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:20230103T035309Z
LOCATION:Room 325-AB\, Level 3\, West Wing
DTSTART;TZID=Asia/Seoul:20221207T140000
DTEND;TZID=Asia/Seoul:20221207T153000
UID:siggraphasia_SIGGRAPH Asia 2022_sess162_papers_410@linklings.com
SUMMARY:VOCAL: Vowel and Consonant Layering for Expressive  Animator-Centr
 ic Singing Animation
DESCRIPTION:Technical Communications, Technical Papers\n\nVOCAL: Vowel and
  Consonant Layering for Expressive  Animator-Centric Singing Animation\n\n
 Pan, Landreth, Fiume, Singh\n\nSinging and speaking are two fundamental fo
 rms of human communication. From a modeling perspective however, speaking 
 can be seen as a subset of singing. We present VOCAL, a system that automa
 tically generates expressive, animator-centric lower face animation from s
 inging audio input. Articulatory phonetics and voice instruction ascribe a
 dditional roles to vowels (projecting melody and volume) and consonants (l
 yrical clarity and rhythmic emphasis) in song. Our approach directly uses 
 these insights to define axes for Melodic-accent and Pitch-sensitivity ({\
 it Ma-Ps}), which together provide an abstract space to visually represent
  various singing styles. In our system. vowels are processed first. A lyri
 cal vowel is often sung tonally as one or more different vowels. We perfor
 m any such vowel modifications using a neural network trained on input aud
 io. These vowels are then dilated from their spoken behaviour to bleed int
 o each other based on Melodic-accent ({\it Ma}), with Pitch-sensitivity ({
 \it Ps}) modeling visual vibrato. Consonant animation curves are then laye
 red in, with viseme intensity modeling rhythmic emphasis (inverse to {\it 
 Ma}).\nOur evaluation is fourfold: we show the impact of our design parame
 ters; we compare our results to ground truth and prior art; we present com
 pelling results on a variety of voices and singing styles; and we validate
  these results with professional singers and animators.\n\nRegistration Ca
 tegory: FULL ACCESS, ON-DEMAND ACCESS\n\nLanguage: ENGLISH\n\nFormat: IN-P
 ERSON, ON-DEMAND
URL:https://sa2022.siggraph.org/en/full-program/?id=papers_410&sess=sess16
 2
END:VEVENT
END:VCALENDAR