O. Roesler

Oliver Roesler

About Me

I am a PhD student at the Brain Embodiment Lab of the University of Reading, a researcher at the Artificial Intelligence Lab of the Vrije Universiteit Brussel, and a research scientist at Modality.AI, Inc. My research focuses on the development of mechanisms to enable natural, adaptive, and open-ended human-agent interactions through an interdisciplinary approach that combines work in knowledge representation and reasoning, language grounding, reinforcement learning based action learning as well as multimodal prediction of human affective and mental states.

Interests
  • Language Grounding
  • Knowledge Representation
  • Multimodal Learning
  • Human-Agent Interaction

Recent Publications

(2021). Multimodal Dialog Based Speech and Facial Biomarkers Capture Differential Disease Progression Rates for ALS Remote Patient Monitoring. In Proceedings of the 32nd International Symposium on Amyotrophic Lateral Sclerosis and Motor Neuron Disease.

Cite

(2021). Voice Activity Detection Considerations in a Dialog Agent for Dysarthric Speakers. In Proceedings of the 12th International Workshop on Spoken Dialog Systems (IWSDS).

PDF Cite

(2021). Multimodal Conversational Technology for Remote Assessment of Symptom Severity in People with Schizophrenia. In Proceedings of the Society for Neuroscience (SfN) Annual Meeting.

Cite

(2021). Investigating the Interplay Between Affective, Phonatory and Motoric Subsystems in Autism Spectrum Disorder Using a Multimodal Dialogue Agent. In Proceedings of the 22nd Annual Conference of the International Speech Communication Association (Interspeech).

PDF Cite DOI

(2021). Investigating the Utility of Multimodal Conversational Technology and Audiovisual Analytic Measures for the Assessment and Monitoring of Amyotrophic Lateral Sclerosis at Scale. In Proceedings of the 22nd Annual Conference of the International Speech Communication Association (Interspeech).

PDF Cite Video DOI

(2021). Unsupervised Online Grounding for Social Robots. Robotics, Volume 10, Number 2.

PDF Cite DOI