Kolloquium WiSe 2023/24

Prof. Dr.-Ing Sebastian Möller

When: Mo, 11.03.2024, at 16:15

Where: Konrad-Zuse-Hörsaal (Room B-201)

We are going to provide a livestream during the lecture. For the access data please register at https://mail-mm01.rrz.uni-hamburg.de/mailman/listinfo/kolloquium.

Topic

Recent Work in Speech and Language Technology

Language: english

Abstract

In this overview talk, I would like to shed light on recent activities our teams have performed in speech and language technologies, and in human-machine interaction in a larger sense. We start from core technologies for extracting information from text, which we use to detect disinformation, which we consider as a hybrid task, and analyze how human evaluators can be supported best using machine classifiers. This requires explanations of model behavior, which we address via textual and dialogic explainability. Spoken and written dialog and its evaluation is also another topic of our research. On the speech side, we continue with our dimension-based speech quality assessment framework, which is also useful for disentangling speaker characteristics, used e.g. in speaker anonymization. We also work on the effect of listener characteristics on speech quality, as well on evaluating speech quality in a conversational scenario. Finally, I briefly summarize some work on XR interfaces, used e.g. for conveying sign language. The models and tools we use in our research are commonly shared with the community, both on a national and european level.

Bio

Sebastian Möller studied electrical engineering at the universities of Bochum, Orléans (France) and Bologna (Italy). From 1994 to 2005, he was a research associate and later a university lecturer at the Institute for Communication Acoustics (IKA) at Ruhr University Bochum, where he worked on speech signal transmission, speech technology and communication acoustics, as well as on aspects of the quality of speech-based systems. He received his PhD from Ruhr-Universität Bochum in 1999 with a thesis on the assessment and prediction of speech quality in telecommunications, and his habilitation in 2004 with a book on the quality of telephone-based spoken dialog systems. From 2005 to 2015, he worked at Telekom Innovation Laboratories, an affiliated institute of Technische Universität Berlin. In April 2007, he was appointed university professor in the field of "Quality and Usability" at TU Berlin, working on the quality and user experience of speech-based and multimodal systems. He has contributed largely to the scientiific basis of Quality of Experience (QoE), and had practical impact by shaping recommendations of the International Telecommunication Union, ITU, on evaluation methods for different types of services. Since 2017, he has headed the research area "Speech and Language Technology" at the German Research Center for Artificial Intelligence, DFKI, as Scientific Director. He is further Adjunct professor at the University of Technology in Sydney, and was a member of the board of the International Speech Communication Association, ISCA, from 2016 to 2023. Between 2021 and 2023, he served as a president to ISCA.