Gabriel Skantze

PROFESSOR

Kungliga Tekniska Högskolanhttps://www.kth.se/profile/skantze

Works for

DIVISION OF SPEECH, MUSIC AND HEARING

Telephone

+46 8 790 78 74

Address

LINDSTEDTSVÄGEN 24

E-mail

skantze@kth.se

Researcher ID

ORCID IDGoogle Scholar ID

About me

I am a Professor in Speech Communication and Technology, with a specialization in Conversational Systems, at the Department of Speech Music and Hearing at KTH in Stockholm.

In my research I study human communication and develop computational models that allow computers and robots to have face-to-face conversations with humans. This involves both verbal and non-verbal (gaze, prosody, etc) aspects of communication, and my research involves phenomena such as turn-taking, feedback, and joint attention, as well as language learning and grounding. Since social robots are likely to play an important role in our future society, the technology has direct applications, but it can also be used to increase our understanding of the mechanisms behind human communication. This requires an interdisciplinary approach, which includes language technology, artificial intelligence, machine learning, phonetics, and linguistics.

In 2014, I co-founded the company Furhat Robotics together with Samer Al Moubayed and Jonas Beskow at KTH. I am working part-time as a Chief Scientist in the company.

I am President Emeritus of SIGdial, the ACL (Association for Computational Linguistics) Special Interest Group on Discourse and Dialogue, Associate Editor for the Human-Robot Interaction section of Frontiers in Robotics and AI, and Action Editor for the ACL Rolling Review.

I am an alumni member of the Young Academy of Sweden - an independent, cross-disciplinary forum for some of the most promising young researchers in Sweden in all disciplines.

Background

I have a MSc in Cognitive Science from Linköping University and I did my PhD in Speech Communication at KTH in 2007. The title of my thesis is Error Handling in Spoken Dialogue Systems: Managing Uncertainty, Grounding and Miscommunication. I was a post-doc at the University of Potsdam in 2008, became Docent in Speech Technology at KTH in 2012, Assistant Professor in 2013, Associate Professor in 2016 and Professor in 2018.

Master thesis opportunities

Contact me if you are interested in doing your Master thesis in any of the projects listed below.

Ongoing research projects

	Representation Learning for Conversational AI.How can we develop generic representation learning that is better suited for conversation than current language models?Funded by WASP (2021-2026).
	PREDICON - Prediction and Coordination for Conversational AI.How can we use deep learning to predict human actions in a conversation?Funded by the Swedish Research Council (2021-2024).
	AnalyTIC - Understanding Predictive models of Turn-taking in Spoken Interaction.How can we use deep learning models to better understand the signals used to coordinate turn-taking in human communication?Funded by Riksbankens Jubileumsfond (2021-2023).
	Anticipatory Control in Conversational Human-Robot Interaction.How can a robot anticipate the conversational behaviour of multiple speakers it is interacting with? Funded by WASP (2024-2028).
	Relying on a Robot - How Agency and Anthropomorphism in Human-Centered AI Affects Social Decision Making.How can we use experimental paradigms from behavioral economics to study human trust towards robots? Funded by Marianne and Marcus Wallenberg Foundation (2022-2027).
	Robot learning of symbol grounding in multiple contexts through dialog. How can a robot understand references to objects in the shared visual scene, and also make references to objects? Funded by WASP (2018-2023).
	Social robots accelerating the transition to sustainable transport.How can social robots be used as hosts on driverless busses? Funded by Energimyndigheten (2020-2024).
	Early Language Development in the Digital Age (e-LADDA).How can social robots be used for language learning? A Marie Skłodowska-Curie Innovative Training Network, funded by EU MSCA ITN (2020-2023)
	Empowering Cultural Integration and Language Learning through Conversational AI. Funded by Digital Futures (2024-2026)
	COBRA: Conversational Brains.Modelling the linguistic, cognitive and brain mechanisms that allow conversation to unfold in both human-human and human-machine interactions.A Marie Skłodowska-Curie Innovative Training Network, funded by EU MSCA ITN (2020-2023)