{"id":150,"date":"2026-09-17T14:23:46","date_gmt":"2026-09-17T12:23:46","guid":{"rendered":"https:\/\/project.inria.fr\/avsp2026\/?page_id=150"},"modified":"2026-09-17T14:37:04","modified_gmt":"2026-09-17T12:37:04","slug":"workshop-program","status":"publish","type":"page","link":"https:\/\/project.inria.fr\/avsp2026\/workshop-program\/","title":{"rendered":"Workshop program"},"content":{"rendered":"\n

AVSP Workshop 2026<\/mark><\/strong> (download PDF)<\/a><\/p>\n\n\n\n

2 Oct 2026 (Fri) | 9:30am to 5:30pm<\/p>\n\n\n\n

Anne Cutler Seminar Room, Level 4, Innovation Quarter
(Address: 160 Hawkesbury Road, Westmead, NSW 2145)<\/p>\n\n\n\n

Time<\/strong><\/td>Activity<\/strong><\/td><\/tr>
9:30am<\/td>Registration and Coffee <\/strong><\/mark><\/td><\/tr>
9:40am<\/td>Welcome and IntroductionBy: Chris Davis  & Denis Burnham <\/strong> <\/td><\/tr>
 <\/strong><\/td> <\/em><\/td><\/tr>
10:00am<\/strong><\/td>Investigating Conversational Speech Latency as a Marker of Cognitive and Temporal Processing During Picture Description Tasks in Schizophrenia, Depression and Mild Cognitive Impairment<\/em><\/em><\/em> <\/em>Speaker: Vikram Ramanarayanan<\/strong> <\/td><\/tr>
Session 1: Development<\/strong><\/td><\/tr>
10:20am<\/td>Tracking acoustic and visible articulatory vowel modification in infant-directed speech across the first year<\/em><\/em> <\/em>Speaker: Eylem Altuntas<\/strong> <\/td><\/tr>
10:40am<\/td>Do children show the \u2018pip and pop\u2019 effect? A pilot study of Audiovisual Attentional Facilitation in children

Speaker: Smriti Khadka (Jeesun Kim)<\/strong> <\/strong><\/td><\/tr>
11:00am<\/td>Is Auditory-visual speech perception in pre-reading children at-risk for dyslexia enhanced or impaired?<\/em>

Speaker: Denis Burnham<\/strong> <\/td><\/tr>
 <\/strong>11:20am<\/td> Tea\/coffee Break<\/mark><\/strong> <\/mark><\/td><\/tr>
Session 2: Data and Processing<\/strong><\/td><\/tr>
11:40pm<\/strong><\/td>Speech Synthesis with Color-based Emotion Representation <\/em>Speaker: <\/em>Ryotaro Nagase (Ryoichi Takashima, Yoichi Yamashita)<\/strong> <\/em><\/td><\/tr>
12:00pm<\/td>A Shared Data Processing Workflow for Benchmarking Audio-Visual Speech Recognition Beyond LRS Datasets<\/em>

Speaker: Rishabh Jain (Naomi Harte)<\/strong> <\/strong> <\/td><\/tr>
12:20pm<\/td>From AV Recordings to Acoustic Measurements: An Open-Source Pipeline for Automatic Analysis in Spontaneous Conversation<\/em> Speaker: Sara R. Martin<\/strong> <\/strong><\/td><\/tr>
12:40pm<\/td>Conversation in Noise: Lessons in measuring auditory and visual signals<\/em> Speaker: Chris Davis<\/strong> <\/td><\/tr>
1:00pm<\/td>Lunch<\/mark><\/strong> <\/mark><\/td><\/tr>
2:00pm<\/td>Process, Not Product: Agentic AI for Multimodal Research, Learning, and Teaming

<\/em><\/strong><\/em><\/strong>Keynote Speaker: 
<\/strong>Michael Richardson
<\/strong>School of Psychological Sciences \u2013 Performance and Expertise Research Centre
Frontier AI Research Centre \u2013 Lifespan Health and Wellbeing Research Centre
Macquarie University<\/em> <\/td><\/tr>
Session 3: Gesture<\/strong><\/td><\/tr>
3:00pm<\/td>Natural Asynchrony in Audio-Visual Speech Recognition: A Feature, Not a Flaw <\/em><\/em> Speaker: Zhaofeng Lin (Naomi Harte)<\/strong> <\/td><\/tr>
3:20pm<\/td>Do Cantonese non-manual gestures track prosodic focus location? Evidence from a picture-correction task<\/em> –  Speaker: Tong Shu (Peggy Mok)<\/strong> <\/td><\/tr>
3:40pm<\/td>Afternoon Tea & \u201c50 Years of McGurk<\/em>\u201d by Chris Davis <\/strong><\/mark><\/td><\/tr>
4:00pm<\/td>Distinctive Face and Head Movements in the Production of Lexical Tones in Cantonese, Mandarin, and Thai<\/em>

Speaker: Denis Burnham<\/strong> (Menezes)<\/strong> <\/td><\/tr>
4:20pm<\/td>[via Zoom] The rhythm of your hands can change how listeners segment the speech stream<\/em> Speaker: Hans Rutger Bosker<\/strong> <\/td><\/tr>
4:40pm<\/td>Light refreshments & Lip-Reading Contest<\/strong><\/mark>
<\/td><\/tr>
5:30pm<\/td>End of program <\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n

AVSP Workshop 2026<\/mark><\/strong><\/p>\n\n\n\n

2 Oct 2026 (Fri) | 9:30am to 5:30pm<\/p>\n\n\n\n

Anne Cutler Seminar Room, Level 4, Innovation Quarter
(Address: 160 Hawkesbury Road, Westmead, NSW 2145)<\/p>\n\n\n\n

<\/p>\n","protected":false},"excerpt":{"rendered":"

AVSP Workshop 2026 (download PDF) 2 Oct 2026 (Fri) | 9:30am to 5:30pm Anne Cutler Seminar Room, Level 4, Innovation Quarter(Address: 160 Hawkesbury Road, Westmead, NSW 2145) Time Activity 9:30am Registration and Coffee  9:40am Welcome and IntroductionBy: Chris Davis  & Denis Burnham       10:00am Investigating Conversational Speech Latency as a Marker\u2026<\/p>\n

Continue reading<\/span><\/i><\/a> <\/p>\n","protected":false},"author":1958,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":"","_members_access_role":[],"_members_access_error":""},"class_list":["post-150","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/project.inria.fr\/avsp2026\/wp-json\/wp\/v2\/pages\/150","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/project.inria.fr\/avsp2026\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/project.inria.fr\/avsp2026\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/project.inria.fr\/avsp2026\/wp-json\/wp\/v2\/users\/1958"}],"replies":[{"embeddable":true,"href":"https:\/\/project.inria.fr\/avsp2026\/wp-json\/wp\/v2\/comments?post=150"}],"version-history":[{"count":3,"href":"https:\/\/project.inria.fr\/avsp2026\/wp-json\/wp\/v2\/pages\/150\/revisions"}],"predecessor-version":[{"id":155,"href":"https:\/\/project.inria.fr\/avsp2026\/wp-json\/wp\/v2\/pages\/150\/revisions\/155"}],"wp:attachment":[{"href":"https:\/\/project.inria.fr\/avsp2026\/wp-json\/wp\/v2\/media?parent=150"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}