S
Sebastian Möller
Researcher at Technical University of Berlin
Publications - 531
Citations - 7103
Sebastian Möller is an academic researcher from Technical University of Berlin. The author has contributed to research in topics: Quality (business) & Quality of experience. The author has an hindex of 34, co-authored 491 publications receiving 5830 citations. Previous affiliations of Sebastian Möller include German Research Centre for Artificial Intelligence & University of Oslo.
Papers
More filters
Posted Content
Evaluating German Transformer Language Models with Syntactic Agreement Tests
TL;DR: This work analyses German pre-trained transformer language models and shows that state-of-the-art German TLMs generally perform well on agreement tasks, but also identifies and discusses syntactic structures that push them to their limits.
Benutzerstudien zur Bewertung multimodaler, interaktiver Anzeigetafeln in unterschiedlichen Entwicklungsstufen
TL;DR: Die Ergebnisse der Fragebogendaten zeigen, dass die multimodalen Systemvarianten hinsichtlich der hedonischen Qualitäten besser beurteilt wurden als die unimodale Variante.
Journal ArticleDOI
Influence of environmental background noise on speech quality assessments task in crowdsourcing microtask platform
Babak Naderi,Sebastian Möller,Frank Neubert,Victor Höller,Friedemann Köster,Laura Fernández Gallardo +5 more
TL;DR: This work reports on the current activity on using microphone signals for evaluating environmental conditions in crowdtesting using a mobile crowdsourcing platform and the impact of environmental noise.
Proceedings ArticleDOI
Comparison of EWPSNR and MOS on an Eye-tracking Labelled Video Dataset
TL;DR: The correlation between EWPSNR and Mean Opinion Score (MOS) on an eye-tracking dataset is measured to evaluate the performance ofEWPSNR to predict the subjective quality and to develop perceptual objective metrics as an alternative to subjective assessments.
Proceedings ArticleDOI
Correlation Between Model-based Approximations of Grounding-related Cognition and User Judgments.
TL;DR: A model of the belief the user has about the system state, and a model of vocabulary alignment are proposed, which show that parameters derived from these models are significantly correlated with the users’ quality perception.