The SECTG Cluster hosts a workshop amongst Early Stage Researchers

early stage researchers workshop

The SECTG Cluster celebrated a meeting targeted to Early Stage Researchers (ESRs) in the field of Artificial Intelligence and Extended Reality to share research results and advancements of  SONICOM, EXPERIENCE, CAROUSEL, TOUCHLESS, and GuestXR projects. The event was held at the Imperial College of London on November 23rd, 2023.

The meeting included a total of 15 talks delivered by early stage researchers partners from each of the five projects of the cluster. During the event, attendees exchanged ideas and networked with fellow scholars, disseminating their research, and presenting their work.

In the case of the GuestXR project, the topics discussed were empathetic haptics, the influence of prior acquaintance on the shared VR experience, and the use of deep learning for acoustic matching in the VR context.

Firstly, Jeanne Hecquard, doctoral student from Inria, introduced the development of a virtual meeting scenario wherein a human user attends a presentation with several virtual agents. The study promotes positive social interactions in VR by fostering empathy with other users present in the virtual scene, proposing affective haptic feedback to reinforce the connection with another user by transmitting their physiological state.

The second presentation was delivered by Esen Küçüktütüncü, PhD candidate from the University of Barcelona. She discussed whether prior acquaintance has an influence on the user experience in a shared VR scenario. Moreover, she introduced the tools used for copresence and how machine learning algorithms are operated to assess participant sentiments.

Joanna Luberadzka, researcher at the Multimedia Technologies Unit from Eurecat, continued by presenting a work that estimates the Room Impulse Response (RIR) from speech recorded in a reverberant acoustic space. The approach of this study is to use deep learning, specifically an encoder-decoder network, which takes a time domain signal at the input and estimates the RIR (or parameters required to approximate an RIR) at the output.

The SECTG cluster is conformed by the projects GuestXR, SONICOM, EXPERIENCE, CAROUSEL and TOUCHLESS, all of them leveraging human-centric and responsible Artificial Intelligence technologies to address issues such as social (mis-) trust, belief formation, the permeation of private and public spheres, social exclusion and divides.