@InProceedings{    feisthauer.ea2019-modeling,
    author       = {Feisthauer, Laurent and Bigo, Louis and Giraud, Mathieu},
    year         = {2019},
    title        = {Modeling and learning structural breaks in sonata forms},
    abstract     = {Expositions of Sonata Forms are structured towards two
                   cadential goals, one being the Medial Caesura (MC). The MC
                   is a gap in the musical texture between the Transition
                   zone (TR) and the Secondary thematic zone (S). It appears
                   as a climax of energy accumulation initiated by the TR,
                   dividing the Exposition in two parts. We introduce
                   high-level features relevant to formalize this energy gain
                   and to identify MCs. These features concern rhythmic,
                   harmonic and textural aspects of the music and
                   characterize either the MC, its preparation or the texture
                   contrast between TR and S. They are used to train a LSTM
                   neural network on a corpus of 27 movements of string
                   quartets written by Mozart. The model correctly locates
                   the MCs on 14 movements within a leave-one-piece-out
                   validation strategy. We discuss these results and how the
                   network manages to model such structural breaks.},
    address      = {Utrecht, Netherlands},
    booktitle    = {Proc. International Society for Music Information
                   Retrieval Conference 2019},
    keywords     = {music analysis with computers},
    mendeley-tags= {music analysis with computers},
    url          = {https://hal.archives-ouvertes.fr/hal-02162936}
}

{"_id":"Bh37ZZLbu9dWpbDQe","bibbaseid":"feisthauer-bigo-giraud-modelingandlearningstructuralbreaksinsonataforms-2019","authorIDs":[],"author_short":["Feisthauer, L.","Bigo, L.","Giraud, M."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Feisthauer"],"firstnames":["Laurent"],"suffixes":[]},{"propositions":[],"lastnames":["Bigo"],"firstnames":["Louis"],"suffixes":[]},{"propositions":[],"lastnames":["Giraud"],"firstnames":["Mathieu"],"suffixes":[]}],"year":"2019","title":"Modeling and learning structural breaks in sonata forms","abstract":"Expositions of Sonata Forms are structured towards two cadential goals, one being the Medial Caesura (MC). The MC is a gap in the musical texture between the Transition zone (TR) and the Secondary thematic zone (S). It appears as a climax of energy accumulation initiated by the TR, dividing the Exposition in two parts. We introduce high-level features relevant to formalize this energy gain and to identify MCs. These features concern rhythmic, harmonic and textural aspects of the music and characterize either the MC, its preparation or the texture contrast between TR and S. They are used to train a LSTM neural network on a corpus of 27 movements of string quartets written by Mozart. The model correctly locates the MCs on 14 movements within a leave-one-piece-out validation strategy. We discuss these results and how the network manages to model such structural breaks.","address":"Utrecht, Netherlands","booktitle":"Proc. International Society for Music Information Retrieval Conference 2019","keywords":"music analysis with computers","mendeley-tags":"music analysis with computers","url":"https://hal.archives-ouvertes.fr/hal-02162936","bibtex":"@InProceedings{ feisthauer.ea2019-modeling,\n author = {Feisthauer, Laurent and Bigo, Louis and Giraud, Mathieu},\n year = {2019},\n title = {Modeling and learning structural breaks in sonata forms},\n abstract = {Expositions of Sonata Forms are structured towards two\n cadential goals, one being the Medial Caesura (MC). The MC\n is a gap in the musical texture between the Transition\n zone (TR) and the Secondary thematic zone (S). It appears\n as a climax of energy accumulation initiated by the TR,\n dividing the Exposition in two parts. We introduce\n high-level features relevant to formalize this energy gain\n and to identify MCs. These features concern rhythmic,\n harmonic and textural aspects of the music and\n characterize either the MC, its preparation or the texture\n contrast between TR and S. They are used to train a LSTM\n neural network on a corpus of 27 movements of string\n quartets written by Mozart. The model correctly locates\n the MCs on 14 movements within a leave-one-piece-out\n validation strategy. We discuss these results and how the\n network manages to model such structural breaks.},\n address = {Utrecht, Netherlands},\n booktitle = {Proc. International Society for Music Information\n Retrieval Conference 2019},\n keywords = {music analysis with computers},\n mendeley-tags= {music analysis with computers},\n url = {https://hal.archives-ouvertes.fr/hal-02162936}\n}\n\n","author_short":["Feisthauer, L.","Bigo, L.","Giraud, M."],"key":"feisthauer.ea2019-modeling","id":"feisthauer.ea2019-modeling","bibbaseid":"feisthauer-bigo-giraud-modelingandlearningstructuralbreaksinsonataforms-2019","role":"author","urls":{"Paper":"https://hal.archives-ouvertes.fr/hal-02162936"},"keyword":["music analysis with computers"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"inproceedings","biburl":"https://hmb.sampaio.me/bibliografia.bib.txt","creationDate":"2019-08-02T17:31:57.860Z","downloads":0,"keywords":["music analysis with computers"],"search_terms":["modeling","learning","structural","breaks","sonata","forms","feisthauer","bigo","giraud"],"title":"Modeling and learning structural breaks in sonata forms","year":2019,"dataSources":["n6MFY2CscQLDpJ7nT","RFLDZw5KyJdadDXDm"]}