Beatty: Automatic Tempo Curve Synthesis for Expressive MIDI Track Playback
Name
Wong-mmwong-meng-eecs-2022-thesis.pdf
Description
Thesis PDF
Size
1.18 MB
Format
Adobe PDF
Checksum (MD5)
308cfaac45651a375e453b0ec627b2e4
Author(s)
Wong, Madeline
Advisor(s)
Egozy, Eran
Date Issued
May 2022
Publisher
Massachusetts Institute of Technology
Abstract
Beatty is a sequence-to-sequence machine learning model to predict expressive timing decisions for excerpts of classical solo piano music. Composed of a bidirectional encoder LSTM and decoder LSTM with attention, Beatty predicts tempo labels based on input note sequences. The input note sequence is obtained by transforming a MIDI file representation of the musical score into a series of one-hot note vectors, which encode the MIDI note pitches, velocities, and durations, and are augmented with additional harmonic tension information. The target output is a sequence of tempo labels, represented as ratios of the sequence’s initial starting tempo. We demonstrate that the harmonic tension augmentation, as well as learning from filtered tempo label sequences, improve model performance. In qualitative evaluation, the model output receives positive feedback when its predicted tempo sequence is subtle and smooth and criticism when it fluctuates too greatly, suggesting areas for future exploration and improvement.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright MIT
Persistent DSpace Link
