Modeling and learning structural breaks in sonata forms. Feisthauer, L.; Bigo, L.; and Giraud, M. In Proc. International Society for Music Information Retrieval Conference 2019, Utrecht, Netherlands, 2019.
Modeling and learning structural breaks in sonata forms [link]Paper  abstract   bibtex   
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.
@inproceedings{feisthauer.ea2019-modeling,
  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},
  author        = {Feisthauer, Laurent and Bigo, Louis and Giraud,
                  Mathieu},
  booktitle     = {Proc. International Society for Music Information
                  Retrieval Conference 2019},
  keywords      = {music analysis with computers},
  mendeley-tags = {music analysis with computers},
  title         = {{Modeling and learning structural breaks in sonata
                  forms}},
  url           = {https://hal.archives-ouvertes.fr/hal-02162936},
  year          = 2019
}
Downloads: 0