My research lies within the broad field of Conversational AI and spoken dialogue systems. Together with the Speech Technology research group at Mercedes-Benz AG that I lead, we focus on methods and technology to realise natural voice-first interaction between humans and machines applying machine learning and artificial intelligence.
Employing machine learning methods, my research addresses the following questions: which properties and abilities must a system have to act in a natural manner, which factors make the behaviour of the system to be perceived as natural, and how to realise this natural interaction from a technical point of view. In other words, the goal is to understand all factors that constitute “natural system behaviour” in the context of spoken interaction.
- [May 2021] Our papers on “Blending Task Success and User Satisfaction: Analysis of Learned Dialogue Behaviour with Multiple Rewards” and “From Argument Search to Argumentative Dialogue: A Topic-independent Approach to Argument Acquisition for Dialogue Systems” have been accepted to SIGDIAL 2021.
- [April 2021] I am co-organising a special session at IWSDS 2021 about “Multilingual approaches to dialogue systems and Conversational AI”.
- [April 2021] Niklas and colleague’s journal paper “EVA 2.0: Emotional and Rational Multimodal Argumentation between Virtual Agents” has been accepted to IT.
- [January 2021] Niklas and colleague’s journal paper “Estimating Subjective Argument Quality Aspects from Social Signals in Argumentative Dialogue Systems” has been accepted to IEEE Access.
- [October 2020] Together with Svetlana Stoyanchev, I am Program Chair of IWSDS 2021.
- [June 2020] Niklas’s paper on “Increasing the Naturalness of an Argumentative Dialogue System through Argument Chains” has been accepted to COMMA 2020 as short paper.
- [June 2020] The position paper on “Towards meaningful, grounded conversations with intelligent agents” that I have written together with Alex Papangelis has been accepted to RoboDial 2.0, a special session at SIGDIAL 2020.
- [June 2020] Our provocation paper on “On the Complexity in Task-oriented Spoken Dialogue Systems” has been accepted to CUI 2020
- [May 2020] Our paper on “Similarity Scoring for Dialogue Behaviour Comparison” has been accepted to SIGDIAL 2020 (watch the talk).
- [February 2020] Louisa, Juliana, and Niklas have their papers accepted at LREC 2020.
- [November 2019] I have been attending the NSF Future Directions Workshop: Toward User-Oriented Agents: Research Directions and Challenges. Update: The final report is out.
- [September 2019] My paper on “Improving Interaction Quality Estimation with BiLSTMs and the Impact on Dialogue Policy Learning” has been a best paper finalist at SIGDIAL 2019 (watch the talk).
- [November 2018] I have been attending the Shonan meeting on “Multimodal Agents for Ageing and Multicultural Societies”.
- [October 2018] Pawel’s paper “MultiWOZ – A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling“ has won Best Ressource Paper at EMNLP 2018.
- [July 2018] Our paper on “Addressing Objects and Their Relations: The Conversational Entity Dialogue Model” has been a best paper finalist at SIGDIAL 2018 (watch the talk).
I am Dialogue Research Lead at Mercedes Benz Research & Development leading the Speech Technology research group with a focus on methods and technology that bring natural spoken human-machine interaction forward thus contributing to the next generations of the Mercedes Benz User Experience. I co-supervise seven doctoral students and I am a lecturer in the “Dialogue Systems” course of the Dialogue Systems Group at Ulm University. Previously, I was a Research Associate at the Spoken Dialogue Systems Group at the University of Cambridge working with Prof. Steve Young and Prof. Milica Gasic within the EPSRC project “Open Domain Statistical Spoken Dialogue Systems”. I have received my Diploma (MSc) in Computer Science from the Karlsruhe Institute of Technology (Germany) in 2010 and my doctorate in engineering (PhD) at the Dialogue Systems Group at Ulm University (Germany) in 2015. The topic of my dissertation was “User-centred Adaptive Spoken Dialogue Modelling”.
- Program Chair of IWSDS 2021
- Area Chair of Track “Dialog and Interactive Systems” at EMNLP-IJCNLP, ACL, EMNLP, NAACL-HLT, EACL, ACL-IJCNLP, since 2019
- Publication Chair of the SIGdial Meeting on Discourse and Dialogue 2019, 2020
- Journal Reviewer for Artificial Intelligence, Computer Speech and Language, Dialogue and Discourse, Journal of Ambient Intelligence and Smart Environments, IEEE Signal Processing Letters, Natural Language Engineering, Review of Managerial Science, Sensors, International Journal of Information Technology & Decision Making
- Conference / Workshop Reviewer for Meeting of Association for Computational Linguistics (ACL), Association for the Advancement of Artificial Intelligence (AAAI) Conference, Conference of the North American Chapter of the Association for Computational Linguistics – Human Language Technologies (NAACL-HLT), Conference on Empirical Methods in Natural Language Processing, Interspeech Conference, SIGDial Meeting on Discourse and Dialogue, Language Resources and Evaluation Conference Spoken Language Technology Workshop (SLT), International Conference on Computational Linguistics (CoLing), International Workshop on Spoken Dialogue Systems (IWSDS), International Conference on Intelligent Environments (IE), NIPS Workshop on Conversational AI: Today’s Practice and Tomorrow’s Potential, International Conference on Signal Processing and Communication Systems, RE-WOCHAT, WOCHAT
- Mentor in the Mentoring Program of the SIGDIAL Meeting on Discourse and Dialogue
- YRRSDS Advisory Committee 2021
- Co-Organizer of the Young Researchers’ Roundtable on Spoken Dialogue Systems (YRRSDS) 2014, 2015