@InProceedings{    brinkman.ea2016-musical,
    author       = {Brinkman, Alan and Shanahan, Daniel and Sapp, Craig
                   Stuart},
    year         = {2016},
    title        = {Musical {Stylometry}, {Machine} {Learning}, and
                   {Attribution} {Studies}: {A} {Semi}-{Supervised}
                   {Approach} to the {Works} of {Josquin}},
    address      = {San Francisco},
    url          = {http://icmpc.org/icmpc14/files/ICMPC14_Proceedings.pdf},
    abstract     = {Compositional authorship is often assigned though factors
                   external to the musical text, such as biographical records
                   and surveys of source attributions; however, such
                   methodologies often fall short and are potentially
                   unreliable. On the other hand, determining compositional
                   authorship through internal factors—through stylistic
                   traits of composers derived from the music itself—is
                   often fraught with errors and biases. One of the
                   underlying assumptions in the field of stylometry is that,
                   while it is difficult for humans to perform a truly
                   unbiased analysis of authorial attribution, computational
                   methods can provide clearer and more objective guidelines
                   than would otherwise be apparent to readers or listeners,
                   and thus might provide corroboration or clues for further
                   investigation. This paper discusses machine-learning
                   approaches for evaluating attribution for compositions by
                   Josquin des Prez. We explore musical characteristics such
                   as melodic sequences, counterpoint motion, rhythmic
                   variability, and other entry measures to search for
                   features inherent to a composer's works or style, and we
                   hope that employing such an approach—one that explicitly
                   states which factors led to the decision-making
                   process—can serve to inform scholars looking at other
                   works and composers.},
    booktitle    = {Proceedings of the {International} {Conference} on
                   {Music} {Perception} and {Cognition}},
    keywords     = {Computational Musicology},
    pages        = {91--97}
}

{"_id":"kNWbronbYgdknXD24","bibbaseid":"brinkman-shanahan-sapp-musicalstylometrymachinelearningandattributionstudiesasemisupervisedapproachtotheworksofjosquin-2016","author_short":["Brinkman, A.","Shanahan, D.","Sapp, C. S."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Brinkman"],"firstnames":["Alan"],"suffixes":[]},{"propositions":[],"lastnames":["Shanahan"],"firstnames":["Daniel"],"suffixes":[]},{"propositions":[],"lastnames":["Sapp"],"firstnames":["Craig","Stuart"],"suffixes":[]}],"year":"2016","title":"Musical Stylometry, Machine Learning, and Attribution Studies: A Semi-Supervised Approach to the Works of Josquin","address":"San Francisco","url":"http://icmpc.org/icmpc14/files/ICMPC14_Proceedings.pdf","abstract":"Compositional authorship is often assigned though factors external to the musical text, such as biographical records and surveys of source attributions; however, such methodologies often fall short and are potentially unreliable. On the other hand, determining compositional authorship through internal factors—through stylistic traits of composers derived from the music itself—is often fraught with errors and biases. One of the underlying assumptions in the field of stylometry is that, while it is difficult for humans to perform a truly unbiased analysis of authorial attribution, computational methods can provide clearer and more objective guidelines than would otherwise be apparent to readers or listeners, and thus might provide corroboration or clues for further investigation. This paper discusses machine-learning approaches for evaluating attribution for compositions by Josquin des Prez. We explore musical characteristics such as melodic sequences, counterpoint motion, rhythmic variability, and other entry measures to search for features inherent to a composer's works or style, and we hope that employing such an approach—one that explicitly states which factors led to the decision-making process—can serve to inform scholars looking at other works and composers.","booktitle":"Proceedings of the International Conference on Music Perception and Cognition","keywords":"Computational Musicology","pages":"91–97","bibtex":"@InProceedings{ brinkman.ea2016-musical,\n author = {Brinkman, Alan and Shanahan, Daniel and Sapp, Craig\n Stuart},\n year = {2016},\n title = {Musical {Stylometry}, {Machine} {Learning}, and\n {Attribution} {Studies}: {A} {Semi}-{Supervised}\n {Approach} to the {Works} of {Josquin}},\n address = {San Francisco},\n url = {http://icmpc.org/icmpc14/files/ICMPC14_Proceedings.pdf},\n abstract = {Compositional authorship is often assigned though factors\n external to the musical text, such as biographical records\n and surveys of source attributions; however, such\n methodologies often fall short and are potentially\n unreliable. On the other hand, determining compositional\n authorship through internal factors—through stylistic\n traits of composers derived from the music itself—is\n often fraught with errors and biases. One of the\n underlying assumptions in the field of stylometry is that,\n while it is difficult for humans to perform a truly\n unbiased analysis of authorial attribution, computational\n methods can provide clearer and more objective guidelines\n than would otherwise be apparent to readers or listeners,\n and thus might provide corroboration or clues for further\n investigation. This paper discusses machine-learning\n approaches for evaluating attribution for compositions by\n Josquin des Prez. We explore musical characteristics such\n as melodic sequences, counterpoint motion, rhythmic\n variability, and other entry measures to search for\n features inherent to a composer's works or style, and we\n hope that employing such an approach—one that explicitly\n states which factors led to the decision-making\n process—can serve to inform scholars looking at other\n works and composers.},\n booktitle = {Proceedings of the {International} {Conference} on\n {Music} {Perception} and {Cognition}},\n keywords = {Computational Musicology},\n pages = {91--97}\n}\n\n","author_short":["Brinkman, A.","Shanahan, D.","Sapp, C. S."],"key":"brinkman.ea2016-musical","id":"brinkman.ea2016-musical","bibbaseid":"brinkman-shanahan-sapp-musicalstylometrymachinelearningandattributionstudiesasemisupervisedapproachtotheworksofjosquin-2016","role":"author","urls":{"Paper":"http://icmpc.org/icmpc14/files/ICMPC14_Proceedings.pdf"},"keyword":["Computational Musicology"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://hmb.sampaio.me/bibliografia.bib.txt","dataSources":["n6MFY2CscQLDpJ7nT","pzyFFGWvxG2bs63zP"],"keywords":["computational musicology"],"search_terms":["musical","stylometry","machine","learning","attribution","studies","semi","supervised","approach","works","josquin","brinkman","shanahan","sapp"],"title":"Musical Stylometry, Machine Learning, and Attribution Studies: A Semi-Supervised Approach to the Works of Josquin","year":2016}