {2000}
}

@inproceedings{smaragdis2004non,
  title={Non-negative matrix factor deconvolution; extraction of multiple sound sources from monophonic inputs},
  author={Smaragdis, Paris},
  booktitle={International Conference on Independent Component Analysis and Signal Separation},
  pages={494--499},
  year={2004},
  organization={Springer}
}

@inproceedings{vembu2005separation,
  title={Separation of Vocals from Polyphonic Audio Recordings.},
  author={Vembu, Shankar and Baumann, Stephan},
  booktitle={ISMIR},
  pages={337--344},
  year={2005},
  organization={Citeseer}
}

@inproceedings{smaragdis2004discovering,
  title={Discovering auditory objects through non-negativity constraints},
  author={Smaragdis, Paris},
  booktitle={ISCA Tutorial and Research Workshop (ITRW) on Statistical and Perceptual Audio Processing},
  year={2004}
}

@inproceedings{rafii2011simple,
  title={A simple music/voice separation method based on the extraction of the repeating musical structure},
  author={Rafii, Zafar and Pardo, Bryan},
  booktitle={2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={221--224},
  year={2011},
  organization={IEEE}
}

@inproceedings{rafii2013online,
  title={Online REPET-SIM for real-time speech enhancement},
  author={Rafii, Zafar and Pardo, Bryan},
  booktitle={2013 IEEE International Conference on Acoustics, Speech and Signal Processing},
  pages={848--852},
  year={2013},
  organization={IEEE}
}

@inproceedings{nussl,
    author = {Ethan Manilow and Prem Seetharaman and Bryan Pardo},
    title = "The Northwestern University Source Separation Library",
    publisher = "Proceedings of the 19th International Society of Music Information Retrieval Conference ({ISMIR} 2018), Paris, France, September 23-27",
    year = 2018
}

@inproceedings{lutzky2004guideline,
  title={A guideline to audio codec delay},
  author={Lutzky, Manfred and Schuller, Gerald and Gayer, Marc and Kr{\"a}mer, Ulrich and Wabnik, Stefan},
  booktitle={Audio Engineering Society Convention 116},
  year={2004},
  organization={Audio Engineering Society}
}

@inproceedings{valin2009full,
  title={A full-bandwidth audio codec with low complexity and very low delay},
  author={Valin, Jean-Marc and Terriberry, Timothy B and Maxwell, Gregory},
  booktitle={2009 17th European Signal Processing Conference},
  pages={1254--1258},
  year={2009},
  organization={IEEE}
}

@article{valin2016high,
  title={High-quality, low-delay music coding in the opus codec},
  author={Valin, Jean-Marc and Maxwell, Gregory and Terriberry, Timothy B and Vos, Koen},
  journal={arXiv preprint arXiv:1602.04845},
  year={2016}
}

@article{carot2009fundamentals,
  title={Fundamentals and principles of musical telepresence},
  author={Car{\^o}t, Alexander and Werner, Christian},
  journal={Journal of Science and Technology of the Arts},
  volume={1},
  number={1},
  pages={26--37},
  year={2009}
}

@article{schuller2002perceptual,
  title={Perceptual audio coding using adaptive pre-and post-filters and lossless compression},
  author={Schuller, Gerald DT and Yu, Bin and Huang, Dawei and Edler, Bernd},
  journal={IEEE Transactions on Speech and Audio Processing},
  volume={10},
  number={6},
  pages={379--390},
  year={2002},
  publisher={IEEE}
}

@techreport{mpeg1-1993-video,
	type = {Standard},
	title = {Information technology — {Coding} of moving pictures and associated audio for digital storage media at up to about 1,5 {Mbit}/s — {Part} 2: {Video}},
	shorttitle = {{ISO}/{IEC} 11172-2},
	language = {en},
	number = {35.040.40},
	institution = {International Organization for Standardization},
	author = {{ISO/IEC JTC 1/SC 29}},
	month = aug,
	year = {1993},
}

@article{tarjano2022efficient,
  title={An Efficient Algorithm for Segmenting Quasi-Periodic Digital Signals Into Pseudo Cycles: Application in Lossy Audio Compression},
  author={Tarjano, Carlos and Pereira, Valdecy},
  journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
  volume={30},
  pages={1694--1703},
  year={2022},
  publisher={IEEE}
}

@article{cunningham2019subjective,
  title={Subjective evaluation of music compressed with the ACER codec compared to AAC, MP3, and uncompressed PCM},
  author={Cunningham, Stuart and McGregor, Iain},
  journal={International Journal of Digital Multimedia Broadcasting},
  volume={2019},
  year={2019},
  publisher={Hindawi}
}

@article{cunningham2014aceremix,
  title={ACERemix: A TOO| for Glitch Music Remix Production and},
  author={Cunningham, Stuart and Weinel, Jonathan and Griffiths, Darryl},
  year={2014}
}

@article{cunningham2014data,
  title={Data reduction of audio by exploiting musical repetition},
  author={Cunningham, Stuart and Grout, Vic},
  journal={Multimedia tools and applications},
  volume={72},
  number={3},
  pages={2299--2320},
  year={2014},
  publisher={Springer}
}

@article{cunningham2009audio,
  title={Audio compression exploiting repetition (ACER): Challenges and solutions},
  author={Cunningham, Stuart and Grout, Vic},
  year={2009},
  publisher={Glynd{\^w}r University Research Online}
}

@inproceedings{cunningham2013initial,
  title={Initial objective \& subjective evaluation of a similarity-based audio compression technique},
  author={Cunningham, Stuart and Weinel, Jonathan and Roberts, Shaun and Grout, Vic and Griffiths, Darryl},
  booktitle={Proceedings of the 8th Audio Mostly Conference},
  pages={1--6},
  year={2013}
}

@inproceedings{cunningham2005play,
  title={Play it Again, Babbage!--A Framework to Exploit Musical Repetition for High-Quality Audio Compression},
  author={Cunningham, Stuart and Grout, Vic and McGinn, John},
  booktitle={Proceedings of IADIS-International Conference on WWW/Internet, Lisbon, Portugal, 19th-22nd October},
  year={2005}
}

@inproceedings{cunningham2007advances,
  title={Advances in similarity-based audio compression},
  author={Cunningham, Stuart and Grout, Vic},
  booktitle={SEIN 2007: Proceedings of the Third Collaborative Research Symposium on Security, E-Learning, Internet and Networking},
  pages={129},
  year={2007},
  organization={Lulu. com}
}

@misc{github2022thesis,
  author = {Lotfaliei, Matin},
  title = {{MSc Thesis: A New Audio Compression Scheme that Leverages Repetition in Music}},
  year = {2022},
  publisher = {GitHub},
  journal = {GitHub Repository},
  howpublished = {\url{https://github.com/matinlotfali/audio-compression-repetition-music}}
}