BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Seoul
X-LIC-LOCATION:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:18871231T000000
DTSTART:19881009T020000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230103T035307Z
LOCATION:Auditorium\, Level 5\, West Wing
DTSTART;TZID=Asia/Seoul:20221206T100000
DTEND;TZID=Asia/Seoul:20221206T120000
UID:siggraphasia_SIGGRAPH Asia 2022_sess153_papers_410@linklings.com
SUMMARY:VOCAL: Vowel and Consonant Layering for Expressive  Animator-Centr
 ic Singing Animation
DESCRIPTION:Technical Papers\n\nVOCAL: Vowel and Consonant Layering for Ex
 pressive  Animator-Centric Singing Animation\n\nPan, Landreth, Fiume, Sing
 h\n\nSinging and speaking are two fundamental forms of human communication
 . From a modeling perspective however, speaking can be seen as a subset of
  singing. We present VOCAL, a system that automatically generates expressi
 ve, animator-centric lower face animation from singing audio input. Articu
 latory phonetics and voice instruction ascribe additional roles to vowels 
 (projecting melody and volume) and consonants (lyrical clarity and rhythmi
 c emphasis) in song. Our approach directly uses these insights to define a
 xes for Melodic-accent and Pitch-sensitivity ({\it Ma-Ps}), which together
  provide an abstract space to visually represent various singing styles. I
 n our system. vowels are processed first. A lyrical vowel is often sung to
 nally as one or more different vowels. We perform any such vowel modificat
 ions using a neural network trained on input audio. These vowels are then 
 dilated from their spoken behaviour to bleed into each other based on Melo
 dic-accent ({\it Ma}), with Pitch-sensitivity ({\it Ps}) modeling visual v
 ibrato. Consonant animation curves are then layered in, with viseme intens
 ity modeling rhythmic emphasis (inverse to {\it Ma}).\nOur evaluation is f
 ourfold: we show the impact of our design parameters; we compare our resul
 ts to ground truth and prior art; we present compelling results on a varie
 ty of voices and singing styles; and we validate these results with profes
 sional singers and animators.\n\nRegistration Category: FULL ACCESS, EXPER
 IENCE PLUS ACCESS, EXPERIENCE ACCESS, TRADE EXHIBITOR\n\nLanguage: ENGLISH
 \n\nFormat: IN-PERSON
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_410&sess=sess15
 3
END:VEVENT
END:VCALENDAR