Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs

Abstract

To apply neural sequence models such as the Transformers to music generation tasks, one has to represent a piece of music by a sequence of tokens drawn from a finite set of pre-defined vocabulary. Such a vocabulary usually involves tokens of various types. For example, to describe a musical note, one needs separate tokens to indicate the note's pitch, duration, velocity (dynamics), and placement (onset time) along the time grid. While different types of tokens may possess different properties, existing models usually treat them equally, in the same way as modeling words in natural languages. In this paper, we present a conceptually different approach that explicitly takes into account the type of the tokens, such as note types and metric types. And, we propose a new Transformer decoder architecture that uses different feed-forward heads to model tokens of different types. With an expansion-compression trick, we convert a piece of music to a sequence of compound words by grouping neighboring tokens, greatly reducing the length of the token sequences. We show that the resulting model can be viewed as a learner over dynamic directed hypergraphs. And, we employ it to learn to compose expressive Pop piano music of full-song length (involving up to 10K individual tokens per song), both conditionally and unconditionally. Our experiment shows that, compared to state-of-the-art models, the proposed model converges 5--10 times faster at training (i.e., within a day on a single GPU with 11 GB memory), and with comparable quality in the generated music.

References in corpus (7)

• CTRL: A Conditional Transformer Language Model for Controllable Generation
• Generating Long Sequences with Sparse Transformers
• Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention
• Temporal Graph Networks for Deep Learning on Dynamic Graphs
• Rethinking Positional Encoding in Language Pre-training
• Adaptive Input Representations for Neural Language Modeling
• MMM : Exploring Conditional Multi-Track Music Generation with the Transformer

Cited by in corpus (5)

• A Domain-Knowledge-Inspired Music Embedding Space and a Novel Attention Mechanism for Symbolic Music Modeling
• MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training
• The Piano Inpainting Application
• Score Transformer: Generating Musical Score from Note-level Representation
• Style-based Composer Identification and Attribution of Symbolic Music Scores: a Systematic Survey