Seminar: Signal Processing and Systems

ECE Women Community

Model-Based and Learning-Based Approaches for Speech Enhancement and Source Localization

Date: February,06,2023 Start Time: 11:30 - 12:30
Location: 1061, Meyer Building
Add to:
Lecturer: Prof. Dr. Simon Doclo
Affiliations: University of Oldenburg, Germany

Despite the progress in single- and multi-microphone speech enhancement algorithms, speech understanding in adverse acoustic environments with background noise, competing speakers, and reverberation is still a major challenge for many speech communication applications, such as conferencing systems and assistive listening devices. In this presentation, I will present some recent advances in model-based and learning-based approaches for speech enhancement and source localization. More specifically, I will focus on:

  • Blind MVDR-based beamforming and WPE-based dereverberation for acoustic sensor networks with spatially distributed microphones;
  • Deep multi-frame filtering for speech enhancement, in particular integrating the multi-frame MVDR filter into an end-to-end supervised learning framework, where the required parameters are estimated by temporal convolutional networks;
  • Supervised learning-based DOA estimation aiming at generalizing well to different microphone array geometries.

Bio

Prof. Dr. Simon Doclo received an M.Sc. degree in electrical engineering and a Ph.D. in applied sciences from KU Leuven, Belgium, in 1997 and 2003. From 2003 to 2007, he was a Postdoctoral Fellow at the Electrical Engineering Department (KU Leuven) and the Cognitive Systems Laboratory (McMaster University, Canada). From 2007 to 2009, he was a Principal Scientist with NXP Semiconductors in Leuven, Belgium. Since 2009 he has been the head of the Signal Processing Group at the University of Oldenburg, Germany, and scientific advisor of the Fraunhofer Institute for Digital Media Technology. His research activities center around acoustical and biomedical signal processing, more specifically, microphone array processing, speech enhancement, active noise control, auditory attention decoding, and hearing aid processing.

Prof. Doclo received several awards, including the EURASIP Signal Processing Best Paper Award in 2003, the IEEE Signal Processing Society 2008 Best Paper Award, and the best paper award of the Information Technology Society (ITG) in 2019. He is a member of the IEEE Signal Processing Society Technical Committee on Audio and Acoustic Signal Processing and the EAA Technical Committee on Audio Signal Processing. Prof. Doclo was the Technical Program Chair of the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) in 2013 and Chair of the ITG Conference on Speech Communication in 2018. In addition, he serves as Senior Area Editor for IEEE/ACM Transactions on Audio, Speech and Language Processing, was an associate editor for IEEE/ACM Transactions on Audio, Speech and Language Processing and EURASIP Journal on Advances in Signal Processing, and served as guest editor for several special issues (IEEE Signal Processing Magazine, Elsevier Signal Processing).

 

All Seminars
Skip to content