Dialogue-Aware Video-to-Music Generation Using Public Domain Film Collections
Video-to-music generation has drawn growing interest for its role in conveying the emotion of visual media, including film. Progress in the field, however, is hampered by a reproducibility gap: models are often trained on crawled corpora referenced through YouTube URLs that may be deleted, with the underlying data often difficult and time-consuming to retrieve. To address this, we introduce the Open Screen Soundtrack Library version 2 (OSSL-v2), a self-hosted corpus of 34,343 video clips totaling 246.4 hours, sourced from public-domain films. Unlike crawled corpora, OSSL-v2 is reproducible (i.e., not subject to link rot) and copyright-conscious, yet still large enough to train functional ...
| Authors | Haven Kim, Zachary Novack, Julian McAuley et al. |
|---|---|
| Primary category | cs.SD |
| Published | 12 August 2026 |
| Last updated at source | 12 August 2026 |
Connected in the knowledge graph
- McAuley-Lab/OSSL-v2Dataset · cited by
Models and datasets referencing this paper
- McAuley-Lab/OSSL-v2Dataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.