BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:A Novel Diffusion Model based Approach for Sleep Music Generation 
 - Kevin Monteiro\, Department of Computer Science and Technology
DTSTART:20260420T110000Z
DTEND:20260420T113000Z
UID:TALK244858@talks.cam.ac.uk
CONTACT:Sam Nallaperuma-Herzberg
DESCRIPTION:Sleep disorders\, particularly insomnia\, and mental health\nc
 onditions affect a significant fraction of adults worldwide\, posing serio
 usmmental and physical health risk. Music therapy offers promising\, low-c
 ost\, and non-invasive treatment\, but current approaches rely heavily on 
 expert-curated playlists\, limiting scalability and personalisation. We pr
 opose a low-cost generative system leveraging recent advances in diffusion
  models to synthesize music for therapy. We focus on insomnia and curate a
  dataset of waveform sleep music to generate audio tailored to sleep. To e
 nsure real-world feasibility\, we optimize our system for training andmuse
  on a single GPU\, balancing quality and efficiency through extensive abla
 tion studies. We show through subjective human evaluations that our genera
 ted music matches or outperforms existing baselines in both perceived qual
 ity and relevance to sleep therapy\, while using only a fraction of the co
 mputational cost.
LOCATION:SS03 Seminar Room\, Willam Gates building (Department of Computer
  Science and Technology)
END:VEVENT
END:VCALENDAR