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
Proceedings Article
Diagnostic Assessment of Telephone Transmission Impact on ASR Performance and Human-to-Human Speech Quality
TL;DR: This paper addresses the transmission channel impact on human-to-human speech communication quality as well as on ASR performance by developing a simulation model which implements all types of stationary impairments which can be found in the mentioned networks.
Proceedings ArticleDOI
Transmission channel effects on human speaker identification in multiparty conference calls
TL;DR: Listeners identified the talkers while listening to the degraded conversations, being more accurate for particular transmission scenarios, and show that human speaker identification can be considered as an additional criterion when judging the benefits of enhanced bandwidths.
Book ChapterDOI
Qualität von Sprach- und Audio-Übertragungssystemen
TL;DR: In this article, the authors present a verwendete Verfahren zur Bestimmung der Qualitat informations-and kommunikation-stechnischer Systeme behandelt werden.
Proceedings Article
Towards standardized metrics and tools for spoken and multimodal dialog system evaluation: position paper
TL;DR: It is argued that standardized metrics and automatic evaluation tools are necessary for speeding up knowledge generation and development processes for dialog systems.
Posted Content
Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools
TL;DR: Thermostat as discussed by the authors is a large collection of model explanations and accompanying analysis tools, which allows to compare models, datasets and explainers without the need to orchestrate implementation details.