2023/12/14 by Julian D. Parker, Janne Spijkervet, Parker, Julian D. +15 · 11 citations
Computer Science · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Music Technology and Sound Studies #Music and Audio Processing #Sound (cs.SD) #Speech and Audio Processing #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2312.08723
openalex publication_date 2023/12/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
End-to-end generation of musical audio using deep learning techniques has seen an explosion of activity recently. However, most models concentrate on generating fully mixed music in response to abstract conditioning information. In this work, we present an alternative paradigm for producing music generation models that can listen and respond to musical context. We describe how such a model can be constructed using a non-autoregressive, transformer-based model architecture and present a number of novel architectural and sampling improvements. We train the described architecture on both an open-source and a proprietary dataset. We evaluate the produced models using standard quality metrics and a new approach based on music information retrieval descriptors. The resulting model reaches the audio quality of state-of-the-art text-conditioned models, as well as exhibiting strong musical coherence with its context.