BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Scansion-based Lyric Generation - Yiwen Chen (University of Cambri
 dge)
DTSTART:20241122T120000Z
DTEND:20241122T130000Z
UID:TALK222625@talks.cam.ac.uk
CONTACT:Suchir Salhan
DESCRIPTION:Abstract:\n\nYiwen Chen's study looks at generating lyrics in 
 Mandarin that match well with both the melody and the tonal contour of the
  language. The approach uses mBART and treats lyrics generation as a seque
 nce-to-sequence (seq2seq) task. Instead of generating lyrics directly from
  the melody\, which is the usual way\, the system uses scansion as an inte
 rmediate step—a contour representation that works with the melody. An ad
 vantage of this method is that it doesn’t need a parallel melody-lyrics 
 dataset.\n\n \n\nThe study also runs an automatic evaluation of the system
  against competitors\, introducing new metrics specific to lyrics. These m
 etrics check how clear the lyrics are\, how well they fit the melody and m
 easure creativity through metrics such as variation. Different ways of imp
 lementing scansion are tested and compared to other lyrics generators. The
  top-performing system beats all others in matching lyrics to melodies\, a
 nd outperforms large language models (LLMs) built specifically for this ta
 sk.\n\nBio: Yiwen Chen is a postdoctoral research assistant at the Centre 
 for Digital Music at Queen Mary University of London. She's also a profess
 ional lyricist who has collaborated with music labels and game companies. 
 Her work focuses on improving the performance of lyrics generators without
  relying on parallel datasets of aligned melody and lyrics that involve co
 pyright issues.\n\n
LOCATION:Zoom link: https://cam-ac-uk.zoom.us/j/4751389294?pwd=Z2ZOSDk0eG1
 wZldVWG1GVVhrTzFIZz09
END:VEVENT
END:VCALENDAR