Leveraging frequency analysis for deep fake image recognition J Frank, T Eisenhofer, L Schönherr, A Fischer, D Kolossa, T Holz International conference on machine learning, 3247-3258, 2020 | 478 | 2020 |
Adversarial attacks against automatic speech recognition systems via psychoacoustic hiding L Schönherr, K Kohls, S Zeiler, T Holz, D Kolossa arXiv preprint arXiv:1808.05665, 2018 | 345 | 2018 |
Explainable authorship verification in social media via attention-based similarity learning B Boenninghoff, S Hessler, D Kolossa, RM Nickel 2019 IEEE international conference on big data (Big Data), 36-45, 2019 | 79 | 2019 |
Learning dynamic stream weights for coupled-HMM-based audio-visual speech recognition AH Abdelaziz, S Zeiler, D Kolossa IEEE/ACM Transactions on Audio, Speech, and Language Processing 23 (5), 863-876, 2015 | 79 | 2015 |
Uncertainty propagation through deep neural networks AH Abdelaziz, S Watanabe, JR Hershey, E Vincent, D Kolossa Interspeech 2015, 2015 | 78 | 2015 |
Nonlinear postprocessing for blind speech separation D Kolossa, R Orglmeister Independent Component Analysis and Blind Signal Separation: Fifth …, 2004 | 76 | 2004 |
Robust speech recognition of uncertain or missing data: theory and applications D Kolossa, R Haeb-Umbach Springer Science & Business Media, 2011 | 73 | 2011 |
Imperio: Robust over-the-air adversarial examples for automatic speech recognition systems L Schönherr, T Eisenhofer, S Zeiler, T Holz, D Kolossa Proceedings of the 36th Annual Computer Security Applications Conference …, 2020 | 72 | 2020 |
Separation and robust recognition of noisy, convolutive speech mixtures using time-frequency masking and missing data techniques D Kolossa, A Klimas, R Orglmeister IEEE Workshop on Applications of Signal Processing to Audio and Acoustics …, 2005 | 72 | 2005 |
Similarity learning for authorship verification in social media B Boenninghoff, RM Nickel, S Zeiler, D Kolossa ICASSP 2019-2019 IEEE international conference on acoustics, speech and …, 2019 | 57 | 2019 |
Unacceptable, where is my privacy? exploring accidental triggers of smart speakers L Schönherr, M Golla, T Eisenhofer, J Wiele, D Kolossa, T Holz arXiv preprint arXiv:2008.00508, 2020 | 53 | 2020 |
Variational Bayesian inference for multichannel dereverberation and noise reduction D Schmid, G Enzner, S Malik, D Kolossa, R Martin IEEE/ACM transactions on audio, speech, and language processing 22 (8), 1320 …, 2014 | 51 | 2014 |
Independent component analysis and time-frequency masking for speech recognition in multitalker conditions D Kolossa, R Fernandez Astudillo, E Hoffmann, R Orglmeister EURASIP Journal on Audio, Speech, and Music Processing 2010, 1-13, 2010 | 50* | 2010 |
Dynamic Stream Weighting for Turbo-Decoding-Based Audiovisual ASR. S Gergen, S Zeiler, AH Abdelaziz, RM Nickel, D Kolossa INTERSPEECH, 2135-2139, 2016 | 46 | 2016 |
Audiovisual speech recognition with missing or unreliable data. D Kolossa, S Zeiler, A Vorwerk, R Orglmeister AVSP, 117-122, 2009 | 45 | 2009 |
Improving audio-visual speech recognition using deep neural networks with dynamic stream reliability estimates H Meutzner, N Ma, R Nickel, C Schymura, D Kolossa 2017 IEEE international conference on acoustics, speech and signal …, 2017 | 39 | 2017 |
An introduction to binaural processing A Kohlrausch, J Braasch, D Kolossa, J Blauert The technology of binaural listening, 1-32, 2013 | 39 | 2013 |
Speaker localization in reverberant rooms based on direct path dominance test statistics B Rafaely, D Kolossa 2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017 | 36 | 2017 |
Dompteur: Taming audio adversarial examples T Eisenhofer, L Schönherr, J Frank, L Speckemeier, D Kolossa, T Holz 30th USENIX Security Symposium (USENIX Security 21), 2309-2326, 2021 | 35 | 2021 |
Uncertain LDA: Including observation uncertainties in discriminative transforms R Saeidi, RF Astudillo, D Kolossa IEEE transactions on pattern analysis and machine intelligence 38 (7), 1479-1488, 2015 | 35 | 2015 |