Our group is concerned with the development of algorithms for a range of important speech analysis tasks both for single channel and multichannel speech. These tasks include voice activity detection, speech enhancement, pitch and multipitch tracking, phone segmentation and classification as well as speaker segmentation and identification.
We distinguish between two fundamentally different types of target applications. First, special emphasis is given to difficult environmental conditions, where the target speech signal is subject to cross-talk and embedded in various types of background noise. Second, we develop high-precision algorithms for semi-automatic analysis and processing of speech recorded in well-controlled studio conditions.