AVSP 2017 program

Day 1 (25 august)
  • 9h – 9h15          Opening
  • 9h15-10h15       Special Session: Remembering Eric Vatikiotis-Bateson
  • 10h15 – 10h30   Coffee break
  • 10h30 – 12h10   Session 1    Gaze and Handedness
  • 14h00 – 16h      Session 2    AV by machines
  • 16h – 16h15       Coffee break
  • 16h15 – 17h35    Session 3    Lip reading by machines


  • Evening – Buffet dinner (at KTH)
Day 2 (26 august)
  • 9h – 10h            Keynote: Sonja A Kotz
  • 10h – 10h30       Coffee break
  • 10h30 – 11h50    Session 4   Prosody and Timing
  • 13h30- 15h10     Session 5    Emotion & Attitudes
  • 15h10 – 15h30    Coffee break
  • 15h30 – 16h50   Session 6     AV Perception
  • 16h50 – 17h00   Closing

Please note that all sessions are oral, and the total time for each presentation is 20 minutes: a 15-minute presentation + 5 minutes questions.


Special session : Remembering Eric Vatikiotis-Bateson
  • Eric Vatikiotis-Bateson and the Birth of AVSP – Denis Burnham, with input from Laurie Fais, Ruth Campbell, Kevin Munhall, and Phillip Rubin and Editor-in-Chief, Chris Davis
Session 1 – Gaze and Handedness
  • Acoustic cue variability affects eye movement behaviour during non-native speech perception: a GAMM model – Jessie S. Nixon and Catherine T. Best
  • The effect of age and hearing loss on partner-directed gaze in a communicative task – Chris Davis,  Jeesun Kim,  Outi Tuomainen and Valerie Hazan
  • Referential Gaze Makes a Difference in Spoken Language Comprehension: Human Speaker vs. Virtual Agent Listener Gaze – Eva Maria Nunnemann,  Kirsten Bergmann,  Helene Kreysa and Pia Knoeferle
  • The influence of handedness and pointing direction on deictic gestures and speech interaction: Evidence from motion capture data on Polish counting-out rhymes – Katarzyna Stoltmann and Susanne Fuchs
  • The Influence of Familial Sinistrality on Audiovisual Speech Perception – Sandhya Vinay and Dawn Behne
Session 2 – AV by machines
  • Using deep neural networks to estimate tongue movements from speech face motion – Christian Kroos,  Rikke Bundgaard-Nielsen,  Catherine Best and Mark D. Plumbley
  • End-to-End Audiovisual Fusion with LSTMs – Stavros Petridis,  Yujiang Wang,  Zuwei Li and Maja Pantic
  • Using visual speech information and perceptually motivated loss functions for binary mask estimation – Danny Websdale and Ben Milner
  • Combining Multiple Views for Visual Speech Recognition – Marina Zimmermann,  Mostafa Mehdipour Ghazi,  Hazim Kemal Ekenel and Jean-Philippe Thiran
  • On the quality of an expressive audiovisual corpus: a case study of acted speech – Slim Ouni,  Sara Dahmani and Vincent Colotte
  • Thin slicing to predict viewer impressions of TED Talks – Ailbhe Cullen and Naomi Harte
Session 3 – Lip reading by machines
  • Exploring ROI size in deep learning based lipreading – Alexandros Koumparoulis,  Gerasimos Potamianos,  Youssef Mroueh and Steven J. Rennie
  • Towards Lipreading Sentences with Active Appearance Models – George Sterpu and Naomi Harte
  • Lipreading using deep bottleneck features for optical and depth images Satoshi Tamura,  Koichi Miyazaki and Satoru Hayamizu
  • Inner Lips Parameter Estimation based on Adaptive Ellipse Model – Li Liu,  Gang Feng and Denis Beautemps
Session 4 – Prosody and Timing
  • Processing of visuo-auditory prosodic information in cochlear-implanted patients deaf patients – Pascal Barone,  Mathieu Marx and Anne Lasfargues-Delannoy
  • Acoustic features of multimodal prominences: Do visual beat gestures affect verbal pitch accent realization? – Gilbert Ambrazaitis and David House
  • Contribution of visual rhythmic information to speech perception in noise – Vincent Aubanel,  Cassandra Masters,  Jeesun Kim and Chris Davis
  • Perceived Audiovisual Simultaneity in Speech by Musicians and Nonmusicians: Preliminary Behavioral and Event-Related Potential (ERP) Findings – Dawn Behne,  Marzieh Sorati and Magnus Alm
Session 5 – Emotion & Attitudes
  • The developmental path of multisensory perception of emotion and phoneme in Japanese speakers – Hisako W. Yamamoto,  Misako Kawahara and Akihiro Tanaka
  • Impact of Culture on the Development of Multisensory Emotion Perception – Misako Kawahara,  Disa Sauter and Akihiro Tanaka
  • Multisensory Perception of Emotion for Human and Chimpanzee Expressions by Humans – Marina Kawase,  Ikuma Adachi and Akihiro Tanaka
  • Cross-Language Perception of Audio-visual Attitudinal Expressions – Hansjörg Mixdorff,  Angelika Hönemann,  Albert Rilliard,  Tan Lee and Matthew Ma
  • Facial activity of attitudinal speech in German – Angelika Hoenemann and Petra Wagner
Session 6 – AV Perception
  • Impact of early bilingualism on infants’ ability to process talking and non-talking faces: new data from 9-month-old infants – Mathilde Fort and Núria Sebastián-Gallés
  • Atypical phonemic discrimination but not audiovisual speech integration in children with autism and the broader autism phenotype – Julia Irwin,  Trey Avery,  Jacqueline Turcios,  Lawrence Brancazio,  Barbara Cook and Nicole Landi
  • Learning to recognize unfamiliar talkers from the word-level dynamics of visual speech – Alexandra Jesse and Paul Saba
  • Applying the summation model in audiovisual speech perception – Kaisa Tiippana,  Ilmari Kurki and Tarja Peromaa