Tokenisation of MIDI Sequences for Transcription

This joined work with Masahiko Sakai and Yosuke Amagasu from Nagoya University was presented at TENOR 2024.

It deals with building a formal correspondence between the events of a MIDI sequence (such as note-on and note-off messages), and the corresponding music notation elements (such as notes, rests, chords, and ornaments). We proceed through a notion of tokens in an input MIDI event sequence and an effective tokenization approach based on a hierarchical representation of music scores. Our tokenization procedure is integrated with an algorithm for music transcription based on parsing wrt a weighted tree grammar. Its effectiveness is shown on examples.

Comments are closed.