CITATION — REFERENCE ENTRY
sheet-images · dorfer2016-sheet-music-score-following
- Claim ID
- sheet-images
- Assertion
- Score following systems have depended on a symbolic, computer-readable score such as MusicXML or MIDI, created manually or by optical music recognition, which remains unreliable for complex music. Dorfer, Arzt, and Widmer proposed an end-to-end multi-modal convolutional network that takes images of sheet music and audio spectrograms and predicts where in a staff a short audio snippet occurs; their proof of concept was limited to monophonic piano music and single staff lines.
- Quote
So far all approaches to this task depend on a symbolic, computer-readable representation of the sheet music, such as MusicXML or MIDI [...]. This representation is created either manually [...] or automatically via optical music recognition software. Unfortunately automatic methods are still highly unreliable and thus of limited use, especially for more complex music like orchestral scores. [...] It consists of an end-to-end multi-modal convolutional neural network that takes as input images of sheet music and spectrograms of the respective audio snippets. [...] the system is fed only a single staff line at a time (not a full page of score). We restrict ourselves to monophonic music, and to the piano.
- Quote language
- en
- Locator
- section: Abstract, 1, 2.1
Available in