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:20260817T171539Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241206T130000
DTEND;TZID=Asia/Tokyo:20241206T141000
UID:siggraphasia_SIGGRAPH Asia 2024_sess147@linklings.com
SUMMARY:(Do) Make Some Noise
DESCRIPTION:Each Paper gives a 10 minute presentation.\n\nSpeed-Aware Audi
 o-Driven Speech Animation using Adaptive Windows\n\nWe present a novel met
 hod that can generate realistic speech animations of a 3D face from audio 
 using multiple adaptive windows. In contrast to previous studies that use 
 a fixed size audio window, our method accepts an adaptive audio window as 
 input, reflecting the audio speaking rate to use consist...\n\n\nSunjin Ju
 ng (KAIST, Visual Media Lab); Yeongho Seol (NVIDIA); Kwanggyoon Seo and Hy
 eonho Na (KAIST, Visual Media Lab); Seonghyeon Kim (KAIST, Visual Media La
 b; Anigma Technologies); and Vanessa Tan and Junyong Noh (KAIST, Visual Me
 dia Lab)\n---------------------\nSIGGesture: Generalized Co-Speech Gesture
  Synthesis via Semantic Injection with Large-Scale Pre-Training Diffusion 
 Models\n\nThe automated synthesis of high-quality 3D gestures from speech 
 holds significant value for virtual humans and gaming. Previous methods pr
 imarily focus on synchronizing gestures with speech rhythm, often neglecti
 ng semantic gestures. These semantic gestures are sparse and follow a long
 -tailed distri...\n\n\nQingrong Cheng (Tencent AI Lab, Tencent TIMI L1 Stu
 dio) and Xu Li and Xinghui Fu (Tencent AI Lab)\n---------------------\nWav
 eBlender: Practical Sound-Source Animation in Blended Domains\n\nSynthesiz
 ing plausible sound sources for modern physics-based animation is exceptio
 nally challenging due to complex animated phenomena that form rapidly movi
 ng, deforming, and vibrating interfaces which produce acoustic waves withi
 n the air domain. Not only must the methods synthesize sounds that ar...\n
 \n\nKangrui Xue (Stanford University); Jui-Hsien Wang and Timothy Langlois
  (Adobe Research); and Doug James (Stanford University, NVIDIA)\n---------
 ------------\nDance-to-Music Generation with Encoder-based Textual Inversi
 on\n\nThe seamless integration of music with dance movements is essential 
 for communicating the artistic intent of a dance piece. This alignment als
 o significantly improves the immersive quality of gaming experiences and a
 nimation productions. Although there has been remarkable advancement in cr
 eating hig...\n\n\nSifei Li, Weiming Dong, and Yuxin Zhang (MAIS, Institut
 e of Automation, Chinese Academy of Sciences; School of Artificial Intelli
 gence, University of Chinese Academy of Sciences); Fan Tang (University of
  Chinese Academy of Sciences); Chongyang Ma (Kuaishou Technology); Oliver 
 Deussen (University of Konstanz); Tong-Yee Lee (National Cheng-Kung Univer
 sity); and Changsheng Xu (MAIS, Institute of Automation, Chinese Academy o
 f Sciences; School of Artificial Intelligence, University of Chinese Acade
 my of Sciences)\n---------------------\nSketching With Your Voice: "Non-Ph
 onorealistic" Rendering of Sounds via Vocal Imitation\n\nWe present a meth
 od for automatically producing human-like vocal imitations of sounds: the 
 equivalent of ``sketching,'' but for auditory rather than visual represent
 ation. Starting with a simulated model of the human vocal tract, we first 
 try generating vocal imitations by tuning the model's control...\n\n\nMatt
 hew Caren, Kartik Chandra, Joshua Tenenbaum, Jonathan Ragan-Kelley, and Ka
 rima Ma (Massachusetts Institute of Technology)\n\nRegistration Category: 
 Full Access, Full Access Supporter\n\nLanguage Format: English Language\n\
 nSession Chair: Yi Zhou (Roblox)
END:VEVENT
END:VCALENDAR