BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260817T171535Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241206T135600
DTEND;TZID=Asia/Tokyo:20241206T141000
UID:siggraphasia_SIGGRAPH Asia 2024_sess147_papers_1006@linklings.com
SUMMARY:Sketching With Your Voice: "Non-Phonorealistic" Rendering of Sound
 s via Vocal Imitation
DESCRIPTION:Matthew Caren, Kartik Chandra, Joshua Tenenbaum, Jonathan Raga
 n-Kelley, and Karima Ma (Massachusetts Institute of Technology)\n\nWe pres
 ent a method for automatically producing human-like vocal imitations of so
 unds: the equivalent of ``sketching,'' but for auditory rather than visual
  representation. Starting with a simulated model of the human vocal tract,
  we first try generating vocal imitations by tuning the model's control pa
 rameters to make the synthesized vocalization match the target sound in te
 rms of perceptually-salient auditory features. Then, to better match human
  intuitions, we apply a cognitive theory of communication to take into acc
 ount how human speakers reason strategically about their listeners. Finall
 y, we show through several experiments and user studies that when we add t
 his type of communicative reasoning to our method, it aligns with human in
 tuitions better than matching auditory features alone does. This observati
 on has broad implications for the study of depiction in computer graphics.
 \n\nRegistration Category: Full Access, Full Access Supporter\n\nLanguage 
 Format: English Language\n\nSession Chair: Yi Zhou (Roblox)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_1006&sess=sess147
END:VEVENT
END:VCALENDAR