TH1.PA3.8
LEARNING TO ASSESS SUBJECTIVE IMPRESSIONS FROM SPEECH
Yuto Kondo, Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko, Noboru Harada, NTT Corporation, Japan
Session:
TH1.PA3: Analysis and Synthesis of Speech and Audio Poster
Track:
ASMSP - Acoustic, Speech and Music Signal Processing
Location:
Poster Area 3
Presentation Time:
Thu, 29 Aug, 10:30 - 12:30 France Time (UTC +1)
Session Co-Chairs:
Mathieu Fontaine, Télécom Paris and Aki Härmä, Maastricht University
Presentation
Discussion
Resources
No resources available.
Session TH1.PA3
TH1.PA3.1: TARGETED AUGMENTED DATA FOR AUDIO DEEPFAKE DETECTION
Marcella Astrid, University of Luxembourg, Luxembourg; Enjie Ghorbel, Manouba University, Tunisia; Djamila Aouada, University of Luxembourg, Luxembourg
TH1.PA3.2: Latent CLAP Loss for Better Foley Sound Synthesis
Tornike Karchkhadze, University of California San Diego, United States; Hassan Salami Kavaki, The City University of New York, United States; Mohammad Rasool Izadi, Bryce Irvin, Mikolaj Kegler, Ari Hertz, Shuo Zhang, Marko Stamenovic, Bose Corporation, United States
TH1.PA3.3: Accessible Obstructive Sleep Apnea Screening using Classical Acoustic Speech Representations
Behrad TaghiBeyglou, University of Toronto, Canada; Alexander Chow, Toronto Rehabilitation Institute- University Health Network, Canada; Parker Mclaurin, Toronto General Hospital Research Institute- University Health Network, Canada; Oviga Yasokaran, Rene Adams, Majida Mohammed, Toronto Rehabilitation Institute- University Health Network, Canada; Mandeep Singh, Toronto Western Hospital- University Health Network,, Canada; Najib Ayas, University of British Columbia, Canada; Sachin Pendharkar, University of Calgary, Canada; Fernanda Almeida, University of British Columbia, Canada; Valeria Rac, Toronto General Hospital Research Institute- University Health Network, Canada; Azadeh Yadollahi, Toronto Rehabilitation Institute- University Health Network, Canada
TH1.PA3.4: Lecture Video Highlights Detection from Speech
Meishu Song, The University of Tokyo, Japan; Ilhan Aslan, Huawei Technologies, Germany; Emilia Parada-Cabaleiro, Johannes Kepler University, Austria; Zijiang Yang, Elisabeth André, University of Augsburg, Germany; Yamamoto Yoshiharu, The University of Tokyo, Japan; Björn Schuller, Imperial College London, United Kingdom
TH1.PA3.5: ON STRATEGIES TO EXPLOIT DEPENDENCIES BETWEEN SINGING VOICE ALIGNMENT AND SEPARATION
Théo Nguyen, Yann TEYTAUT, Axel ROEBEL, IRCAM, France
TH1.PA3.6: Analysis of Respiratory Health Indicators in Speech-Breathing-Patterns
Gauri Deshpande, TCS Research, University of Augsburg Germany, India; Bjorn Schuller, Imperial College London, Germany
TH1.PA3.7: Heart Rate from Read-Speech Influenced by Physical Exercise
Harish Battula, Gauri Deshpande, Sachin Patel, TCS Research, India; Bjorn Schuller, Imperial College London, Germany
TH1.PA3.8: LEARNING TO ASSESS SUBJECTIVE IMPRESSIONS FROM SPEECH
Yuto Kondo, Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko, Noboru Harada, NTT Corporation, Japan
TH1.PA3.9: MEMORY EFFICIENT NEURAL SPEECH SYNTHESIS BASED ON FASTSPEECH2 USING ATTENTION FREE TRANSFORMER
Eirini Sisamaki, Vassilis Tsiaras, Yannis Stylianou, University of Crete, Greece
TH1.PA3.10: LNACONT: LANGUAGE-NORMALIZED AFFINE COUPLING LAYER WITH CONTRASTIVE LEARNING FOR CROSS-LINGUAL MULTI-SPEAKER TEXT-TO-SPEECH
Sungwoong Hwang, Changhwan Kim, HYUNDAI MOTOR COMPANY, Korea (South)