Timo Gerkmann Postdoctoral Researcher Sound and Image Processing Lab KTH Campus, Osquldas v. 10th Floor, Room Royal Institute of Technology (KTH) Stockholm, Sweden  mailto:gerkmann [at] kth.se Phone: +46-8-790 8869 Fax: +46-8-791 7654

---

Biography

Timo Gerkmann studied electrical engineering at the universities of Bremen and Bochum, Germany. He received his Dipl.-Ing. degree in 2004 and his Dr.-Ing. degree in 2010 both at the Institute of Communication Acoustics (IKA) at the Ruhr-Universität Bochum, Bochum, Germany. From January 2005 to July 2005 he visited Siemens CR in Princeton, NJ, USA. Currently he is a postdoctoral researcher at the Sound and Image Processing Lab at the Royal Institute of Technology (KTH), Stockholm, Sweden. His main research interests are on digital speech and audio processing, including single and multichannel speech enhancement.

---

Publications

Year 2011

Author:	 Jalil Taghia, Timo Gerkmann, Arne Leijon
Title:	 Blind Source Separation of Nondisjoint Sources in the Time-Frequency Domain with Model-based Determination of Source Contribution
In:	 IEEE International Symposium on Signal Processing and Information Technology
Date:	 December 2011

Author:	 Nasser Mohammadiha, Timo Gerkmann, Arne Leijon
Title:	 A New Approach for Speech Enhancement Based on a Constrained Nonnegative Matrix Factorization
In:	 IEEE International Symposium on Intelligent Signal Processing and Communication Systems
Date:	 December 2011

Author:	 Timo Gerkmann and Richard C. Hendriks
Title:	 Noise Power Estimation Based on the Probability of Speech Presence
In:	 Proceedings IEEE Workshop on Applications of Signal Processing to Audio and Acoustics
Date:	 October 2011

Author:	 Nasser Mohammadiha, Timo Gerkmann, Arne Leijon
Title:	 A New Linear MMSE Filter for Single Channel Speech Enhancement Based on Nonnegative Matrix Factorization
In:	 Proceedings IEEE Workshop on Applications of Signal Processing to Audio and Acoustics
Date:	 October 2011

Author:	 Timo Gerkmann
Title:	 Cepstral Weighting for Speech Dereverberation Without Musical Noise
In:	 Proceedings European Signal Processing Conference
Pages:   2309--2313
Date:	 September 2011

Author:	 Richard C. Hendriks, Timo Gerkmann
Title:	 Noise Correlation Matrix Estimation for Multi-Microphone Speech Enhancement
In:      IEEE Trans. Audio, Speech and Language Processing (accepted for publication)

Author:	 Richard C. Hendriks, Timo Gerkmann
Title:	 Estimation of the Noise Correlation Matrix
In:	 Proceedings IEEE International Conference on Acoustics, Speech, and Signal Processing
Pages:   4740--4743
Date:	 May 2011

Author:	 Rainer Martin, Timo Gerkmann
Title:	 Besser Hören dank Algorithmen: Wie digitale Signalverarbeitung Hörgeräte verbessert und die Kommunikation erleichtert
In:	 rubin Wissenschaftsmagazin
Date:	 Spring 2011

Year 2010

Author:	 Timo Gerkmann
Title:	 Statistical Analysis of Cepstral Coefficients and Applications in Speech Enhancement
School:	 Ruhr-Universität Bochum, Bochum, Germany
Date:	 December 2010
Type:	 PhdThesis
Note:	 http://www.dr.hut-verlag.de/9783868536966.html

Author:	 Timo Gerkmann, Martin Krawczyk, Rainer Martin
Title:	 Speech presence probability estimation based on temporal cepstrum smoothing
In:	 Proceedings IEEE International Conference on Acoustics, Speech, and Signal Processing
Pages:	 4254-4257
Date:	 March 2010

Author:	 Timo Gerkmann, Rainer Martin
Title:	 Cepstral smoothing with reduced computational complexity
In:	 ITG-Fachtagung Sprachkommunikation
Date:	 October 2010

Author:	 Timo Gerkmann, Rainer Martin
Title:	 Empirical distributions of DFT-domain speech coefficients based on estimated speech variances
In:	 International Workshop on Acoustic Echo and Noise Control
Date:	 August 2010

Author:	 Anil Nagathil, Timo Gerkmann, Rainer Martin
Title:	 Musical Genre Classification Based on a Highly-resolved Cepstral Modulation Spectrum
In:	 Proceedings European Signal Processing Conference
Pages:	 462-466
Date:	 August 2010

Year 2009

Author:	 Timo Gerkmann, Rainer Martin
Title:	 On the Statistics of Spectral Amplitudes After Variance Reduction by Temporal Cepstrum Smoothing and Cepstral Nulling
Journal: IEEE Transactions on Signal Processing
Volume:	 57
Number:	 11
Pages:	 4165-4174
Date:	 November 2009

Author:	 Timo Gerkmann, Rainer Martin, Derya Dalga
Title:	 Multi-Microphone Maximum A Posteriori Fundamental Frequency Estimation in the Cepstral Domain
In:	 Proceedings IEEE International Conference on Acoustics, Speech, and Signal Processing
Pages:	 4505-4508
Date:	 April 2009

Year 2008

Author:	 Colin Breithaupt, Timo Gerkmann, Rainer Martin
Title:	 A Novel A Priori SNR Estimation Approach Based on Selective Cepstro-Temporal Smoothing
In:	 Proceedings IEEE International Conference on Acoustics, Speech, and Signal Processing
Pages:	 4897-4900
Date:	 April 2008

Author:	 Timo Gerkmann, Colin Breithaupt, Rainer Martin
Title:	 Improved A Posteriori Speech Presence Probability Estimation Based on a Likelihood Ratio with Fixed Priors
Journal: IEEE Trans. Audio, Speech and Language Processing
Volume:	 16
Number:	 5
Pages:	 4165-4174
Date:	 July 2008

Author:	 Timo Gerkmann, Colin Breithaupt, Rainer Martin
Title:	 Bias Compensation for Cepstro-Temporal Smoothing of Spectral Filter Gains
In:	 ITG-Fachtagung Sprachkommunikation
Date:	 January 2008

Author:	 Dirk Mauler, Timo Gerkmann, Rainer Martin
Title:	 An Analysis of Quefrency Selective Temporal Smoothing of the Cepstrum in Speech Enhancement
In:	 International Workshop on Acoustic Echo and Noise Control
Date:	 January 2008

Year 2007

Author:	 Colin Breithaupt, Timo Gerkmann, Rainer Martin
Title:	 Cepstral Smoothing of Spectral Filter Gains for Speech Enhancement Without Musical Noise
Journal: IEEE Signal Processing Letters
Date:	 December 2007

Year 2006

Author:	 Timo Gerkmann, Rainer Martin
Title:	 Soft Decision Combining for Dual Channel Noise Reduction
In:	 ISCA Interspeech
Pages:	 2134-2137
Date:	 September 2006

Author:	 Justinian Rosca, Timo Gerkmann, Doru-Cristian Balcan
Title:	 Statistical Inference of Missing Speech Data in the ICA Domain
In:	 Proceedings IEEE International Conference on Acoustics, Speech, and Signal Processing
Volume:	 5
Pages:	 617-620
Date:	 May 2006

Back