dr hab. inż. Konrad Kowalczyk, prof. AGH

Head of the Group - Associate Professor

Contact details:
office: C2 Building, Room 418
phone: +48 12-617-3639
email: konrad.kowalczyk@agh.edu.pl

Bio

Konrad Kowalczyk received the B.Eng. and M.Sc. degrees in electronics and telecommunications from AGH University of Science and Technology, Krakow, Poland, in 2005, the Ph.D. degree in electronics from the School of Electronics, Electrical Engineering and Computer Science, Queen’s University, Belfast, U.K., in 2009, and the Habilitation (D.Sc.) degree in information and communication technology (ICT) from AGH University of Science and Technology in Krakow, in 2020. During his doctoral studies on numerical modelling of room acoustics at Queen’s University, he was associated with the Sonic Arts Research Centre (SARC). He was a Visiting Ph.D. Student at the Center for Computer Research in Music and Acoustics (CCRMA), Stanford University, in 2007 and at the Audio Lab, University of York, U.K., in 2008. From 2009 until 2011, he was a Postdoctoral Research Fellow at the Chair of Multimedia Communications and Signal Processing (LMS), University of Erlangen-Nuremberg, Germany, where he worked on acoustic scene analysis using microphone arrays. From 2012 until 2014 he was with Audio and Multimedia Division of Fraunhofer Institute for Integrated Circuits IIS and the International Audio Laboratories Erlangen as an Associate Researcher for communication acoustics and spatial audio processing. In 2015 he joined the Faculty of Computer Science, Electronics and Telecommunications, AGH University of Science and Technology in Krakow. Since 2020 he holds a position of an Associate Professor and heads AGH’s Signal Processing Group.

Konrad Kowalczyk was a finalist of the IEEE Best Student Paper Contest at the ICASSP conference held in Hawaii in 2007, a winner of the AES Student Technical Paper Award at the AES convention held in Amsterdam in 2008, and a coauthor of a paper that won the Best Student Paper Award at IWAENC conference held in Antibes, France in 2014. In 2016 and 2019 he received the best paper awards at IEEE SPA conferences held in Poznan. He also received the Stanislaw Staszic Medal for the best graduate of AGH in 2005 and in 2016 he received a scholarship of the Polish Ministry of Science and Higher Education (MNiSW) for Distinguished Young Scientists. In 2015, as a laureate of the Top 500 Innovators program, he completed postgraduate training in science management and commercialization at the University of Cambridge and the University of Oxford, U.K.


Research interests

  • speech and audio signal processing
  • machine learning: deep neural network (DNN)-based audio and speech processing
  • array signal processing: beamforming, adaptive multichannel filtering
  • speech enhancement: dereverberation, noise reduction, source separation
  • distributed signal processing: self-localization, synchronization, signal enhancement
  • speech processing: speaker recognition
  • sound field analysis: source localization, acoustic parameter inference
  • virtual acoustics: room acoustic simulations, in-car sound reproduction
  • acoustic event detection and classification
  • spatial audio acquisition and rendering over loudspeakers and headphones

Research projects

Konrad Kowalczyk is currently the Principle Investigator in the following research projects:
1. “Audio Processing using Distributed Acoustic Sensors (APDAS)”, 2018-2022, Program First TEAM, Foundation for Polish Science (FNP)
2. “Analiza zastosowania uczenia maszynowego w przestrzennym przetwarzaniu sygnałów dźwiękowych (Machine learning for spatial sound processing)”, 2019-2022, Program OPUS, National Science Center (NCN)

Main past research projects:
1. “Analiza możliwości wykorzystania akustyki pomieszczeń w celu poprawy jakości ekstrakcji sygnałów mowy (Analysis of using room acoustics information for speech signal extraction)”, 2015-2017, Program FUGA, National Science Center (NCN)
2. “Video COmmunication for NEtworked CommuniTies (VCONECT)”, 2012 -2014, EU FP7 Information and Communication Technologies (ICT), Fraunhofer Institute for Integrated Circuits IIS, Erlangen, Germany
3. “Self-Configuring ENvironment-aware Intelligent aCoustic sensing”, 2009-2011, EU FP7 Future and Emerging Technologies (FET), Friedrich-Alexander University of Erlangen-Nuremberg, Germany
4. “Numerical Modelling of Acoustic Spaces for Auralization and Acoustic Prediction”, 2005 – 2009, EU ESF Program, Queen’s University, Belfast, UK


Teaching

I am a supervisor of Ph.D., M.Sc., B.Eng. theses work and am running lectures for the following courses:

  • Signal Processing (B.Eng. level)
  • Digital Signal Processing (B.Eng. level)
  • Advanced Techniques in Signal Processing (M.Sc. level)
  • Statistical Signal Processing in Audio and Speech Applications (Doctoral School)

Main publications before joining AGH

Journal articles:
[J1] J. Sheaffer, M. van Walstijn, B. Rafaely, and K. Kowalczyk, “Binaural reproduction of finite difference simulations using spherical array processing,” IEEE/ACM Trans. on Audio, Speech and Language Processing, vol. 23, No. 12, pp. 2125-2135, Dec. 2015.
[J2] K. Kowalczyk, O. Thiergart, M. Taseska, G. Del Galdo, and V. Pulkki, E.A.P. Habets, “Parametric spatial sound processing: a flexible and efficient solution to sound scene acquisition, modification and reproduction,” IEEE Signal Processing Magazine, vol. 32, No. 2, pp. 31-42, Mar. 2015.
[J3] P. Götz, K. Kowalczyk, A. Silzle, and E.A.P. Habets, “Mixing time prediction using spherical microphone arrays,” J. Acoustical Society of America, vol. 137, No. 2, pp. EL206-212, Feb. 2015.
[J4] D. Markovic, K. Kowalczyk, F. Antonacci, C. Hofmann, A. Sarti, and W. Kellermann, “Estimation of acoustic reflection coefficients through pseudospectrum matching,” IEEE/ACM Trans. on Audio, Speech and Language Processing, vol. 22, No. 1, pp. 1-13, Jan. 2014.
[J5] E. Mabande, K. Kowalczyk, H. Sun, and W. Kellermann, “Room geometry interference based on spherical microphone array eigenbeam processing,” J. Acoustical Society of America (JASA), vol. 134, No. 4, pp. 2773-2789, Oct. 2013.
[J6] K. Kowalczyk, E.A.P. Habets, W. Kellermann, and P.A. Naylor, “Blind system identification using sparse learning for TDOA estimation of room reflections,” IEEE Signal Processing Letters, vol. 20, No. 7, pp. 653-656, Jul. 2013.
[J8] H. Sun, E. Mabande, K. Kowalczyk, and W. Kellermann, “Localization of distinct reflections in rooms using spherical microphone array eigenbeam processing,” J. Acoustical Society of America (JASA), vol. 131, No. 4, pp. 2828-2840, Apr. 2012.
[J9] K. Kowalczyk and M. van Walstijn, “Room acoustics simulation using 3-D compact explicit FDTD schemes,” IEEE Trans. on Audio, Speech and Language Processing, vol. 19, No. 1, pp. 34-46, Jan. 2011.
[J10] K. Kowalczyk, M. van Walstijn, and D.T. Murphy, “A phase grating approach to modeling surface diffusion in FDTD room acoustics simulations,” IEEE Trans. on Audio, Speech and Language Processing, vol. 19, No. 3, pp. 528-537, Mar. 2011.
[J11] K. Kowalczyk and M. van Walstijn, “Wideband and isotropic 2D room acoustics simulation with interpolated FDTD schemes,” IEEE Trans. on Audio, Speech and Language Processing, vol. 18, No. 1, pp. 78-89, Jan. 2010.
[J12] K. Kowalczyk and M. van Walstijn, “Formulation of a locally reacting wall in FDTD/K-DWM modeling of acoustic spaces,” Acta Acustica united with Acustica, special issue on Virtual Acoustics, vol. 94, No. 6, pp. 891-906, Nov./Dec. 2008.
[J13] K. Kowalczyk and M. van Walstijn, “Modeling frequency-dependent boundaries as digital impedance filters in FDTD and K-DWM room acoustics simulations,” J. Audio Engineering Society, vol. 56, No. 7/8, pp. 569-583, Jul./Aug. 2008.

Books:
[B1] K. Kowalczyk, “Boundary and medium modelling using compact finite difference schemes in simulations of room acoustics for audio and architectural design applications,”, Verlag Dr. Hut, München, Germany, 2011. (ISBN: 978-3-8439-0273-1)

Patents:
[P1] E.A.P. Habets, O. Thiergart, K. Kowalczyk, “System, apparatus and method for consistent scene reproduction based on informed spatial filtering”, Patent US 9936323 B2 (granted in USA on 03.04.2018), Patent 6466968 (granted in Japan on 18.01.2019), Patent CN 106664501 B (granted in China on 15.02.2019)
[P2] E.A.P. Habets, O. Thiergart, and K. Kowalczyk, “System, apparatus and method for consistent scene reproduction based on adaptive functions”, Patent US 10015613 B2 (granted in USA on 03.07.2018), Patent RU 2663343 C2 (granted in Russia on 03.08.2018), Patent 6466969 (granted in Japan on 18.01.2019)

Conference papers:
[C1] S. Braun, K. Kowalczyk, and E.A.P. Habets, “ Residual noise control using a parametric multichannel Wiener filter,” Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Process. (ICASSP), pp. 360-364, Brisbane, Australia, Apr. 2015.
[C2] O. Thiergart, K. Kowalczyk, and E.A.P. Habets, “An acoustical zoom based on informed spatial filtering,” Proc. Int. Workshop on Acoustic Sign. Enhancement (IWAENC), Antibes – Juan les Pins, France, Sep. 2014. Coauthor of the paper winning the Best Student Paper Award
[C3] K. Kowalczyk, A. Craciun, C. Dachmann, and E.A.P. Habets, “Spatial perception of virtual X-Y recordings,” Proc. Int. Workshop on Acoustic Sign. Enhancement (IWAENC), Antibes – Juan les Pins, France, Sep. 2014.
[C4] J. Sheaffer, M. van Walstijn, B. Rafaely, and K. Kowalczyk, “A spherical array approach for simulation of binaural impulse responses using the finite difference time domain method,” Proc. Forum Acusticum, Krakow, Poland, Sep. 2014.
[C5] S. Chakrabarty, K. Kowalczyk, M. Taseska, and E.A.P. Habets, “Extended Kalmann filter with probabilistic data association for multiple non-concurrent speaker localization in reverberant environments,” Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Process. (ICASSP), pp.7445-7449, Florence, Italy, May 2014.
[C6] P. Götz, A. Silzle, K. Kowalczyk, and E.A.P. Habets, “Diffuseness-based mixing time prediction using a spherical microphone array,” Int. Conf. Spatial Audio (ICSA), Erlangen, Germany, Feb. 2014.
[C7] K. Kowalczyk, O. Thiergart, A. Craciun, E.A.P. Habets, “Sound acquisition in noisy and reverberant environments using virtual microphones,” Proc. IEEE Workshop on Applications of Sign. Process. to Audio and Acoustics (WASPAA), New Paltz, NY, Oct. 2013.
[C8] K. Kowalczyk, A. Craciun, E.A.P. Habets, “Generating virtual microphone signals in noisy environments,” Proc. European Signal Process. Conf. (EUSIPCO), Marrakech, Morocco, Sep. 2013.
[C9] D. Markovic, C. Hofmann, F. Antonacci, K. Kowalczyk, A. Sarti, and W. Kellermann, “Reflection coefficient estimation by pseudospectrum matching,” Proc. Int. Workshop on Acoustic Sign. Enhancement (IWAENC), pp. 181-184, Aachen Germany, Sep. 2012.
[C10] P. Annibale, F. Antonacci, P. Bestagini, A. Brutti, A. Canclini, L. Cristoforetti, E. Habets, J. Filos, W. Kellermann, K. Kowalczyk, A. Lombard, E. Mabande, D. Markovic, P. Naylor, M. Omologo, R. Rabenstein, A. Sarti, P. Svaizer and M. Thomas, “The SCENIC project: space-time audio processing for environment-aware acoustic sensing and rendering,” Proc. 131st Audio Eng. Soc. Conv., New York, NY, Oct. 2011.
[C11] E. Mabande, H. Sun, K. Kowalczyk, and W. Kellermann, “Comparison of subspace-based and steered beamformer-based reflection localization methods,” Proc. European Signal Process. Conf. (EUSIPCO), Barcelona, Spain, Aug. 2011.
[C12] M. van Walstijn and K. Kowalczyk, “Formulation and analysis of frequency-dependent boundaries in finite-difference simulation with compact explicit schemes,” Proc. Forum Acusticum, Aalborg, Denmark, Jun/Jul. 2011.
[C13] E. Mabande, H. Sun, K. Kowalczyk, and W. Kellermann, “On 2D localization of reflectors using robust beamforming techniques,” Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Process. (ICASSP), pp.153-156, Prag, Czech Republic, May 2011.
[C14] H. Sun, E. Mabande, K. Kowalczyk, and W. Kellermann, “Joint DOA and TDOA estimation for 3D localization of reflective surfaces using eigenbeam MVDR and spherical microphone arrays,” Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Process. (ICASSP), pp.113-116, Prag, Czech Republic, May 2011.
[C15] K. Kowalczyk and M. van Walstijn, “Finite difference time domain modeling of phase grating diffusion,” Proc. IEEE Int. Symp. on Communications, Control and Signal Process. (ISCCSP), pp.1-4, Limassol, Cyprus, Mar. 2010.
[C16] K. Kowalczyk and M. van Walstijn, “A comparison of nonstaggered compact FDTD schemes for the 3D wave equation,” Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Process. (ICASSP), pp.197-200, Dallas, TX, Mar. 2010.
[C17] M. van Walstijn and K. Kowalczyk, “On the numerical solution of the 2D wave equation with compact FDTD schemes,” Int. Conf. on Digital Audio Effects (DAFx), pp. 205-212, Espoo, Finland, Sep. 2008.
[C18] K. Kowalczyk and M. van Walstijn, “Modeling frequency-dependent boundaries as digital impedance filters in FDTD and K-DWM room acoustics simulations,” 124th Convention of the Audio Eng. Soc., Amsterdam, The Netherlands, May 2008. Winner of the AES Student Technical Papers Award
[C19] K. Kowalczyk and M. van Walstijn, “Virtual room acoustics using finite difference methods. How to model and analyze frequency-dependent boundaries?,” Proc. IEEE Int. Symp. on Communications, Control and Signal Process. (ISCCSP), pp.1504-1509, St. Julians, Malta, Mar. 2008
[C20] K. Kowalczyk and M. van Walstijn, “Formulation of a locally reacting wall in finite difference modeling of acoustic spaces,” Int. Symp. on Room Acoustics (ISRA), Seville, Spain, Sep. 2007.
[C21] K. Kowalczyk and M. van Walstijn, “On-line simulation of 2D resonators with reduced dispersion error using compact implicit finite difference schemes,” Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Process. (ICASSP), pp.285-288, Honolulu, Hawaii, Apr. 2007. Finalist of the IEEE ICASSP Best Student Paper Contest

Published abstracts, demos, show & tell contributions:
[A1] W. Kellermann, E. Mabande, H. Sun, and K. Kowalczyk, “Precise and efficient localization of room reflections using compact microphone arrays,” J. Acoustical Society of America (JASA), vol. 131, pp. 3283, Apr. 2012.
[A2] P. Annibale, F. Antonacci, P. Bestagini, A. Brutti, A. Canclini, L. Cristoforetti, E. Habets, W. Kellermann, K. Kowalczyk, A. Lombard, E. Mabande, D. Markovic, P. Naylor, M. Omologo, R. Rabenstein, A. Sarti, P. Svaizer and M. Thomas, “The SCENIC project: environment-aware acoustic sensing and rendering,” Procedia in Computer Science, vol. 7, pp. 150-152, Oct. 2011.