Der Rückblick zum TEWI-Kolloquium von Sebastian Möller, Quality and usability lab, Telekom Innovation Labs, TU Berlin am 23.11.2012 beinhaltet die Videoaufzeichnung sowie die Folien:
[iframe height=“350″ src=“http://video.aau.at/video.php?video=ftf_moeller.mp4″]
Abstract: Speech-based services come in an ever increasing variety, and it becomes more and more difficult for system designers and service operators to ensure a sufficiently high quality, usability, and finally acceptance of these services. Whereas the ultimate way to measure quality is by asking test users, such empirical tests require a substantial effort in terms of time and money, and are thus commonly limited to an absolute minimum. One way to cope with this problem is to estimate the quality which will be perceived by the user on the basis of physically measurable quantities, such as speech signals, or parameters describing a spoken interaction.
In this talk, we will present approaches for prediction the quality and usability of speech-based services taking three common application examples: (1) Speech transmission services where overall quality as well as individual quality dimensions can be estimated from transmitted and reference speech signals; (2) synthesized-speech services where no reference is available but can be built artificially with the help of prior knowledge; as well as (3) spoken dialogue services where user behavior needs to be predicted, with the help of probabilities and rules. Small examples will underline the usefulness but also the limitations of the currently available approaches.
CV: Sebastian Möller was born in 1968 and studied electrical engineering at the universities of Bochum (Germany), Orléans (France) and Bologna (Italy). From 1994 to 2005, he held the position of a scientific researcher at the Institute of Communication Acoustics (IKA), Ruhr-University Bochum, and worked on speech signal processing, speech technology, communication acoustics, as well as on speech communication quality aspects. Since June 2005, he works at Deutsche Telekom Laboratories, TU Berlin. He was appointed Professor at TU Berlin for the subject „Quality and Usability“ in April 2007, and heads the „Quality and Usability Lab“ at Telekom Innovation Laboratories.
He received a Doctor-of-Engineering degree at Ruhr-University Bochum in 1999 for his work on the assessment and prediction of speech quality in telecommunications. In 2000, he was a guest scientist at the Institut dalle Molle d’Intélligence Artificielle Perceptive (IDIAP) in Martigny (Switzerland) where he worked on the quality of speech recognition systems. He gained the qualification needed to be a professor (venia legendi) at the Faculty of Electrical Engineering and Information Technology at Ruhr-University Bochum in 2004, with a book on the quality of telephone-based spoken dialogue systems. In September 2008, we worked as a Visiting Fellow at MARCS Auditory Laboratories, University of Western Sydney (Australia) on the evaluation of avatars. In November 2011, he was Visiting Professor at the Universidad de Granada (Spain), and from Februar to April 2012 Visiting Professor at the Ben Gurion University of the Negev in Be’er Sheva (Israel). He is currently Adjunct Professor at the University of Canberra (Australia). His most recent book on „Quality Engineering“ was published in 2010.
Sebastian Möller was awarded the GEERS prize in 1998 for his interdisciplinary work on the analysis of infant cries for early hearing-impairment detection, the ITG prize of the German Association for Electrical, Electronic & Information Technologies (VDE) in 2001, the Lothar-Cremer prize of the German Acoustical Association (DEGA) in 2003, a Heisenberg fellowship of the German Research Foundation (DFG) in 2005, and the Johann Philipp Reis prize in 2009. Since 1997, he has taken part in the standardization activities of the International Telecommunication Union (ITU-T) on transmission performance of telephone networks and terminals. He is currently acting as a Rapporteur for question Q.8/12.