Multi-Genre Music Transformer -- Composing Full Length Musical Piece

TL;DR

This paper introduces a Multi-Genre Transformer model that generates diverse, full-length musical compositions across genres, leveraging compound words for detailed musical event representation and achieving faster training times.

Contribution

The paper presents a novel Multi-Genre Transformer that models genre and form in music generation, improving diversity and training efficiency over previous methods.

Findings

Generated music is diverse and comparable to original tracks.

Model trains 2-5 times faster than existing models.

Effective representation of musical events using compound words.

Abstract

In the task of generating music, the art factor plays a big role and is a great challenge for AI. Previous work involving adversarial training to produce new music pieces and modeling the compatibility of variety in music (beats, tempo, musical stems) demonstrated great examples of learning this task. Though this was limited to generating mashups or learning features from tempo and key distributions to produce similar patterns. Compound Word Transformer was able to represent music generation task as a sequence generation challenge involving musical events defined by compound words. These musical events give a more accurate description of notes progression, chord change, harmony and the art factor. The objective of the project is to implement a Multi-Genre Transformer which learns to produce music pieces through more adaptive learning process involving more challenging task where genres or form of the composition is also considered. We built a multi-genre compound word dataset, implemented a linear transformer which was trained on this dataset. We call this Multi-Genre Transformer, which was able to generate full length new musical pieces which is diverse and comparable to original tracks. The model trains 2-5 times faster than other models discussed.