ILCB's monthly newsletter N°38

ILCB's monthly newsletter

N°38 - July 15th, 2024

Institute of Language, Communication and the Brain

Bringing together experts in linguistics, neuroscience, psychology, medicine and computer science to understand and to model how language functions.

Dear members of the ILCB community,

After the final “tour de force” of successfully hosting the 20th anniversary of the International Workshop on Language Production (IWoLP) in Marseille – special thanks to Nadera Bureau, Xavier Alario, Krsitof Strijkers Raphaël Fargier, Svetlana Pinet, and Elin Runqvist for the countless hours – I can proudly and happily send all of us to halftime! Enjoy the summer and relax!

(IWoLP 2024; Foto Xavier Alario)

After the summer break, we will host our three new IMERA chairs: Suzanne Fuchs, Antoni Rodriguez-Fornells, and Peter Simor. You can meet them at the ILCB summer school (last week of August at CIRM) or at the ILCB back-to-school day party (Friday, September 27th at LPL: please save the date). This will also be a good opportunity to welcome our new postdoc (Paul Best, CRPN and LIS) and congratulate Diya (Shreejata Gupta) who obtained a one-year extension of her current postdoc grant.

I wishing all of you a beautiful summer break, and look forward to seeing you back at the ILCB summer school!

Best wishes,

Johannes

Portrait of the month

Magalie Ochs

Magalie Ochs is Associate Professor in Computer Science at Aix-Marseille University in the Laboratoire d’Informatique et des Systèmes (LIS). Since her master in Artificial Intelligence at Montréal University, Magalie’s research aims at integrating social and emotional intelligence in social robots and virtual agents. She has worked in several national and international laboratories: University Paris 8, Orange Lab, University Paris 6 (LIP6), National Institute of Informatics in Tokyo, Telecom ParisTech. She has explored different computational methods and models to endow social robots and virtual characters with socio-emotional capabilities: perception, reasoning and expression. In an interdisciplinary approach, Magalie’s research focuses on…

Figure of the month

Predicting Feedback Position and Type During Conversation

During natural interactions, listeners produce reactions in response to speakers, a phenomenon known as conversational feedback. Feedback depends on the main speaker’s production. Our model uses multimodal features to predict when and what type of feedback will occur during conversations. Throughout the conversations, the model computes the feedback probability (the black curve on the top panel) and predicts feedback when this probability exceeds a given threshold (vertical red lines). Predicted feedback and observed feedback (blue areas) are then compared to assess model performance. By leveraging features like morpho-syntax, prosody, and gestures in the speaker's production, it identifies key moments that trigger listener responses. This computational model provides precise descriptionf of the context in which feedback occurs.

Auriane Boudin, Roxane Bertrand, Stéphane Rauzy, Magalie Ochs, and Philippe Blache
A Multimodal Model for Predicting Feedback Position and Type During Conversation
Speech Communication 159 (April 2024):103066 -- @HAL

Quote of the month

"When we decompose a well-specified computational model into smaller pieces, each of which would apply hundreds or thousands of times in the course of a naturalistic listening session, it becomes possible to quantitatively compare model variants that are based on different leading ideas from linguistics."

Hale, J. T., Campanelli, L., Li, J., Bhattasali, S., Pallier, C., & Brennan, J. R.
Neurocomputational Models of Language Processing.
Annual Review of Linguistics, 2022, 8(1), 427–446. -- PDF