MuseMorphose: Full-Song and Fine-Grained Piano Music Style Transfer With One Transformer VAE

• Published in: IEEE/ACM transactions on audio, speech, and language processing Vol. 31; pp. 1953 - 1967
• Main Authors: Wu, Shih-Lun, Yang, Yi-Hsuan
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Coders; controllable music generation; Decoders; Decoding; deep learning; Harmonic analysis; Measurement; Music; music style transfer; Pianos; Recurrent neural networks; Task analysis; Transformer; Transformers; variational autoencoder (VAE)
• ISSN: 2329-9290; 2329-9304
• DOI: 10.1109/TASLP.2023.3270726

Transformers and variational autoencoders (VAE) have been extensively employed for symbolic (e.g., MIDI) domain music generation. While the former boast an impressive capability in modeling long sequences, the latter allow users to willingly exert control over different parts (e.g., bars) of the music to be generated. In this paper, we are interested in bringing the two together to construct a single model that exhibits both strengths. The task is split into two steps. First, we equip Transformer decoders with the ability to accept segment-level, time-varying conditions during sequence generation. Subsequently, we combine the developed and tested in-attention decoder with a Transformer encoder, and train the resulting MuseMorphose model with the VAE objective to achieve style transfer of long pop piano pieces, in which users can specify musical attributes including rhythmic intensity and polyphony (i.e., harmonic fullness) they desire, down to the bar level. Experiments show that MuseMorphose outperforms recurrent neural network (RNN) based baselines on numerous widely-used metrics for style transfer tasks.