[iva] [Meetings] RSS 2024 Workshop on Embodied Voices (WEV) - call for participation

[Paige Tuttosi]

Dear colleagues,

We invite you to attend our hybrid workshop: RSS 2024 Workshop on Embodied Voices (WEV)

Website: https://rosielab.github.io/wev/
Hybrid attendance sign-up: https://forms.gle/9wy89rL5NGZE4ouE8
Workshop: 8:45-17:00 CET, July 15th 2024
Location: Hybrid, Delft University of Technology, Netherlands and online

Overview and Aim

In this workshop, we aim to bring together and nourish a multidisciplinary community of those working in speech synthesis and perception, robotics, psychology and their applications in embodied interaction. By doing so we hope to bridge the disconnect between state-of-the-art generative models for voice and the in the wild implementation in embodied characters, whether it be robots, virtual agents or beyond.

Voice Design Challenge (250€ prize)

We invite in-person and online participants to design compelling and appropriate voices for robots!  Teams will be assigned a physical robot and/or an avatar with a short personal story to provide context such as their job, where they are, and who will be using them. Working through a co-design canvas, participants will brainstorm an appropriate voice for their robots. They will then be provided with a state-of-the-art TTS system through an online GUI allowing control of the voice based on reference files and linguistic context to generate their desired voices and send them to the robots. We will finish with demos where each team will present their design process and selection.

Robot embodiments (robot, image or avatar) include:
Nao (United robotics group)
Furhat
TIAGo Pro (Pal robotics)
Mirokai (Enchanted Tools)

Guest Judge:
Dr. Roger K. Moore

Register your interest here:
https://forms.gle/9wy89rL5NGZE4ouE8

Invited Speakers:

Dr. Lea Luka Sikau - How human voices are produced, modified and believed to shatter glass
Dr. Zhengjun Yue - Speech Technology for Healthcare in Robotics
Dr. Tony Belpaeme - Giving Robots a Voice
Dr. Kazuhiro Nakadai - Robot Audition for Human Robot Interaction
Dr. Catherine Lai - Watch your tone! Understanding prosodic variation in synthetic speech
Dr. James P. Trujillo - Facial Signals Combine to Influence the Interpretation of Speech

Lightning Talks:

Virtual Datasets for Spatial Hearing in Robotics - O. Eldardeer, L. Grasse, M. Tata, F. Rea

No More Mumbles: Enhancing Robot Intelligibility through Speech Adaptation - Q.  Ren, Y. Hou, D. Botteldooren, T. Belpaeme

Hey, OK, Play! A rough guide for the dynamic design and interplay of multimodal, nonverbal communication signals in embodied voice assistants - O. Niebuhr, I. Valls-Ratés

The CANELA Framework: Creating Audio-based Novel Engineered LAnguages for HRI - H. Garcia Goo, V. Evers, K. Truong

Organizers

   -Paige Tuttösí, Simon Fraser University & FEMTO-ST
  -Charlotte Stinkeste, KTH Royal Institute of Technology
  -Siyang Wang, KTH Royal Institute of Technology
  -Minja Axelsson, University of Cambridge
  -Paul Maublanc, Aarhus University
  -Emma Hughson, Cambridge Consultants
  -Chuxuan Zhang, Simon Fraser University
  -Marine Chamoux, Aldebaran
  -Lawrence Kim, Simon Fraser University
  -Angelica Lim, Simon Fraser University

Contact

All questions about submissions should be emailed to wev [AT] rosielab.ca
Cheers, and looking forward to seeing you online or in Delft!

Paige Tuttösí



-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.uni-bielefeld.de/mailman2/unibi/public/iva-list/attachments/20240627/4c2eaf16/attachment-0001.html>