Steven Wegmann
Director
Speech
International Computer Science Institute
United States of America
Biography
Steven Wegmann has worked at industrial research laboratories on problems in speech processing for nearly two decades, holding positions at Dragon Systems, Lernout & Hauspie, VoiceSignal Technologies, Nuance Communications, and Cisco Systems. Earlier in his career, he was a mathematician who specialized in algebraic topology. He obtained his doctorate in mathematics at the University of Warwick while he was a Marshall Scholar. He has been a staff researcher at ICSI since 2010 and began leading the Speech Group in 2013.
Research Interest
Key research areas include auditory-inspired signal processing, statistical modeling, rich transcription of natural and impromptu meetings, and rich transcription of broadcast and conversational telephone speech.
Publications
-
Ravuri S, Wegmann S. 2016. How neural network depth compensates for HMM conditional independence assumptions in DNN-HMM acoustic models. Proceedings of Interspeech 2016.
-
Su H, Wegmann S. 2016. Factor analysis based speaker verification using ASR. Proceedings of Interspeech 2016.
