managing-storing-sharing-paper/references.bib

@unpublished{solomon-data,
  TITLE = {{Long-form, child-centered audio-recordings collected in the Solomon Islands in 2019}},
  AUTHOR = {Walker, Sara and Grosjean, Paulina and Cristia, Alejandrina},
  NOTE = {unpublished private dataset},
  YEAR = {2019},
}

@article{soderstrom2021developing,
  title={Developing A Cross-Cultural Annotation System and MetaCorpus for Studying Infants’ Real World Language Experience},
  author={Soderstrom, Melanie and Casillas, Marisa and Bergelson, Elika and Rosemberg, Celia and Alam, Florencia and Warlaumont, Anne S and Bunce, John},
  journal={Collabra: Psychology},
  volume={7},
  number={1},
  pages={23445},
  year={2021},
  publisher={University of California Press}
}

@article{soska2021hyper,
  title={(Hyper) active Data Curation: A Video Case Study from Behavioral Science},
  author={Soska, Kasey and Xu, Melody and Gonzalez, Sandy and Hertzberg, Orit and Gilmore, Rick O and Tamis-LeMonda, Catherine and Adolph, Karen E},
  year={2021},
  journal={PsyArXiv},
  url={https://psyarxiv.com/89rcb/download?format=pdf}
}

@article{ear1,
  doi = {10.3758/bf03195410},
  url = {https://doi.org/10.3758/bf03195410},
  year = {2001},
  month = nov,
  publisher = {Springer Science and Business Media {LLC}},
  volume = {33},
  number = {4},
  pages = {517--523},
  author = {Matthias R. Mehl and James W. Pennebaker and D. Michael Crow and James Dabbs and John H. Price},
  title = {The Electronically Activated Recorder ({EAR}): A device for sampling naturalistic daily activities and conversations},
  journal = {Behavior Research Methods,  Instruments,  {\&} Computers}
}

@inproceedings{schuller2017interspeech,
  title={The Interspeech 2017 computational paralinguistics challenge: Addressee, cold \& snoring},
  author={Schuller, Bj{\"o}rn and Steidl, Stefan and Batliner, Anton and Bergelson, Elika and Krajewski, Jarek and Janott, Christoph and Amatuni, Andrei and Casillas, Marisa and Seidl, Amdanda and Soderstrom, Melanie and others},
  booktitle={Interspeech},
  year={2017}
}

@article{lenaeval1,
  title={A thorough evaluation of the Language Environment Analysis (LENA) system},
  author={Cristia, Alejandrina and Lavechin, Marvin and Scaff, Camila and Soderstrom, Melanie and Rowland, Caroline and R{\"a}s{\"a}nen, Okko and Bunce, John and Bergelson, Elika},
  year={2019},
  publisher={OSF Preprints},
  journal={Behavior Research Methods}
}
@article{boersma2006praat,
  title={Praat: doing phonetics by computer},
  author={Boersma, Paul},
  journal={http://www. praat. org/},
  year={2006}
}
@inproceedings{krishnamachari2021developing,
  title={Developing Neural Representations for Robust Child-Adult Diarization},
  author={Krishnamachari, Suchitra and Kumar, Manoj and Kim, So Hyun and Lord, Catherine and Narayanan, Shrikanth},
  booktitle={2021 IEEE Spoken Language Technology Workshop (SLT)},
  pages={590--597},
  year={2021},
  organization={IEEE}
}


@article{warlaumont2014social,
  title={A social feedback loop for speech development and its reduction in autism},
  author={Warlaumont, Anne S and Richards, Jeffrey A and Gilkerson, Jill and Oller, D Kimbrough},
  journal={Psychological science},
  volume={25},
  number={7},
  pages={1314--1324},
  year={2014},
  publisher={Sage Publications Sage CA: Los Angeles, CA}
}

@article{riad2020vocal,
  title={Vocal markers from sustained phonation in Huntington's Disease},
  author={Riad, Rachid and Titeux, Hadrien and Lemoine, Laurie and Montillot, Justine and Bagnou, Jennifer Hamet and Cao, Xuan Nga and Dupoux, Emmanuel and Bachoud-L{\'e}vi, Anne-Catherine},
  journal={Interspeech},
  year={2020}
}

@article{ear2,
  doi = {10.1037/0022-3514.84.4.857},
  url = {https://doi.org/10.1037/0022-3514.84.4.857},
  year = {2003},
  publisher = {American Psychological Association ({APA})},
  volume = {84},
  number = {4},
  pages = {857--870},
  author = {Matthias R. Mehl and James W. Pennebaker},
  title = {The sounds of social life: A psychometric analysis of students{\textquotesingle} daily social environments and natural conversations.},
  journal = {Journal of Personality and Social Psychology}
}
@book{macwhinney2000childes,
  title={The CHILDES project: The database},
  author={MacWhinney, Brian},
  volume={2},
  year={2000},
  publisher={Psychology Press}
}


@inproceedings{vandam2016homebank,
  title={HomeBank: An online repository of daylong child-centered audio recordings},
  author={VanDam, Mark and Warlaumont, Anne S and Bergelson, Elika and Cristia, Alejandrina and Soderstrom, Melanie and De Palma, Paul and MacWhinney, Brian},
  booktitle={Seminars in Speech and Language},
  volume={37},
  pages={128},
  year={2016},
  organization={NIH Public Access}
}

@article{christakis2009audible,
  title={Audible television and decreased adult words, infant vocalizations, and conversational turns: a population-based study},
  author={Christakis, Dimitri A and Gilkerson, Jill and Richards, Jeffrey A and Zimmerman, Frederick J and Garrison, Michelle M and Xu, Dongxin and Gray, Sharmistha and Yapanel, Umit},
  journal={Archives of pediatrics \& adolescent medicine},
  volume={163},
  number={6},
  pages={554--558},
  year={2009},
  publisher={American Medical Association}
}

@misc{warl,
  doi = {10.21415/T54S3C},
  url = {http://homebank.talkbank.org/access/Password/Warlaumont.html},
  author = {Warlaumont,  Anne},
  title = {HomeBank Warlaumont Corpus},
  publisher = {TalkBank},
  year = {2016}
}

@article{Nee2021,
  doi = {10.3765/plsa.v6i1.4967},
  url = {https://doi.org/10.3765/plsa.v6i1.4967},
  year = {2021},
  month = mar,
  publisher = {Linguistic Society of America},
  volume = {6},
  number = {1},
  pages = {213},
  author = {Julia Nee},
  title = {Understanding the effects of language revitalization workshops using long-format speech environment recordings},
  journal = {Proceedings of the Linguistic Society of America}
}

@article{casillas2019step,
    author = {Casillas, Marisa and Cristia, Alejandrina},
    title = "{A step-by-step guide to collecting and analyzing long-format speech environment (LFSE) recordings}",
    journal = {Collabra: Psychology},
    volume = {5},
    number = {1},
    year = {2019},
    month = {05},
    issn = {2474-7394},
    doi = {10.1525/collabra.209},
    url = {https://doi.org/10.1525/collabra.209},
    note = {24},
    eprint = {https://online.ucpress.edu/collabra/article-pdf/5/1/24/437539/209-3199-1-pb.pdf},
}

@article{lavechin2020opensource,
title={An open-source voice type classifier for child-centered daylong recordings},
author={Marvin Lavechin and Ruben Bousbib and Hervé Bredin and Emmanuel Dupoux and Alejandrina Cristia},
year={2020},
journal={Interspeech}
}

@article{rasanen2020,
  title={ALICE: An open-source tool for automatic measurement of phoneme, syllable, and word counts from child-centered daylong recordings},
  author={R{\"a}s{\"a}nen, Okko and Seshadri, Shreyas and Lavechin, Marvin and Cristia, Alejandrina and Casillas, Marisa},
  journal={Behavior Research Methods},
  pages={1--18},
  year={2020},
  publisher={Springer}
}

@inproceedings{AlFutaisi2019,
  doi = {10.1145/3340555.3353751},
  url = {https://doi.org/10.1145/3340555.3353751},
  year = {2019},
  month = oct,
  publisher = {{ACM}},
  author = {Najla Al Futaisi and Zixing Zhang and Alejandrina Cristia and Anne Warlaumont and Bjorn Schuller},
  title = {{VCMNet}: Weakly Supervised Learning for Automatic Infant Vocalisation Maturity Analysis},
  booktitle = {2019 International Conference on Multimodal Interaction}
}

@misc{pympi-1.70,
	author={Lubbers, Mart and Torreira, Francisco},
	title={pympi-ling: a {Python} module for processing {ELAN}s {EAF} and {Praat}s {TextGrid} annotation files.},
	howpublished={\url{https://pypi.python.org/pypi/pympi-ling}},
	year={2013-2021},
	note={Version 1.70}
}

@inproceedings{bird2020decolonising,
  title={Decolonising speech and language technology},
  author={Bird, Steven},
  booktitle={Proceedings of the 28th International Conference on Computational Linguistics},
  pages={3504--3519},
  year={2020}
}

@article{cychosz2021using,
  title={Using big data from long-form recordings to study development and optimize societal impact},
  author={Cychosz, Meg and Cristia, Alejandrina},
  year={2021},
  journal={OSF Preprints}
}

@article{Cychosz2020,
  doi = {10.3758/s13428-020-01365-9},
  url = {https://doi.org/10.3758/s13428-020-01365-9},
  year = {2020},
  month = feb,
  publisher = {Springer Science and Business Media {LLC}},
  volume = {52},
  number = {5},
  pages = {1951--1969},
  author = {Margaret Cychosz and Rachel Romeo and Melanie Soderstrom and Camila Scaff and Hillary Ganek and Alejandrina Cristia and Marisa Casillas and Kaya de Barbaro and Janet Y. Bang and Adriana Weisleder},
  title = {Longform recordings of everyday life: Ethics for best practices},
  journal = {Behavior Research Methods}
}

@misc{eaf-anonymizer-original,
  title={HomeBank ITS file anonymizer},
  url={https://github.com/HomeBankCode/ITS_annonymizer},
  journal={GitHub},
  author={Sarah MacEwan},
  year = {2019}
 }

@inproceedings{Casillas2017,
  author={Marisa Casillas and Elika Bergelson and Anne S. Warlaumont and Alejandrina Cristia and Melanie Soderstrom and Mark VanDam and Han Sloetjes},
  title={A New Workflow for Semi-Automatized Annotations: Tests with Long-Form Naturalistic Recordings of Childrens Language Environments},
  year=2017,
  booktitle={Proc. Interspeech 2017},
  pages={2098--2102},
  doi={10.21437/Interspeech.2017-1418},
  url={http://dx.doi.org/10.21437/Interspeech.2017-1418}
}

@article{Poldrack2014,
  doi = {10.1038/nn.3818},
  url = {https://doi.org/10.1038/nn.3818},
  year = {2014},
  month = oct,
  publisher = {Springer Science and Business Media {LLC}},
  volume = {17},
  number = {11},
  pages = {1510--1517},
  author = {Russell A Poldrack and Krzysztof J Gorgolewski},
  title = {Making big data open: data sharing in neuroimaging},
  journal = {Nature Neuroscience}
}

@misc{starter,
  doi = {10.17910/B7.390},
  url = {http://databrary.org/volume/390},
  author = {Bergelson, Elika and Warlaumont, Anne and Cristia, Alejandrina and Casillas, Marisa and Rosemberg, Celia and Soderstrom, Melanie and Rowland, Caroline and Durrant, Samantha and Bunce, John},
  title = {Starter-ACLEW},
  publisher = {Databrary},
  year = {2017},
  copyright = {Databrary Access Agreement}
}


@article{Perkel_2019,
	doi = {10.1038/d41586-019-01040-w},
	url = {https://doi.org/10.1038/d41586-019-01040-w},
	year = 2019,
	month = {apr},
	publisher = {Springer Science and Business Media {LLC}},
	volume = {568},
	number = {7750},
	pages = {131--132},
	author = {Jeffrey M. Perkel},
	title = {11 ways to avert a data-storage disaster},
	journal = {Nature}
}
@misc{ffmpeg,
  title={ffmpeg tool},
  author={ffmpeg{ }Developers},
  url={http://ffmpeg.org/},
  year={2021}
}
@article{Brase2009datacite,
  doi = {10.2139/ssrn.1639998},
  url = {https://doi.org/10.2139/ssrn.1639998},
  year = {2010},
  publisher = {Elsevier {BV}},
  author = {Jan Brase},
  title = {Datacite - A Global Registration Agency for Research Data},
  journal = {{SSRN} Electronic Journal}
}
@misc{robert2018pydub,
  title={Pydub},
  author={Robert, James and Webbie, Marc and others},
  year={2018},
  publisher={GitHub},
  url={http://pydub.com/}
}
@article{ryant2019second,
  title={The second dihard diarization challenge: Dataset, task, and baselines},
  author={Ryant, Neville and Church, Kenneth and Cieri, Christopher and Cristia, Alejandrina and Du, Jun and Ganapathy, Sriram and Liberman, Mark},
  journal={arXiv preprint arXiv:1906.07839},
  year={2019}
}

@article{ryant2018first,
  title={First DIHARD challenge evaluation plan},
  author={Ryant, Neville and Church, Kenneth and Cieri, Christopher and Cristia, Alejandrina and Du, Jun and Ganapathy, Sriram and Liberman, Mark},
  journal={2018, tech. Rep.},
  year={2018}
}

@article{ryant2020third,
  title={Third DIHARD Challenge Evaluation Plan},
  author={Ryant, Neville and Church, Kenneth and Cieri, Christopher and Du, Jun and Ganapathy, Sriram and Liberman, Mark},
  journal={arXiv preprint arXiv:2006.05815},
  year={2020}
}

@article{Wilkinson2016,
  doi = {10.1038/sdata.2016.18},
  url = {https://doi.org/10.1038/sdata.2016.18},
  year = {2016},
  month = mar,
  publisher = {Springer Science and Business Media {LLC}},
  volume = {3},
  number = {1},
  author = {Mark D. Wilkinson and Michel Dumontier and IJsbrand Jan Aalbersberg and Gabrielle Appleton and Myles Axton and Arie Baak and Niklas Blomberg and Jan-Willem Boiten and Luiz Bonino da Silva Santos and Philip E. Bourne and Jildau Bouwman and Anthony J. Brookes and Tim Clark and Merc{\`{e}} Crosas and Ingrid Dillo and Olivier Dumon and Scott Edmunds and Chris T. Evelo and Richard Finkers and Alejandra Gonzalez-Beltran and Alasdair J.G. Gray and Paul Groth and Carole Goble and Jeffrey S. Grethe and Jaap Heringa and Peter A.C 't Hoen and Rob Hooft and Tobias Kuhn and Ruben Kok and Joost Kok and Scott J. Lusher and Maryann E. Martone and Albert Mons and Abel L. Packer and Bengt Persson and Philippe Rocca-Serra and Marco Roos and Rene van Schaik and Susanna-Assunta Sansone and Erik Schultes and Thierry Sengstag and Ted Slater and George Strawn and Morris A. Swertz and Mark Thompson and Johan van der Lei and Erik van Mulligen and Jan Velterop and Andra Waagmeester and Peter Wittenburg and Katherine Wolstencroft and Jun Zhao and Barend Mons},
  title = {The {FAIR} Guiding Principles for scientific data management and stewardship},
  journal = {Scientific Data}
}

@misc{zenodo,
  doi = {10.25495/7GXK-RD71},
  url = {https://www.zenodo.org/},
  author = {{European Organization For Nuclear Research} and {OpenAIRE}},
  keywords = {FOS: Physical sciences, Publication, Dataset},
  language = {en},
  title = {Zenodo},
  publisher = {CERN},
  year = {2013}
}

@article {dataverse,
	title = {An Introduction to the Dataverse Network as an Infrastructure for Data Sharing},
	journal = {Sociological Methods and Research},
	volume = {36},
	year = {2007},
	pages = {173{\textendash}199},
	abstract = {We introduce a set of integrated developments in web application software, networking, data citation standards, and statistical methods designed to put some of the universe of data and data sharing practices on somewhat firmer ground. We have focused on social science data, but aspects of what we have developed may apply more widely. The idea is to facilitate the public distribution of persistent, authorized, and verifiable data, with powerful but easy-to-use technology, even when the data are confidential or proprietary. We intend to solve some of the sociological problems of data sharing via technological means, with the result intended to benefit both the scientific community and the sometimes apparently contradictory goals of individual researchers.},
	author = {Gary King}
}

@misc{pandas-software,
    author       = {The Pandas development team},
    title        = {pandas-dev/pandas: Pandas},
    month        = feb,
    year         = 2020,
    publisher    = {Zenodo},
    version      = {latest},
    doi          = {10.5281/zenodo.3509134},
    url          = {https://doi.org/10.5281/zenodo.3509134}
}

@InProceedings{pandas-paper,
  author    = { Wes McKinney },
  title     = { {D}ata {S}tructures for {S}tatistical {C}omputing in {P}ython },
  booktitle = { {P}roceedings of the 9th {P}ython in {S}cience {C}onference },
  pages     = { 56 - 61 },
  year      = { 2010 },
  editor    = { St\'efan van der Walt and Jarrod Millman },
  doi       = { 10.25080/Majora-92bf1922-00a }
}
@misc{gilkerson2008power,
  title={The power of talk (LENA Foundation Technical Report LTR-01-2)},
  author={Gilkerson, J and Richards, JA},
  year={2008},
  publisher={Retrieved from LENA Foundation: https://www.lena.org/wp-content/uploads/2016/07/LTR-01-2_PowerOfTalk.pdf}
}

@article{vandam2018vetting,
  title={Vetting Manual: Preparation of Recordings for Unrestricted Publication in HomeBank (Version 1.1)},
  author={VanDam, M and Warlaumont, A and MacWhinney, B and Soderstrom, M and Bergelson, E},
  journal={DOI: https://doi. org/10.21415/T56H4M},
  year={2018}
}

@article{broesch2020navigating,
  title={Navigating cross-cultural research: methodological and ethical considerations},
  author={Broesch, Tanya and Crittenden, Alyssa N and Beheim, Bret A and Blackwell, Aaron D and Bunce, John A and Colleran, Heidi and Hagel, Kristin and Kline, Michelle and McElreath, Richard and Nelson, Robin G and others},
  journal={Proceedings of the Royal Society B},
  volume={287},
  number={1935},
  pages={20201245},
  year={2020},
  publisher={The Royal Society}
}

@Article{10.12688/f1000research.10783.1,
AUTHOR = { Ghosh, SS and Poline, JB and Keator, DB and Halchenko, YO and Thomas, AG and Kessler, DA and Kennedy, DN},
TITLE = {A very simple, re-executable neuroimaging publication [version 1; peer review: 2 approved with reservations]
},
JOURNAL = {F1000Research},
VOLUME = {6},
YEAR = {2017},
NUMBER = {124},
DOI = {10.12688/f1000research.10783.1}
}

@Article{Eglen2017,
author={Eglen, Stephen J.
and Marwick, Ben
and Halchenko, Yaroslav O.
and Hanke, Michael
and Sufi, Shoaib
and Gleeson, Padraig
and Silver, R. Angus
and Davison, Andrew P.
and Lanyon, Linda
and Abrams, Mathew
and Wachtler, Thomas
and Willshaw, David J.
and Pouzat, Christophe
and Poline, Jean-Baptiste},
title={Toward standard practices for sharing computer code and programs in neuroscience},
journal={Nature Neuroscience},
year={2017},
month={Jun},
day={01},
volume={20},
number={6},
pages={770-773},
abstract={Computational techniques are central in many areas of neuroscience and are relatively easy to share. This paper describes why computer programs underlying scientific publications should be shared and lists simple steps for sharing. Together with ongoing efforts in data sharing, this should aid reproducibility of research.},
issn={1546-1726},
doi={10.1038/nn.4550},
url={https://doi.org/10.1038/nn.4550}
}
@article{xu2008lenatm,
  title={The lenaTM language environment analysis system: The interpretive time segments (its) file},
  author={Xu, D and Yapanel, U and Gray, S and Baer, CT},
  journal={LENA Research Foundation Technical Report LTR-04-2},
  year={2008}
}

@article{levin2021sensing,
  title={Sensing everyday activity: Parent perceptions and feasibility},
  author={Levin, Hannah I and Egger, Dominique and Andres, Lara and Johnson, Mckensey and Bearman, Sarah Kate and de Barbaro, Kaya},
  journal={Infant Behavior and Development},
  volume={62},
  pages={101511},
  year={2021},
  publisher={Elsevier}
}

@inproceedings{wittenburg2006elan,
  title={ELAN: a professional framework for multimodality research},
  author={Wittenburg, Peter and Brugman, Hennie and Russel, Albert and Klassmann, Alex and Sloetjes, Han},
  booktitle={5th International Conference on Language Resources and Evaluation (LREC 2006)},
  pages={1556--1559},
  year={2006}
}

@article{MacWhinney2000,
  doi = {10.1162/coli.2000.26.4.657},
  url = {https://doi.org/10.1162/coli.2000.26.4.657},
  year = {2000},
  month = dec,
  publisher = {{MIT} Press - Journals},
  volume = {26},
  number = {4},
  pages = {657},
  author = {Brian MacWhinney},
  title = {The {CHILDES} Project: Tools for Analyzing Talk (third edition): Volume I: Transcription format and programs,  Volume {II}: The database},
  journal = {Computational Linguistics}
}

@article{pub.1022076283,
 author = {Van Essen, David C. and Smith, Stephen M. and Barch, Deanna M. and Behrens, Timothy E.J. and Yacoub, Essa and Ugurbil, Kamil and Consortium, for the WU-Minn HCP},
 doi = {10.1016/j.neuroimage.2013.05.041},
 journal = {NeuroImage},
 keywords = {},
 number = {},
 pages = {62-79},
 title = {The WU-Minn Human Connectome Project: An overview},
 url = {http://europepmc.org/articles/pmc3724347?pdf=render},
 volume = {80},
 year = {2013}
}



@misc{vandam-day,
  doi = {10.21415/T5388S},
  url = {http://homebank.talkbank.org/access/Public/VanDam-5minute.html},
  author = {VanDam,  Mark},
  title = {HomeBank VanDam Public 5-minute Corpus},
  publisher = {TalkBank},
  year = {2015}
}

@misc{exelang-book,
  url = {https://bookdown.org/alecristia/exelang-book/},
  author = {Pisani, Sara and Gautheron, Lucas and Cristia, Alejandrina},
  title = {Long-form recordings: From A to Z},
  year = {2021}
}

@INPROCEEDINGS{zooniverse,
       author = {{Borne}, K.~D. and {Zooniverse Team}},
        title = "{The Zooniverse: A Framework for Knowledge Discovery from Citizen Science Data}",
     keywords = {0800 EDUCATION, 0815 EDUCATION / Informal education, 1914 INFORMATICS / Data mining, 1942 INFORMATICS / Machine learning},
    booktitle = {AGU Fall Meeting Abstracts},
         year = 2011,
       volume = {2011},
        month = dec,
          eid = {ED23C-0650},
       adsurl = {https://ui.adsabs.harvard.edu/abs/2011AGUFMED23C0650B},
      adsnote = {Provided by the SAO/NASA Astrophysics Data System}
}

@article{semenzin2020a,
  doi = {10.31219/osf.io/z6exv},
  url = {https://doi.org/10.31219/osf.io/z6exv},
  year = {2020},
  month = nov,
  publisher = {Center for Open Science},
  author = {Semenzin, Chiara and Hamrick, Lisa  and Seidl, Amanda and Lynne Kelleher, Bridgette and Cristia, Alejandrina},
  title = {Describing vocalizations in young children: A big data approach through citizen science annotation},
  journal = {}
}

@article{semenzin2020b,
  doi = {10.31219/osf.io/gpxf5},
  url = {https://doi.org/10.31219/osf.io/gpxf5},
  year = {2020},
  month = nov,
  publisher = {Center for Open Science},
  author = {Semenzin, Chiara and Hamrick, Lisa  and Seidl, Amanda and Lynne Kelleher, Bridgette and Cristia, Alejandrina},
  title = {Towards Large-Scale Data Annotation of Audio from Wearables: Validating Zooniverse Annotations of Infant Vocalization Types},
  journal = {}
}

@book{datalad_handbook,
  doi = {10.5281/ZENODO.3608612},
  url = {https://zenodo.org/record/3608612},
  author = {Wagner,  Adina S. and Waite,  Laura K. and Meyer,  Kyle and Heckner,  Marisa K. and Kadelka,  Tobias and Reuter,  Niels and Waite,  Alexander Q. and Poldrack,  Benjamin and Markiewicz,  Christopher J. and Halchenko,  Yaroslav O. and Vavra,  Peter and Chormai,  Pattarawat and Poline,  Jean-Baptiste and Paas,  Lya K. and Herholz,  Peer and Mochalski,  Lisa N. and Kraljevic,  Nevena and Wiersch,  Lisa and Hutton,  Alexandre and Hanke,  Michael},
  keywords = {data management,  book,  datalad,  version control,  teaching resource},
  title = {The DataLad Handbook},
  publisher = {Zenodo},
  year = {2020},
  copyright = {Creative Commons Attribution Share Alike 4.0 International}
}

@article{datalad_paper,
  doi = {10.21105/joss.03262},
  url = {https://doi.org/10.21105/joss.03262},
  year = {2021},
  month = jul,
  publisher = {The Open Journal},
  volume = {6},
  number = {63},
  pages = {3262},
  author = {Yaroslav Halchenko and Kyle Meyer and Benjamin Poldrack and Debanjum Solanky and Adina Wagner and Jason Gors and Dave MacFarlane and Dorian Pustina and Vanessa Sochat and Satrajit Ghosh and Christian M\"{o}nch and Christopher Markiewicz and Laura Waite and Ilya Shlyakhter and Alejandro de la Vega and Soichi Hayashi and Christian H\"{a}usler and Jean-Baptiste Poline and Tobias Kadelka and Kusti Skyt{\'{e}}n and Dorota Jarecka and David Kennedy and Ted Strauss and Matt Cieslak and Peter Vavra and Horea-Ioan Ioanas and Robin Schneider and Mika Pfl\"{u}ger and James Haxby and Simon Eickhoff and Michael Hanke},
  title = {{DataLad}: distributed system for joint management of code,  data,  and their relationship},
  journal = {Journal of Open Source Software}
}

@article{decentralization_hanke,
  doi = {10.1515/nf-2020-0037},
  url = {https://doi.org/10.1515/nf-2020-0037},
  year = {2021},
  month = jan,
  publisher = {Walter de Gruyter {GmbH}},
  volume = {0},
  number = {0},
  author = {Michael Hanke and Franco Pestilli and Adina S. Wagner and Christopher J. Markiewicz and Jean-Baptiste Poline and Yaroslav O. Halchenko},
  title = {In defense of decentralized research data management},
  journal = {Neuroforum}
}

@article{decentralization_robinson,
  doi = {10.1038/sdata.2018.221},
  url = {https://doi.org/10.1038/sdata.2018.221},
  year = {2018},
  month = oct,
  publisher = {Springer Science and Business Media {LLC}},
  volume = {5},
  number = {1},
  author = {Danielle C. Robinson and Joe A. Hand and Mathias Buus Madsen and Karissa R. McKelvey},
  title = {The Dat Project,  an open and decentralized research data tool},
  journal = {Scientific Data}
}

@misc{reproducible_paper,
author = {Adina Wagner},
title = {datalad-handbook/repro-paper-sketch: A template to create a reproducible paper with LaTeX, Makefiles, Python, and DataLad},
howpublished = {\url{https://github.com/datalad-handbook/repro-paper-sketch/}},
month = {},
year = {2020},
note = {(Accessed on 04/30/2021)},
journal = {}
}

@book{alpha,
 author = {Krippendorff, Klaus},
 title = {Content analysis : an introduction to its methodology},
 publisher = {SAGE},
 year = {2013},
 address = {Los Angeles London},
 isbn = {1412983150},
 chapter = {12}
 }


@article{kappa,
  doi = {10.1037/h0031619},
  url = {https://doi.org/10.1037/h0031619},
  year = {1971},
  publisher = {American Psychological Association ({APA})},
  volume = {76},
  number = {5},
  pages = {378--382},
  author = {Joseph L. Fleiss},
  title = {Measuring nominal scale agreement among many raters.},
  journal = {Psychological Bulletin}
}

@Book{AC1,
 author = {Gwet, Kilem},
 title = {Handbook of inter-rater reliability : the definitive guide to measuring the extent of agreement among raters},
 publisher = {Advanced Analytics, LLC},
 year = {2014},
 address = {Gaithersburg, MD},
 isbn = {0970806280}
 }
 
 @article{nltk,
  added-at = {2020-01-10T00:00:00.000+0100},
  author = {Loper, Edward and Bird, Steven},
  biburl = {https://www.bibsonomy.org/bibtex/2eac35636d7e2bb4a0264313ed0791372/dblp},
  ee = {https://arxiv.org/abs/cs/0205028},
  interhash = {1af05e5f1cea0feeea8da5f68707a841},
  intrahash = {eac35636d7e2bb4a0264313ed0791372},
  journal = {CoRR},
  keywords = {dblp},
  timestamp = {2020-01-11T11:43:05.000+0100},
  title = {NLTK: The Natural Language Toolkit},
  url = {http://dblp.uni-trier.de/db/journals/corr/corr0205.html#cs-CL-0205028},
  volume = {cs.CL/0205028},
  year = 2002
}

@article{gamma,
  doi = {10.1162/coli_a_00227},
  url = {https://doi.org/10.1162/coli_a_00227},
  year = {2015},
  month = sep,
  publisher = {{MIT} Press - Journals},
  volume = {41},
  number = {3},
  pages = {437--479},
  author = {Yann Mathet and Antoine Widl\"{o}cher and Jean-Philippe M{\'{e}}tivier},
  title = {The Unified and Holistic Method Gamma ($\upgamma$) for Inter-Annotator Agreement Measure and Alignment},
  journal = {Computational Linguistics}
}

@unpublished{pygamma_agreement,
  TITLE = {{pygamma-agreement: Gamma $\gamma$ measure for inter/intra-annotator agreement in Python}},
  AUTHOR = {Titeux, Hadrien and Riad, Rachid},
  URL = {https://hal.archives-ouvertes.fr/hal-03144116},
  NOTE = {working paper or preprint},
  YEAR = {2021},
  MONTH = Feb,
  KEYWORDS = {Annotation de corpus},
  PDF = {https://hal.archives-ouvertes.fr/hal-03144116/file/gamma-paper.pdf},
  HAL_ID = {hal-03144116},
  HAL_VERSION = {v1},
}

@inproceedings{pyannote.metrics,
  author = {Herv\'e Bredin},
  title = {{pyannote.metrics: a toolkit for reproducible evaluation, diagnostic, and error analysis of speaker diarization systems}},
  booktitle = {{Interspeech 2017, 18th Annual Conference of the International Speech Communication Association}},
  year = {2017},
  month = {August},
  address = {Stockholm, Sweden},
  url = {http://pyannote.github.io/pyannote-metrics},
}

@inproceedings{mfa,
  author={Michael McAuliffe and Michaela Socolof and Sarah Mihuc and Michael Wagner and Morgan Sonderegger},
  title={Montreal Forced Aligner: Trainable Text-Speech Alignment Using Kaldi},
  year=2017,
  booktitle={Proc. Interspeech 2017},
  pages={498--502},
  doi={10.21437/Interspeech.2017-1386},
  url={http://dx.doi.org/10.21437/Interspeech.2017-1386}
}

@article{Wu2018,
  doi = {10.2196/10046},
  url = {https://doi.org/10.2196/10046},
  year = {2018},
  month = jun,
  publisher = {{JMIR} Publications Inc.},
  volume = {6},
  number = {6},
  pages = {e10046},
  author = {Robert Wu and Daniyal Liaqat and Eyal de Lara and Tatiana Son and Frank Rudzicz and Hisham Alshaer and Pegah Abed-Esfahani and Andrea S Gershon},
  title = {Feasibility of Using a Smartwatch to Intensively Monitor Patients With Chronic Obstructive Pulmonary Disease: Prospective Cohort Study},
  journal = {{JMIR} {mHealth} and {uHealth}}
}

@article{Gorgolewski2016,
  doi = {10.1038/sdata.2016.44},
  url = {https://doi.org/10.1038/sdata.2016.44},
  year = {2016},
  month = jun,
  publisher = {Springer Science and Business Media {LLC}},
  volume = {3},
  number = {1},
  author = {Krzysztof J. Gorgolewski and Tibor Auer and Vince D. Calhoun and R. Cameron Craddock and Samir Das and Eugene P. Duff and Guillaume Flandin and Satrajit S. Ghosh and Tristan Glatard and Yaroslav O. Halchenko and Daniel A. Handwerker and Michael Hanke and David Keator and Xiangrui Li and Zachary Michael and Camille Maumet and B. Nolan Nichols and Thomas E. Nichols and John Pellman and Jean-Baptiste Poline and Ariel Rokem and Gunnar Schaefer and Vanessa Sochat and William Triplett and Jessica A. Turner and Gaël Varoquaux and Russell A. Poldrack},
  title = {The brain imaging data structure,  a format for organizing and describing outputs of neuroimaging experiments},
  journal = {Scientific Data}
}

@article{Horien2020,
  doi = {10.1038/s41562-020-01005-4},
  url = {https://doi.org/10.1038/s41562-020-01005-4},
  year = {2020},
  month = dec,
  publisher = {Springer Science and Business Media {LLC}},
  volume = {5},
  number = {2},
  pages = {185--193},
  author = {Corey Horien and Stephanie Noble and Abigail S. Greene and Kangjoo Lee and Daniel S. Barron and Siyuan Gao and David O'Connor and Mehraveh Salehi and Javid Dadashkarimi and Xilin Shen and Evelyn M. R. Lake and R. Todd Constable and Dustin Scheinost},
  title = {A hitchhiker's guide to working with large,  open-source neuroimaging datasets},
  journal = {Nature Human Behaviour}
}

@article{Powell2021,
  doi = {10.1038/d41586-021-00331-5},
  url = {https://doi.org/10.1038/d41586-021-00331-5},
  year = {2021},
  month = feb,
  publisher = {Springer Science and Business Media {LLC}},
  volume = {590},
  number = {7845},
  pages = {198--201},
  author = {Kendall Powell},
  title = {The broken promise that undermines human genome research},
  journal = {Nature}
}


@article{hanke_defense_2021,
	title = {In defense of decentralized research data management},
	volume = {0},
	issn = {2363-7013, 0947-0875},
	url = {https://www.degruyter.com/document/doi/10.1515/nf-2020-0037/html},
	doi = {10.1515/nf-2020-0037},
	language = {en},
	number = {0},
	urldate = {2021-03-22},
	journal = {Neuroforum},
	author = {Hanke, Michael and Pestilli, Franco and Wagner, Adina S. and Markiewicz, Christopher J. and Poline, Jean-Baptiste and Halchenko, Yaroslav O.},
	month = jan,
	year = {2021},
	pages = {000010151520200037},
}

@article{gravityspy,
  doi = {10.1088/1361-6382/aa5cea},
  url = {https://doi.org/10.1088/1361-6382/aa5cea},
  year = {2017},
  month = feb,
  publisher = {{IOP} Publishing},
  volume = {34},
  number = {6},
  pages = {064003},
  author = {M Zevin and S Coughlin and S Bahaadini and E Besler and N Rohani and S Allen and M Cabero and K Crowston and A K Katsaggelos and S L Larson and T K Lee and C Lintott and T B Littenberg and A Lundgren and C {\O}sterlund and J R Smith and L Trouille and V Kalogera},
  title = {Gravity Spy: integrating advanced {LIGO} detector characterization,  machine learning,  and citizen science},
  journal = {Classical and Quantum Gravity}
}

% code
@misc{zooniverse_example,
  doi = {10.12751/G-NODE.K2H9AZ},
  url = {https://doi.gin.g-node.org/10.12751/g-node.k2h9az},
  author = {Gautheron,  Lucas},
  keywords = {daylong recordings,  crowd-sourcing,  speech data management,  annotation campaigns},
  language = {en},
  title = {Launching a campaign of annotations on Zooniverse with ChildProject},
  publisher = {G-Node},
  year = {2021},
  copyright = {MIT License}
}

@article{datalad_procedures,
  doi = {10.17605/OSF.IO/6VCXK},
  url = {https://osf.io/6vcxk/},
  author = {Gautheron,  Lucas},
  title = {DataLad Procedures for the management of long-form recordings},
  publisher = {Open Science Framework},
  year = {2021},
  journal = {}
}

@article{datalad_extension,
  doi = {10.17605/OSF.IO/C2J5A},
  url = {https://osf.io/c2j5a/},
  author = {Gautheron,  Lucas},
  title = {DataLad extension for child-centered in-situ recordings},
  publisher = {Open Science Framework},
  year = {2021},
  copyright = {MIT License},
  journal = {}
}