Franz Pernkopf

2015
Zöhrer, M., Peharz R., & Pernkopf F. (2015).  Representation Learning for Single-Channel Source Separation and Bandwidth Extension. IEEE Transactions on Audio, Speech, and Language Processing. 23(12), 2398--3409. Download: Master2014-TASLP_July15.pdf (5.98 MB)
Zöhrer, M., & Pernkopf F. (2015).  Representation Models in Single Channel Source Separation. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP).  Download: SCSS_Re1.pdf (1.7 MB)
Ratajczak, M., Tschiatschek S., & Pernkopf F. (2015).  Structured Regularizer for Neural Higher- Order Sequence Models. European Conference on Machine Learning (ECML).  Download: ecml2015Martin.pdf (437.5 KB)
2014
Ratajczak, M., Tschiatschek S., & Pernkopf F. (2014).  Context-Speci c Deep Conditional Random Fields for Structured Prediction. International Conference on Machine Learning (ICML), Workshop on Learning Tractable Probabilistic Models.  Download: ltpm2014_submission_4_accepted.pdf (314.24 KB)
Zöhrer, M., & Pernkopf F. (2014).  General Stochastic Networks for Classifi cation. Neural Information Processing Systems (NIPS).
Tschiatschek, S., Paul K., & Pernkopf F. (2014).  Integer Bayesian Networks. European Conference on Machine Learning (ECML).  Download: main_1.pdf (407.69 KB)
Pernkopf, F., Peharz R., & Tschiatschek S. (2014).  Introduction to Probabilistic Graphical Models. Academic Press Library in Signal Processing, Vol. 1, Ch. 18. 989-1064. Download: PGM.pdf (825.41 KB)
2013
Mowlaee, P., Morales-Cordovilla J. A., Pernkopf F., Pessentheiner H., Hagmüller M., & Kubin G. (2013).  The 2nd ‘CHIME’ Speech Separation and Recognition Challenge: Approaches on Single-channel Speech Separation and Model-driven Speech Enhancement. in Proceeding of the 2nd CHiME Speech Separation and Recognition Challenge, IEEE Int. Conf. Acoustics, Speech, Signal Processing, May. 2013, . 59-64.
Tschiatschek, S., Chacon C. C., & Pernkopf F. (2013).  Bound for Bayesian Network Classifiers with Reduced Precision Parameters. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP). 3357- 3361. Download: main.pdf (97.51 KB)
Leitner, C., & Pernkopf F. (2013).  Generalization of Pre-Image Iterations for Speech Enhancement. International Conference on Acoustics, Speech, and Signal Processing (ICASSP). 7010-7014.
Wohlmayr, M., & Pernkopf F. (2013).  Model-Based Multiple Pitch Tracking Using Factorial HMMs: Model Adaptation and Inference. Audio, Speech, and Language Processing, IEEE Transactions on. 21, 1742-1754. Download: mainFranzCh3_shortRev4.pdf (427.02 KB)