Music audio generation spans instrumental clips, full songs with vocals, edits of existing recordings, and systems that play alongside a musician in real time. This monograph explains the methods behind these systems for readers familiar with neural-network training who are new to music generation. It introduces neural...
M. Modrzejewski, Joanna Kurkowska, Dorien Herremans· 0 citations
Sparse autoencoders (SAEs) can expose features of a generative model without predefined labels, but in language models the evidence used to interpret these features has proven an unreliable guide to which of them steer the output. Whether interpretations of SAE features predict control in music generators has not, to o...
Language models are compared on question-answering benchmarks that pose each question in one wording, and a reworded question can change which of two models scores higher. We ask whether giving the models tools makes such comparisons more stable. An accuracy gain cannot answer this, because tools change several steps b...
Open audio-language models are used as judges of generated music: given a clip and its text prompt, the model rates the clip, and the judge is validated by how well its ratings correlate with expert ratings. The correlation does not show what the judge responds to: the music, the text prompt, or the way the question is...
DINO-A is presented, an adaptation of self-distillation from vision to general audio representation learning, and it is traced to two mechanisms: the interaction between DINO's high-dimensional projection space and FSD50K's limited scale, and the additional cost of multi-crop augmentation, which DINO uses but BYOL-A v2...
Tomasz Radzikowski, M. Modrzejewski, Przemysław Rokita· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.