Mitarbeiter/innen
Prof. Dr.-Ing. Dorothea Kolossa
Book Chapters
Martin, R., Kolossa, D. (2012). “Voice activity detection, noise estimation, and adaptive filters for acoustic signal enhancement”, in: T. Virtanen, R. Singh, B. Raj (eds.): “Techniques for Noise Robustness in Automatic Speech Recognition”, John Wiley & Sons, September 2012.
Fernandez Astudillo, R., Kolossa, D. (2011). “Uncertainty Propagation”, in: Kolossa, D., Haeb-Umbach, R. (eds.): „Robust Speech Recognition of Uncertain or Missing Data - Theory and Applications“, Springer Verlag, pp. 35-64, July 2011.
Hoffmann, E., Kolossa, D., Orglmeister, R. (2011). “Recognition of Multiple Speech Sources using ICA”, in: Kolossa, D., Haeb-Umbach, R. (eds.): „Robust Speech Recognition of Uncertain or Missing Data - Theory and Applications“, Springer Verlag, pp. 319-344, July 2011.
Vorwerk, A., Zeiler, S., Kolossa, D., Fernandez Astudillo, R., Lerch, D. (2011). “Use of Missing and Unreliable Data for Audiovisual Speech Recognition”, in: Kolossa, D., Haeb-Umbach, R. (eds.): „Robust Speech Recognition of Uncertain or Missing Data - Theory and Applications“, Springer Verlag, pp. 345-375, July 2011.
Edited Book
Kolossa, D., Haeb-Umbach, R. (2011) (eds.): „Robust Speech Recognition of Uncertain or Missing Data - Theory and Applications“, Springer Verlag, 380 pages, July 2011.
Journal Articles
Fernandez Astudillo, R., Kolossa, D., Abad, A., Zeiler, S., Saeidi, R., Mowlaee, P., da Silva Neto, J. P., Martin, R. (2012). “Integration of Beamforming and Uncertainty-of-Observation Techniques for Robust ASR in Multi-Source Environments”, Computer Speech and Language, Special Issue on Multisource Environments, to appear 2012.
Hoffmann, E., Kolossa, D., Köhler, B.-U., Orglmeister, R. (2012). “Using Information Theoretic Distance Measures for Solving the Permutation Problem of Blind Source Separation of Speech Signals” , EURASIP Journal on Audio, Speech, and Music Processing, vol. 2012:14, April 2012.
Fernandez Astudillo, R., Kolossa D., Philipp Mandelartz, P., Orglmeister, R. (2010). "An Uncertainty Propagation Approach to Robust ASR using the ETSI Advanced Front-End", IEEE Journal of Selected Topics in Signal Processing, Special issue on Natural Interaction with Intelligent Environments, vol. 4, pp. 824 – 833, October 2010.
Kohl, F., Wübbeler, G., Kolossa, D., Bär, M., Orglmeister R., Elster, C. (2010). "Shifted factor analysis for the separation of evoked dependent MEG signals”, Phys. Med. Biol., vol. 55, pp. 4219–4230, 2010.
Kolossa, D., Fernandez Astudillo, R., Hoffmann, E., Orglmeister, R. (2010). "Independent Component Analysis and Time-Frequency Masking for Multi-Speaker-Recognition“, EURASIP Journal on Audio, Speech, and Music Processing. vol. 2010, Article ID 651420, 13 pages, 2010.
Peer-Reviewed Conferences
Kolossa, D., Nickel, R., Zeiler, S., Martin, R. (2012). “Inventory-Based Audio-Visual Speech Enhancement”, Proc. Interspeech, Portland, Oregon, USA, September 9-13, 2012.
Jacobi, R. C., Hennig, A., Kolossa, D. (2012). „Simulation Methods for Inductively Coupled Sensor Systems in Varying Environments“, Proc. PRIME, Aachen, Germany, June 12-15, 2012.
Abdelaziz, A. H., Kolossa, D. (2012). "Decoding of Uncertain Features Using the Posterior Distribution of the Clean Data for Robust Speech Recognition", International Speech Communication Association, (2012).
Abdelaziz, A. H., Zeiler, S., Kolossa, D. (2012). "Audio-Visual Speech Recognition for Uncertain Acoustical Observations", ITG Fachtagung Sprachkommunikation, (2012).
Schmid, D., Thüne, P., Kolossa, D., Enzner, G. (2012). "Dereverberation Preprocessing and Training Data Adjustments for Robust Speech Recognition in Reverberant Environments," in Proc. ITG Conference Speech Communication, Braunschweig, Germany, Sep. 2012.
Nickel, R., Astudillo, R., Kolossa, D., Zeiler, S., Martin, R. (2012). "Inventory-Style Speech Enhancement with Uncertainty-of- Observation Techniques",
ICASSP, pp. 4645-4648, Kyoto, Japan, March 2012.
Kolossa, D. (2011). “High-Level Processing of Binaural Features”, Proc. Forum Acusticum, Aalborg, Denmark, June 27-July 1, 2011.
Kolossa, D., Fernandez Astudillo, R., Abad, A., Zeiler, S., Saeidi, R., Mowlaee, P., da Silva Neto, J.P., Martin, R. (2011). “CHiME Challenge: Approaches to Robustness using Beamforming and Uncertainty-of-Observation Techniques”, to appear in Proc. CHiME Workshop on Machine Listening in Multisource Environments, Florence, Italy, Sept.1, 2011.
Kolossa, D., Astudillo, R. F., Abad, A., Zeiler, S., Saeidi, R., Mowlaee, da Silva Neto, J. P., Martin, R. (2011). “CHIME Challenge: Approaches to Robustness using Beamforming and Uncertainty-of-Observation Techniques”, in Proc. CHiME 2011 - to appear in Workshop on Machine Listening in Multisource Environments, Interspeech 2011 satellite event.
Kolossa, D., Fernandez Astudillo, R., Zeiler, S. , Vorwerk, A., Lerch, D., Chong, J., Orglmeister, R. (2010). “Missing Feature Audiovisual Speech Recognition under Real-Time Constraints”, ITG Fachtagung Sprachkommunikation, paper 22, 4 pages, Bochum, Germany, October 6-8, 2010.
Kolossa, D., Chong, J., Zeiler, S., Keutzer, K. (2010). “Efficient Manycore CHMM Speech Recognition for Audiovisual and Multistream Data”, Proc. Interspeech 2010, pp. 2698 – 2701, Makuhari, Japan, September 26-30, 2010.
Kohl, F. , Wübbeler, G., Kolossa, D., Elster, C., Bär, M., Orglmeister, R.(2010). "Noise adjusted PCA for finding the subspace of evoked dependent signals from MEG data”, Latent Variable Analysis and Signal Separation (LVA 2010), Lecture Notes in Computer Science, vol. 6365, pp. 442-449, September 2010.
Kolossa, D., Zeiler, S., Vorwerk, A., Orglmeister, R.(2009). "Audiovisual Speech Recognition with Missing or Unreliable Data", Audiovisual Speech Processing Workshop (AVSP 2009), Brighton, UK, September 10-13, 2009.
Fernandez Astudillo, R., Kolossa, D., Orglmeister, R. (2009). "Accounting for the Uncertainty of Speech Estimates in the Complex Domain for Minimum Mean Square Error Speech Enhancement", Interspeech 2009, Brighton, UK, September 2009.
Jeub, M., Kolossa, D., Fernandez Astudillo, R., Orglmeister, R. (2009). "Performance Analysis of Wavelet-based Voice Activity Detection", invited paper, Proc. DAGA2009, pp. 407-408, Rotterdam, March 2009.
Kohl, F., Wübbeler, G., Kolossa, D., Elster, C., Bär, M., Orglmeister, R. (2009). "Non-Independent BSS: A Model for Evoked MEG Signals with Controllable Dependencies" in: Proceedings of the ICA 2009, pp. 443-450, Paraty, Brazil, March 15-18, 2009.
Hoffmann, E., Kolossa, D., Orglmeister, R. (2009). "Time Frequency Masking Strategy for Blind Source Separation of Acoustic Signals Based on Optimally-Modified LOG-Spectral Amplitude Estimator" in: Proceedings of the ICA 2009, pp. 581-588, Paraty, Brazil, March 15-18, 2009.
Kohl, F., Wübbeler, G., Kolossa, D., Orglmeister, R. , Elster, C., Bär, M. (2008). "Performance of ICA for MEG data generated from subspaces with dependent sources", Proc. European Biomedical Engineering Congress (EMBEC), Antwerpen, Nov. 2008.
Kolossa, D., Hoffmann, E., Orglmeister, R. (2008). "ICA-Based Bayesian Time-Frequency Masking", invited paper, ITG Fachtagung Sprachkommunikation, Aachen, October 2008.
Fernandez Astudillo, R., Kolossa, D., Orglmeister, R. (2008). "Uncertainty Propagation for Speech Recognition using RASTA Features in Highly Nonstationary Noisy Environments", ITG Fachtagung Sprachkommunikation, Aachen, October 2008.
Kohl, F., Wübbeler, G., Sander, T., Trahms, L., Kolossa, D. , Orglmeister, R., Elster, C. and Bär, M. (2008). " Performance of ICA for Dependent Sources using Synthetic Stimulus Evoked MEG Data", invited paper, Workshop Biosignalverarbeitung, pp. 32-35, Potsdam, July 2008.
Kolossa, D., Araki, S. , Delcroix, M., Nakatani, T., Orglmeister, R., Makino, S. (2008). „Missing Feature Speech Recognition in a Meeting Situation with Maximum SNR Beamforming”, invited paper, Proc. ISCAS, pp. 3218-3221, Seattle, WA, May 2008.
Hoffmann, E., Kolossa, D., Orglmeister, R. (2007). „A Soft Masking Strategy based on Multichannel Speech Probability Estimation for Source Separation and Robust Speech Recognition”, Proc. IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA 2007), pp. 118-121, New Paltz, NY.
Hoffmann, E., Kolossa, D., Orglmeister, R. (2007). “A Batch Algorithm for Blind Source Separation of Acoustic Signals Using ICA and Time-Frequency Masking”, Proc. ICA 2007, pp. 480-487, Springer Verlag, Berlin.
Fernandez Astudillo, R. , Kolossa, D. , Orglmeister, R. (2007). “Propagation of Statistical Information Through Non-Linear Feature Extractions For Robust Speech Recognition”, Proc. MaxEnt2007, pp. 245-252, 27th Int. Workshop on Bayesian Inference and Maximum Entropy Methods in Science and Engineering, Saratoga Springs, July 2007.
Kolossa, D., Fernandez Astudillo, R., Orglmeister, R. (2007). “Spracherkennung im Automobil durch Verwendung von Missing Feature Techniken“, invited paper, Proc. DAGA 2007, pp. 301-302.
Kolossa, D., Sawada, H., Fernandez Astudillo, R., Orglmeister, R., Makino, S. (2006). „Recognition of convolutive speech mixtures by missing feature techniques for ICA“, invited paper, in: Proc. 40th Asilomar Conference on Signals, Systems and Computers, pp. 1397-1401, October 29 - November 1, Pacific Grove, USA, 2006.
Maraboina, S., Kolossa, D., Bora, P., Orglmeister, R. (2006). „Multi-Speaker Voice Activity Detection using ICA and Beampattern Analysis“, in: Proc. Eusipco 2006, September 4-8, Florence, Italy.
Kolossa, D., Klimas, A., Baumann, W., Orglmeister, R. (2006). „Robuste Erkennung gestörter Sprache im Automobil durch MMSE-Störgeräuschunterdrückung und Missing-Data Spracherkennung“, invited paper, in: Proc. Daga 2006, March 20 - 23, Braunschweig, Germany.
Kolossa, D., Klimas, A., Orglmeister, R.(2005). „Separation and Robust Recognition of Noisy, Convolutive Speech Mixtures using Time-Frequency Masking and Missing Data Techniques“, in: Proceedings of the WASPAA 2005, pp. 82-85, New Paltz, NY, USA, October 16-19, 2005.
Kolossa, D., Orglmeister, R.(2004). „Nonlinear Postprocessing for Blind Speech Separation“, in: Proceedings of the ICA 2004, pp. 832–839, Granada, Spain, September 22-24, 2004.
Baumann, W., Kolossa, D., Orglmeister, R. (2003). „Realtime Implementation of a Beamforming Based Convolutive Source Separation Algorithm“, Tagung der Deutschen Gesellschaft für Akustik, DAGA 2003, Aachen, March 18-20, 2003.
Baumann, W., Kolossa, D., Orglmeister, R. (2003).„Beamforming-Based Convolutive Source Separation“, in: Proceedings ICASSP 2003, pp. 357-360, Hong Kong, China, April 6-10, 2003.
Baumann, W., Kolossa, D., Orglmeister, R. (2003). „Maximum Likelihood Permutation Correction for Convolutive Source Separation“, in: Proceedings of the ICA 2003, pp. 373-378, Nara, Japan, April 1-4, 2003.
Kolossa, D., Huo, Q. (2002). „Using Time-Stretched Pulses for Accurate Splitting of Speech Utterances Played Back in Noisy Reverberant Environments“, in: Proceedings of the International Conference on Spoken Language Processing (ICSLP), pp.1541-1544, September 16-20 2002, Denver, CO, USA.
Baumann, W. , Köhler, B.-U., Kolossa, D., Orglmeister, R. (2001). „Real Time Separation of Convolutive Mixtures“, in: Proceedings of the ICA2001, pp.65-69, San Diego, California, USA.
Kolossa, D., Köhler, B.-U., Conrath, M., Orglmeister, R. (2001). „Optimal Permutation Correction by Multiobjective Genetic Algorithms”, in: Proceedings of the ICA2001, pp. 373-378, San Diego, California, USA.
Kolossa, D., Grübel, G. (2000). „Evolutionary Computation and Nonlinear Programming in Multi-Model Robust Control Design“, In: Lecture Notes on Computer Science vol. 1803, pp. 147-157, Stefano Cagnoni et al. (Eds.), Springer Verlag, Berlin, Heidelberg, New York, 2000.
Theses
Kolossa, D. (2008). "Independent Component Analysis for Environmentally Robust Speech Recognition”, PhD Thesis, TU Berlin, 2008.
Kolossa, D. (1998). "Entwurf & Aufbau eines Mikrocontrollersystems mit dem PowerPC MPC821 von Motorola“, Institute for Computer Architecture and Circuit Design, Diploma Thesis TU Berlin, 1998.
Patent
European Patent Number DEA102010006956: Volmer, A., Orglmeister, R., Hoffmann, E., Kolossa, D. (2012). „Verfahren und Meßgerät zum Messen der Sauerstoffsättigung im Blut“, March 2012.
German Patent Number 10312065.3 : Baumann, W., Kolossa, D., Orglmeister, R. (2004). „Frequenzvariantes Beamforming zur Sprechertrennung im KFZ“, March 2004.
Invited Talks
Honda Research Institute Europe, Offenbach: “Uncertainty-of-Observation Techniques for Robust and Multimodal Pattern Recognition”, July 2012.
NTT Communications Science Labs, Kyoto: "Environmentally Robust Audiovisual Speech Recognition using Uncertain and Missing Data", Oct. 2010.
International Computer Science Institute (ICSI), Berkeley: “Robust Realtime-Capable Audiovisual Speech Recognition“, March 2010.
UC Berkeley, Parlab: "Audiovisual Speech Recognition with Missing or Unreliable Data", Nov. 2009.
Microsoft Research, Redmond Lab: "Application of Missing Feature Theory to Maximum SNR Beamforming and ICA", May 2008.
NTT Communications Science Labs, Kyoto: "Application of Missing Feature Theory to Maximum SNR Beamforming", Aug. 2007.
ZIB Postdam: "Trennung von überlagerten Sprechersignalen durch Independent Component Analysis", Nov. 2006.
NTT Communications Science Labs, Kyoto: "Robust Speech Recognition using Missing Data Techniques", Mar. 2006.
Acoustics Group, Univ. Oldenburg: "Zeit-Frequenzmaskierung und Missing-Feature Erkennung für gestörte Sprachsignale", Feb. 2006.
Dept. Computer Science, University of Hongkong: "Principle and Applications of Independent Component Analysis", Aug. 2005.
Lecture Notes
Kolossa, D. (2011). „Einführung in die automatische Spracherkennung“, TU Berlin, 155 pages, 2010.
