Pejman Mowlaee of Graz University of Technology

Abstract:

The digital processing of speech signals is a key factor in human-machine interaction and is used in different everyday applications including assistive listening devices (digital hearing aids), mobile telephony, automatic speech recognition, speaker recognition, noise reduction and voice command devices. Since the invention of the telephone in 1876, large progress has been made towards advanced techniques developed to improve the achievable quality of the speech signal processing technologies experienced in everyday life. Among these efforts, the Fourier spectral magnitude based speech processing methods have been successfully employed while the spectral phase has been largely neglected. In this talk, we first present an overview on the phase importance/unimportance beliefs in the literature. Then we focus on phase estimation fundamentals which is arguably required to initiate any phase-aware signal processing. In particular, reliable extracted information about phase can be utilized to push the performance achievable by the conventional speech processing methods that rely on the magnitude spectrum only. As some applications we exemplify speech enhancement, automatic speech recognition, and speech quality estimation (some demos are available at www.spsc.tugraz.at/PhaseLab [12]). Finally, some conclusions and future directions will be provided. The content of this presentation is based on our papers published in [3-11] and the overview paper [2] and book [1].

Biography:

Speaker Biography:

Pejman Mowlaee was born in Bandar Anzali, Iran, in March 1983. He received his Electrical Engineering (B.Sc.) degree with straight honors from Guilan University, Rasht, Iran in 2005. He received his M.Sc. degrees in Telecommunication Engineering in signal processing with straight honors from Iran University of Science and Technology, Tehran, Iran, in 2007. He received his PhD. degree at Aalborg University, Aalborg, Denmark in 2010 where he was a research assistant atMultimedia and Information Signal Processing (MISP) under supervision of Prof. Soren Hldt Jensen. From January 2011 till September 2012 he was a Marie Curie post-doctoral fellowship for Digital Signal Processing in Audiology (AUDIS) at Institute of Communication Acoustics (IKA), Ruhr-University Bochum (RUB), Germany, coordinated by Prof. Rainer Martin. Since September 2012, he is a Senior Research and Teaching Associate (Assistant Professor), at Speech and Signal Processing (SPSC) Laboratory in Graz University of Technology in Graz, Austria. He is active reviewer for IEEE Transactions on Audio, Speech and Language Processing, IEEE Signal Processing Letters, ElsevierDigital Signal Processing, Elsevier Speech Communication Journals, EURASIP and reviewer for ICASSP, EUSIPCO and INTERSPEECH conferences and TC member for AASP. Since 2013, he is a senior member of IEEE. He has been an author and co-author of over fifty peer-reviewed publications with research topics of digital speech and audio processing, including speech enhancement, source separation, statistical modeling of speech signals, phase-aware signal processing for speech communication, and robust speech recognition. He was a part of the organizing comittee for EUSIPCO 2010 in Aalborg and AUDIS workshop 2012 in Aachen. He was co-organizer for special session Phase Importance in Speech Processing held at INTERSPEECH 2014 in Singapore. He organized the tutorial session on Phase Estimation From Theory to Practice in INTERSPEECH 2015. He is the guest editor for the special issue on Phase-Aware Signal Processing in Elsevier journal of Speech Communication. He is the author of the book Phase-Aware Signal Processing in Speech Communication: History, Theory and Practice at John Wiley and Sons in 2016. He is the project leader for the standalone project number P28070-N33 from the Austrian Science Fund (FWF).

Email:

Address:Graz University of Technology (TU Graz), Inffeldgasse 16c/EG, Graz, Austria, A-8010

Pejman Mowlaee of Graz University of Technology

Biography:

Email:

Address:Graz, Austria