BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Text-and-audio methods - Catalina Cangea (Google DeepMind)
DTSTART:20240130T130000Z
DTEND:20240130T140000Z
UID:TALK210016@talks.cam.ac.uk
CONTACT:Mateja Jamnik
DESCRIPTION:This talk supports the R255 Advanced Topics in Machine Learnin
 g course module on Multimodal Learning and provides a bird’s eye view of
  the rapidly evolving text-audio landscape\, with a focus on music as a pr
 imary example of audio data. I will first present types of tasks that exis
 t in this space\, then discuss data curation challenges and follow with an
  overview of some existing retrieval and generation methods\, including a 
 quick primer on diffusion models. Finally\, I will describe current evalua
 tion metrics and their limitations.\n\n"You can also join us on Zoom":http
 s://cam-ac-uk.zoom.us/j/92041617729\n
LOCATION:Lecture Theatre 2\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR