Dr.-Ing. Jalal Taghia

Ruhr-Universität Bochum
Institut für Kommunikationsakustik
Fakultät für Elektrotechnik und Informationstechnik
Raum: ID/2/316
Universitätsstr. 150
D-44780 Bochum

Email: Jalal.Taghia@rub.de
Tel.: +49 234 32 26662

 

Jalal Taghia was born in Ghazvin, Iran. He received the B.Sc. degree in Electrical Engineering from Azad University, Ghazvin, Iran in 2006. He pursued his education in Electrical Engineering and received the M.Sc. degree from Shahid Beheshti University, Tehran, Iran in 2009. He was a research fellow in the EU Marie Curie Initial Training Network AUDIS (“Digital Signal Processing in Audiology”) from 2009 to 2012.

Jalal Taghia obtained the Dr.-Ing. degree from the Institute of Communication Acoustics (IKA), Ruhr-Universität Bochum, Bochum, Germany in 2016. The title of his doctoral dissertation is “Speech Intelligibility Prediction and Single-channel Noise Reduction Based on Information Measures”. Since October 2016 he is a postdoctoral researcher at the Institute of Communication Acoustics (IKA), Ruhr-Universität Bochum. Currently, his main research interests include instrumental assessment of speech intelligibility, single-channel speech enhancement, and information theory for signal processing.

 

Publications

  • Jalal Taghia, D. Kolossa, and R. Martin, “ALE for robots! A single-channel approach to robot self-noise cancellation,” International Workshop on Acoustic Signal Enhancement (IWAENC), Xi’an, Sept. 2016.

  • A. Nelus, S. Gergen, Jalal Taghia, and R. Martin, “Towards opaque audio features for privacy in acoustic sensor networks,” ITG Conference on Speech Communication, Paderborn, Oct. 2016.

  • Jalal Taghia and R. Martin, “A Frequency-domain adaptive line enhancer with step-size control based on mutual information for harmonic noise reduction”, IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 24, no. 6, pp. 1140-1154, June 2016.

  • Jalal Taghia and R. Martin, "A negentropy based adaptive line enhancer for single-channel noise reduction at low SNR conditions”, IEEE international conference on acoustics, speech, and signal processing (ICASSP), Florence, 2014.

  • Jalal Taghia and R. Martin, “Objective intelligibility measures based on mutual information for speech subjected to speech enhancement processing”, IEEE Transactions on Audio, Speech, and Language Processing, vol. 22, no. 1, pp. 6-16, January 2014.

  • Taghia, Jalal, Martin, R., Taghia, Jalil, Leijon, A. (2013). "Dual-Channel Noise Reduction Based on a Mixture of Circular-Symmetric Complex Gaussians on Unit Hypersphere", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Vancouver, 2013.

  • Jalal Taghia, R. Martin, Jalil Taghia and A. Leijon, "Dual-channel noise reduction based on a mixture of circular-symmetric complex Gaussians on unit hypersphere", IEEE international conference on acoustics, speech, and signal processing (ICASSP), Vancouver, 2013.

  • A. Chinaev, R. H. Umbach, Jalal Taghia and R. Martin, "Improved single-channel nonstationary noise tracking by an optimized MAP-based postprocessor", IEEE international conference on acoustics, speech, and signal processing (ICASSP), Vancouver, 2013.

  • Jalal Taghia, R. Martin, Jalil Taghia, A. Leijon, "An investigation on mutual information for the linear predictive system and the extrapolation of speech signals", The 10th ITG Conference on Speech Communication, Braunschweig, Germany, September 2012.

  • Jalal Taghia, R. C. Hendriks, and R. Martin, "On mutual information as a measure of speech intelligibility”, IEEE international conference on acoustics, speech, and signal processing (ICASSP), Kyoto, 2012.

  • Jalal Taghia, Jalil Taghia, N. Mohammadiha, J. Sang, V. Bouse, and R. Martin, "An evaluation of noise power spectral density estimation algorithms in adverse acoustic environments", IEEE Int. Conference on Acoustics, Speech and Signal Processing (ICASSP), Prague, 2011.

  • Jalal  Taghia  and M. H. Savoji, "Audio blind source separation of linear and instantaneous mixtures", the 14th National CSI Computer Conference (CSICC'09), Amirkabir University of Technology, Tehran, 2009.

  • Jalal Taghia, and M. H. Savoji, "Noise separation in analog integrated circuits using empirical mode decomposition", the 16th European Signal Processing Conference (EUSIPCO'08), Lausanne, 2008.

  • Jalal Taghia, and M. H. Savoji, "Blind noise separation in analog integrated circuits by empirical mode decomposition", World Applied Sciences Journal (WASJ), IDOSI publication, volume 5, issue 4, pp. 422-431, 2008.

  • Jalal Taghia, Jalil Taghia, "One-channel audio source separation of convolutive mixtures", Advances in Computer and Information Sciences and Engineering, Springer Netherlands pp. 202-206, 2008.

  • Jalil Taghia, Jalal Taghia, and M. A. Doostari, "Digital image watermarking based on bidimentional empirical mode decomposition", Congress on Image and Signal Processing (CISP'08), China, 2008.

Talks

  • Jalal Taghia and R. Martin, ”Speech intelligibility measures based on mutual information”, Audiological Scientists and Developers, Erlanger Kolloquium, Siemens AG Healthcare Sector, Erlangen, February 2014.

  • Jalal Taghia and R. Martin, "An evaluation of noise power spectral density estimation algorithms in terms of mean estimation error, estimation error variance, and speech leakage", Audiological Scientists and Developers, Erlanger Kolloquium, Erlangen, Germany, 2011.