Exploring Musical Roots: Applying Audio Embeddings to Empower Influence Attribution for a Generative Music Model
Year: 2024
Type: conference-paper
Abstract: Every artist has a creative process that draws inspiration from previous artists and their works. Today, "inspiration" has been automated by generative music models. The black box nature of these models obscures the identity of the works that influence their creative output. As a result, users may inadvertently appropriate or copy existing artists' works. We establish a replicable methodology to systematically identify similar pieces of music audio in a manner that is useful for understanding training data attribution. We compare the effect of applying CLMR [1] and CLAP [2] embeddings to similarity measurement in a set of 5 million audio clips used to train VampNet [3], a recent open source generative music model. We validate this approach with a human listening study. We also explore the effect that modifications of an audio example (e.g., pitch shifting) have on similarity measurements. This work is foundational to incorporating automated influence attribution into generative modeling, which promises to let model creators and users move from ignorant appropriation to informed creation. Audio samples accompanying this paper are available at tinyurl.com/exploring-musical-roots.
Authors: Julia Barnett, Hugo Flores García, Bryan Pardo
Language: English
Topic: Music and Audio Processing
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6968215872
FWCI:
Cites:
Cited by:
Related to: