Author

Hao-Wen Dong

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

MusPyExpress: Extending MusPy with Enhanced Expression Text Support

Current work in modeling symbolic music primarily relies on representations extracted from MIDI-like data. While such formats allow for modeling symbolic music as sequences of notes, they omit the large space of symbolic annotations common in western sheet music broadly known as expression text, such as tempo or dynami...

Phillip Long, Hao-Wen Dong, Julian J. McAuley et al. · 1 citation

Preprint Aug 2026

Dialogue-Aware Video-to-Music Generation Using Public Domain Film Collections

This work introduces 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, and uses this film-domain corpus to study dialogue as a conditioning signal for video-to-music generation, motivated by the close temporal coupl...

Haven Kim, Zachary Novack, Julian J. McAuley et al. · 1 citation