Room number

IDEG080

Telephone number

• office: +43 316 873 - 4436

Position

Professor

Email

pernkopf@tugraz.at

Research interests

His research interests include machine learning, discriminative learning, graphical models, feature selection, finite mixture models, and image- and speech processing applications.

Franz Pernkopf received his MSc (Dipl. Ing.) degree in Electrical Engineering at Graz University of Technology, Austria, in summer 1999. He earned a PhD degree from the University of Leoben, Austria, in 2002. In 2002 he was awarded the Erwin Schrödinger Fellowship. He was a Research Associate in the Department of Electrical Engineering at the University of Washington, Seattle, from 2004 to 2006. From 2010-2019 he was Associate Professor at the Laboratory of Signal Processing and Speech Communication, Graz University of Technology, Austria. In 2010, he received the young investigator award of the province Styria, Austria. Since 2019, he is Professor for Intelligent Systems at the Signal Processing and Speech Communication Laboratory at Graz University of Technology, Austria.

His research is focused on pattern recognition, machine learning, and computational data analytics with application in various fields ranging from signal and speech processing to medical data analysis and other data modeling problems from industrial applications. He is particularly interested in probabilistic graphical models for reasoning under uncertainty, discriminative and hybrid learning paradigms, deep neural networks, and sequence modeling. Graphical models unite probability and graph theory and allow to efficiently formalize both static and dynamic, as well as linear and nonlinear systems and processes. They provide an approach to deal with two inherent problems throughout applied mathematics and engineering, namely, uncertainty and complexity. His recent interest in deep learning is nourished by the remarkable performance boost in many image,signal and speech processing problems. This is particularly true when having big amounts of data and almost unlimited computing resources available. Here, the research is focused on resource-efficient deep learning methods for constraint computing infrastructure of real-world applications.

CV for download.

---

Research Programs

• Dependable Internet of Things in Adverse Environments
• National Research Network Signal and Information Processing in Science and Engineering

Research Topics

• Acoustic Source Localization and Separation
• Machine Learning
• Probabilistic Graphical Models
• Speech and Speaker Recognition
• Computational Lung Sound Analysis

Research Projects

• SEAMAL Front - Sicher angewandtes maschinelles Lernen
• Resource-Efficient Deep Models for Embedded Systems
• Learning of Bayesian Network Classiers and Sum- Product Networks
• Propabilistc Graphical Models for Signal Analysis
• Probabilistic Graphical Models for Time-Series Signal Mixtures
• Computerunterstützte akustische Diagnostik thorakaler Erkrankungen
• Signal and Information Processing in Science and Engineering - Nonlinear Dynamic and Machine Learning (SISE-NDML-II) FWF S10610-N13
• Discriminative Learning of Graphical Models with Application to Speech and Image Processing
• Discriminative Learning of Bayesian Network Classifiers
• Description and Classification of 3-D Surfaces

Courses

• Signal Processing and Machine Learning 1 and 2
• TI-Bachelorseminar am SPSC
• Computational Intelligence
• Digital Signal Processing Laboratory
• Masterseminar-TI / Toningenieur-Masterarbeiten am SPSC
• Privatissimum
• Privatissimum Old
• Privatissimum 2021/2022
• Automatic Speech Recognition
• Speech Communication Laboratory
• Privatissimum 2019/2020
• Privatissimum 2020/2021
• Privatissimum 2022/2023
• Privatissimum 2023/2024
• Toningenieur-Projekt am SPSC
• Verfassen wissenschaftlicher Arbeiten

Student Projects

• Single-channel source separation for conversational speech in realistic environments
• Machine Learning Based Speech (or Music) Separation(open)
• Acoustic Event Detection and Classification(open)
• Generative Deep Learning for the Creation of 3D Objects(open)
• Radio-Frequency Simultaneous Localization and Mapping using Transformer-based Deep Learning(open)
• Alignment of Laser Measurements for Refractory Modelling
• Ultra-wideband Radar Child Presence Detection Using Deep Learning
• Wear Prediction of Refractory Lining using Neural Networks
• Applying Semi-Supervised Learning to Adventitious Lung Sound Classification
• CNN-based Homophone Disambiguation for conversational speech
• On Optimal Feature Orderings In Bayesian NEtwork Classifiers
• Deep Neural Networks for Multi-Instrument Recognition and Timbre Characterization
• Oxygen Saturation Measurements for Apnea Divers
• Low-Complexity Convolutional Neural Networks for Acoustic Scene Classification
• Audio-Klassifikation der Getriebegeräusche Rasseln un dheulen
• Sound Classification of A Multichannel Auscultation Pad
• Machine Learning for Automatic F0 Contour Discrimination and Labelling
• Monitoring of Dairy Cows with Deep Learning
• Anomaly Detection in Dairy Cows
• Machine Learning for Discharge Prediction in Nuclear Fusion Reactors
• Integration and Deployment of Machine Learning Models
• Vibration Diagnosis in Automotive Applications
• FPGA Implementation of a Neural Network for Radar Interference Mitigation
• Measureing Room Impuse Responses Using an Autonomous Robot
• Generative adversarial networks for time-series tasks
• Automatic Graph Tracking Dynamic Probabilistic Programs via Source Transformations
• Machine Learning Assisted Heat Detection in Dairy Cows
• Automatic Measurement of Room Impulse Responses via Autonomous Robots
• Speech Recognition - A Transfer Learning Approach
• Battery Modeling By Means Of Statistical Models
• Synthesizing Infomap - A Kullback-Leibler Divergence-Based Approach To Community Detection
• Efficient Single-Channel Music Source Separation with Deep Neural Networks
• Extension of Signal Monitoring Applications with Machine Learning
• Keyword spotting using resource-efficient deep learning
• Improving inference runtime for Dirichlet Process Bayesian Neural Networks
• Target Detection in Automotive Radar Signals
• Bayesian Neural Networks for Missing Data Scenarios
• Resource-efficient Neural Networks
• Oxygen Measurements for Apnea Divers
• Requirements Specification of a Systems-Engineering Tool: Example on Effort Estimation using Neural Networks
• Dynamical Compuation Graphs in Universal Probabilistic Programming
• Probabilistic Graphical Models for Signal Analysis and Recognition
• Changepoint Detection in Smartphone Usage
• Channel Selection for Distant Automatic Speech Recognition on the CHiME-5 dataset
• Self-Confident Belief Propagation: An Approach for Iterative Improvement of the Bethe Approximation
• Predicting the Latency of MQTT Brokers Using Deep Learning
• 16 Channel USB 2.0 Sound Card for Digital MEMS Microphones
• Evolutionary Neural Network Poker Agents and the Effects of Opponent Modeling
• Binarized Neural Networks under the Influence of Label Noise: A Performance Evaluation
• sound classification of YouTube videos with Recurrent Neural Networks
• Tracking of fundamental frequencies in pathologic voice(open)
• Cloud Storage Performance Analysis
• Acoustic Event Detection of General Sounds
• Real-Time Automatic Recognition of Spoken Digits on an Embedded System using Deep Recurrent Neural Networks
• Segmental Conditional Random Fields for Phone Recognition
• Message Scheduling in Loopy BeliefPropagation
• Hybrid Generative-Discriminative Training of Gaussian Mixture Models
• Vibration Analysis and Classification(open)
• Modelling of gas sensor responses using deep models(open)
• Residual Belief Propagation and Beyond
• Hybrid Generative-Discriminative Training of Gaussian Mixture Models
• Keyword Spotting for Emergency
• Artificial Pitch for Electro-Larynx Speech(open)
• Relation of Loopy Sum-Product Algorithm and Rank-1 Tensor Approximation
• Acoustic Detection of General Audio Events
• Vibroakustisches Monitoring in Smart Homes
• Reduced Precision Bayesian Network Classifiers
• Glottal Movement Extraction from High-Speed Videos
• Maximum Margin Hidden Markov Models
• Structure Learning of Bayesian Networks Using Latent Variables(open)
• Model Self-Adaptation during Operation Using Mixture Data
• Multi-Channel Speech Enhancement
• Effect of Quantization in Bayesian Network Classifiers
• Battery modeling using statistical models
• Dictionary-based Speech Enhancement using an Air-Bone-Microphone
• Charakterisierung der Schädigung von Hüfttotalendoprothesen mittels Körperschall(open)
• Pattern Recognition of Hydroacoustic Signals
• Database for multi-pitch tracking
• Single Channel Source Separation using Dictionary Design Methods for Sparse Coders
• Wavelet Based Speaker Change Detection in Single Channel Speech Data
• Vibration Analysis for Adjustment and Monitoring of a Waste Shredder
• Text-to-Speech Engine with Austrian German Corpus
• Unsupervised Speaker Segmentation in One-Channel Speech Data
• A Flexible Sender-Based Packet Loss Recovery Method

PhD Theses

• A Holistic Approach to Multi-channel Lung Sound Classification
• Sum-Product Networks for Complex Modelling Scenarios
• Deep Learning and Structured Prediction
• Deep Learning for Resource-Constrained Radar Systems
• Speech Enhancement Using Deep Neural Beamformers
• Kernel PCA and Pre-Image Iterations for Speech Enhancemen
• Machine Learning Models for Failure Prediction in RF Cavities for Accelerators
• Machine Learning for Acoustic Scene and Respiratory Sound Classification
• Maximum Margin Bayesian Networks
• Understanding the Behavior of Belief Propagation
• Probabilistic Methods for Resource Efficiency in Machine Learning
• Probabilistic Model-Based Multiple Pitch Tracking of Speech
• Source-Filter Model Based Single Channel Speech Separation

Publications

• Journal article Fragner S., Pfeifenberger L., Hagmüller M. & Pernkopf F. (2024) Dataset of directional room impulse responses for realistic speech data. in Data in Brief , 53. [more info] [doi]
• Conference paper Mutsam N., Fuchs A., Ziegler F. & Pernkopf F. (2024) Data-Scarce Condition Modeling Requires Model-Based Prior Regularization. in 48th IEEE International Conference on Acoustics, Speech, and Signal Processing. [more info]
• Journal article Fragner S., Pfeifenberger L., Hagmüller M. & Pernkopf F. (2024) Dataset of Room Impulse Responses for Realistic Speech Data. in Data in Brief . [more info]
• Journal article Roth W., Schindler G., Klein B., Peharz R., Tschiatschek S., Fröning H., Pernkopf F. & Ghaharamani Z. (2024) Resource-Efficient Neural Networks for Embedded Systems. in Journal of Machine Learning Research. [more info]
• Conference paper Möderl J., Posch S., Pernkopf F. & Witrisal K. (2024) UWBCarGraz Dataset for Car Occupancy Detection using Ultra-Wideband Radar.. [more info] [doi]
• Conference paper Fuchs A., Knoll C., Leitinger E. & Pernkopf F. (2023) Self-attention for enhanced OAMP Detection in MIMO Systems. in 48th IEEE International Conference on Acoustics, Speech, and Signal Processing. [more info] [doi]
• Conference paper Bradl H., Huber M. & Pernkopf F. (2023) Transfer Learning Using Musical/Non-Musical Mixtures for Multi-Instrument Recognition. in 15th ITG Conference on Speech Communication. [more info]
• Conference paper Maier L., Fuchs A. & Pernkopf F. (2023) Distribution Mismatch Correction for Acoustic Scene Classification. in 15th ITG Conference on Speech Communication. [more info]
• Conference paper Oswald C., Toth M., Meissner P. & Pernkopf F. (2023) Angle-Equivariant Convolutional Neural Networks for Interference Mitigation in Automotive Radar. in 20th European Radar Conference (pp. 135-138). [more info] [doi]
• Conference paper Oswald C., Toth M., Meissner P. & Pernkopf F. (2023) End-to-End Training of Neural Networks for Automotive Radar Interference Mitigation. in 2023 IEEE International Radar Conference. [more info] [doi]
• Conference paper Knoll C. & Pernkopf F. (2023) Reliable Belief Propagation: Recent Theoretical and Practical Advances. in 33rd IEEE International Workshop on Machine Learning for Signal Processing. [more info] [doi]
• Data set/Database Möderl J., Posch S., Pernkopf F. & Witrisal K. (2023) UWBCarGraz Dataset.. [more info] [doi]
• Journal article Möderl J., Pernkopf F., Witrisal K. & Leitinger E. (2023) Fast Variational Block-Sparse Bayesian Learning. in IEEE Transactions on Signal Processing. [more info]
• Journal article Möderl J., Pernkopf F., Witrisal K. & Leitinger E. (2023) Variational Inference of Structured Line Spectra Exploiting Group-Sparsity. in IEEE Transactions on Signal Processing. [more info]
• Conference paper Toth C., Lorch L., Knoll C., Krause A., Pernkopf F., Peharz R. & Kügelgen J. (2023) Active Bayesian Causal Inference. in 36th Conference on Neural Information Processing Systems. [more info]
• Conference paper Obermair C., Fuchs A., Felsberger L., Pernkopf F., Apollonio A. & Wollmann D. (2023) Example or Prototype? Learning Concept-Based Explanations in Time Series. in 14th Asian Conference on Machine Learning. [more info]
• Conference paper Möderl J., Leitinger E., Pernkopf F. & Witrisal K. (2023) Variational Message Passing-based Respiratory Motion Estimation and Detection Using Radar Signals. in 48th IEEE International Conference on Acoustics, Speech, and Signal Processing. [more info]
• Journal article Mutsam N., Pernkopf F. & Lammer G. (2022) Digital Optimization of Refractory Maintenance. in Iron & Steel Technology, 2022(July), p. 42-49. [more info]
• Conference paper Schuppler B., Berger E., Kogler X. & Pernkopf F. (2022) Homophone Disambiguation Profits from Durational Information. in 23rd Annual Conference of the International Speech Communication Association (pp. 3198-3202). [more info] [doi]
• Journal article Obermair C., Cartier-Michaud T., Apollonio A., Millar L., Felsberger L., Fischl L., Bovbjerg H., Wollmann D., Wuensch W., Catalan-Lasheras N., Boronat M., Pernkopf F. & Burt G. (2022) Explainable Machine Learning for Breakdown Prediction in High Gradient RF Cavities. in Physical Review Accelerators and Beams, 25(10). [more info] [doi]
• Journal article Pfeifenberger L. & Pernkopf F. (2022) Blind Speech Separation and Dereverberation using Neural Beamforming. in Speech Communication, 140, p. 29-41. [more info] [doi]
• Journal article Nguyen T. & Pernkopf F. (2022) Lung Sound Classification Using Co-Tuning and Stochastic Normalization. in IEEE Transactions on Biomedical Engineering, 69(9), p. 2872-2882. [more info] [doi]
• Journal article Knoll C., Weller A. & Pernkopf F. (2022) Self-Guided Belief Propagation – a Homotopy Continuation Method. in IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, p. 1-18. [more info] [doi]
• Conference paper Hirschmugl M., Rock J., Meissner P. & Pernkopf F. (2022) Fast and Resource-Efficient CNNs for Radar Interference Mitigation on Embedded Hardware. in 19th European Radar Conference (pp. 197-200). [more info] [doi]
• Conference paper Peter D., Roth W. & Pernkopf F. (2022) End-to-end Keyword Spotting using Neural Architecture Search and Quantization. in 47th IEEE International Conference on Acoustics, Speech and Signal Processing (pp. 3423-3427). [more info]
• Conference paper Leisenberger H., Pernkopf F. & Knoll C. (2022) Fixing the Bethe Approximation: How Structural Modifications in a Graph Improve Belief Propagation. in 38th Conference on Uncertainty in Artificial Intelligence (pp. 1085–1095). [more info]
• Conference paper Möderl J., Pernkopf F. & Witrisal K. (2022) Car Occupancy Detection Using Ultra-Wideband Radar. in 18th European Radar Conference (pp. 313-316). [more info] [doi]
• Conference paper Fuchs A., Knoll C. & Pernkopf F. (2021) Wasserstein Distribution Correction for Improved Robustness in Deep Neural Networks.. [more info]
• Conference paper Möderl J., Pernkopf F. & Witrisal K. (2021) Car Occupant Detection Using Ultra-Wideband Radar.. [more info]
• Conference paper Mutsam N., Pernkopf F. & Lammer G. (2021) Digital optimization of refractory maintenance. in Iron and Steel Technology Conference and Exposition (pp. 1657-1666). [more info] [doi]
• Conference paper Mutsam N., Pernkopf F. & Lammer G. (2021) Digital Optimization of Refractory Mainenance.. [more info]
• Conference paper Fuchs A., Rock J., Toth M., Meissner P. & Pernkopf F. (2021) Complex-Valued Convolutional Neural Networks for Enhanced Radar Signal Denoising and Interference Mitigation.. [more info]
• Conference paper Fragner S., Topar T., Giller P., Pfeifenberger L. & Pernkopf F. (2021) Autonomous Robot for Measuring Room Impulse Responses.. [more info]
• Conference paper Pfeifenberger L., Zöhrer M. & Pernkopf F. (2021) Acoustic Echo Cancellation with Cross-Domain Learning.. [more info]
• Conference paper Nguyen T. & Pernkopf F. (2021) Crackle Detection In Lung Sounds Using Transfer Learning And Multi-Input Convolitional Neural Networks.. [more info]
• Conference paper Obermair C., Apollonio A., Charifoulline Z., Maciejewski M., Pernkopf F. & Verweij A. (2021) Machine Learning with a Hybrid Model for Monitoring of the Protection Systems of the LHC.. [more info]
• Conference paper Obermair C., Apollonio A., Carier-Michaud T., Catalan-Lasheras N., Felsberger L., Millar W., Wuensch W. & Pernkopf F. (2021) Machine Learning Models for Breakdown Prediction in RF Cavities for Accelerators. in 2021 International Particle Accelarator Conference. [more info]
• Journal article Aichinger P. & Pernkopf F. (2021) Synthesis and Analysis-by-Synthesis of Modulated Diplophonic Glottal Area Waveforms. in IEEE Transactions on Audio Speech and Language Processing , 29, p. 914-926. [more info] [doi]
• Journal article Rock J., Roth W., Toth M., Meissner P. & Pernkopf F. (2021) Resource-efficient Deep Neural Networks for Automotive Radar Interference Mitigation. in IEEE Journal on Selected Topics in Signal Processing, 15(4), p. 927-940. [more info] [doi]
• Conference paper Fuchs A., Knoll C. & Pernkopf F. (2021) Distribution Mismatch Correction for Improved Robustness in Deep Neural Networks. in Distribution Shifts. [more info]
• Conference paper Leisenberger H., Knoll C., Seeber R. & Pernkopf F. (2021) Convergence Behavior of Belief Propagation: Estimating Regions of Attraction via Lyapunov Functions. in 37th Conference on Uncertainty in Artificial Intelligence (pp. 1863-1873). [more info]
• Conference paper Roth W., Schindler G., Fröning H. & Pernkopf F. (2021) On Resource-Efficient Bayesian Network Classifiers and Deep Neural Networks. in International Conference on Pattern Recognition. [more info]
• Conference paper Peter D., Roth W. & Pernkopf F. (2021) Resource-efficient DNNs for Keyword Spotting using Neural Architecture Search and Quantization. in 25th International Conference on Pattern Recognition. [more info]
• Patent Meissner P., Toth M., Rock J., Pernkopf F. & Messner E. (2020) FMCW RADAR MIT STÖRSIGNALUNTERDRÜCKUNG MITTELS KÜNSTLICHEM NEURONALEN NETZ.. [more info]
• Conference paper Trapp M., Peharz R., Pernkopf F. & Rassmusen C. (2020) Deep Structured Mixtures of Gaussian Processes. in 23rd International Conference on Artificial Intelligence and Statistics (pp. 2251-2261). [more info]
• Preprint Pfeifenberger L., Zöhrer M., Roth W., Schindler G., Fröning H. & Pernkopf F. (2020) Resource-Efficient Speech Mask Estimation for Multi-Channel Speech Enhancement.. [more info]
• Conference paper Schindler G., Roth W., Pernkopf F. & Fröning H. (2020) Parameterized Structured Pruning for Deep Neural Networks. in 6th International Conference on Machine Learning, Optimization, and Data Science (pp. 16-27). [more info] [doi]
• Conference paper Pfeifenberger L. & Pernkopf F. (2020) Nonlinear Residual Echo Suppression using a Recurrent Neural Network. in 21st Annual Conference of the International Speech Communication Association (pp. 3950-3954). [more info] [doi]
• Conference paper Nguyen T. & Pernkopf F. (2020) Lung Sound Classification Using Snapshot Ensemble of Convolutional Neural Networks. in 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society (pp. 760-763). [more info] [doi]
• Conference paper Nguyen T., Kośmider M. & Pernkopf F. (2020) Acoustic Scene Classification for Mismatched Recording Devices Using Heated-Up Softmax and Spectrum Correction. in 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (pp. 126-130). [more info] [doi]
• Conference paper Huber M., Schindler G., Roth W., Fröning H., Schörkhuber C. & Pernkopf F. (2020) Towards Real-Time Single-Channel Singing-Voice Separation with Pruned Multi-Scaled DenseNets. in 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (pp. 806-810). [more info] [doi]
• Conference paper Fuchs A., Priewald R. & Pernkopf F. (2020) Laser-based Hair Crack Detection on Wafers. in 2020 31st Annual SEMI Advanced Semiconductor Manufacturing Conference. [more info] [doi]
• Journal article Messner E., Fediuk M., Swatek P., Scheidl S., Smolle-Jüttner M., Olschewski H. & Pernkopf F. (2020) Multi-channel Lung Sound Classification with Convolutional Recurrent Neural Networks. in Computers in Biology and Medicine, 122. [more info] [doi]
• Journal article Mutsam N. & Pernkopf F. (2020) Tracking of a Gunning Jet Using Particle Filtering in Infrared Image Sequences. in IEEE Transactions on Instrumentation and Measurement, 69(9), p. 6101-6111. [more info] [doi]
• Conference paper Rock J., Roth W., Meissner P. & Pernkopf F. (2020) Quantized Deep Neural Networks for Radar Interference Mitigation. in 2020 European Conference on Machine Learning - ITEM Workshop. [more info]
• Conference paper Roth W. & Pernkopf F. (2020) Differentiable TAN Structure Learning for Bayesian Network Classifiers. in 10th International Conference on Probabilistic Graphical Models. [more info]
• Conference paper Nguyen T. & Pernkopf F. (2020) Lung Sound Classification Using Snapshopt Ensemble of Convolutional Neural Networks. in 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society. [more info]
• Journal article Knoll C. & Pernkopf F. (2020) Belief propagation: accurate marginals or accurate partition function—where is the difference?. in Journal of Statistical Mechanics: Theory and Experiment, 2020(12). [more info] [doi]
• Journal article Roth W. & Pernkopf F. (2020) Bayesian Neural Networks with Weight Sharing Using Dirichlet Processes. in IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(1), p. 246-252. [more info] [doi]
• Conference paper Viertauer A., Mutsam N., Pernkopf F., Gantner A., Grimm G., Lammer G. & Ratz A. (2019) Refractory Lifetime Prognosis for RH-Degassers. in UNITECR. [more info]
• Conference paper Viertauer A., Mutsam N., Pernkopf F., Gantner A., Grimm G., Winkler W., Lammer G. & Ratz A. (2019) Refractory condition monitoring and lifetime prognosis for Rh degasser. in Iron and Steel Technology Conference and Exposition (pp. 1081-1089). [more info] [doi]
• Technical report Roth W., Schindler G., Zöhrer M., Pfeifenberger L., Peharz R., Tschiatschek S., Fröning H., Pernkopf F. & Ghahramani Z. (2019) Resource-Efficient Neural Networks for Embedded Systems.. [more info]
• Conference paper Gabler P., Trapp M., Ge H. & Pernkopf F. (2019) Graph Tracking in Dynamic Probabilistic Programs via Source Transformations.. [more info]
• Conference paper Fuchs A., Priewald R. & Pernkopf F. (2019) Recurrent Dilated DenseNets for a Time-Series Segmentation Task.. [more info]
• Conference paper Rock J., Toth M., Meissner P. & Pernkopf F. (2019) CNNs for Interference Mitigaton and Denoising in Automotive Radar Using Real World Data.. [more info]
• Conference paper Nguyen T., Pernkopf F. & Fuchs A. (2019) Acoustic Scene Classification Using Deep Mixture of Pre-trained Convolutional Neural Networks.. [more info]
• Conference paper Trapp M., Peharz R., Ge H., Pernkopf F. & Ghaharamani Z. (2019) Bayesian Learning of Sum-Product Networks.. [more info]
• Conference paper Roth W., Schindler G., Fröning H. & Pernkopf F. (2019) Training Discrete-Valued Neural Networks with Sign Activations Using Weight Distributions.. [more info]
• Conference paper Nguyen T. & Pernkopf F. (2019) Acoustic Scene Classification with Mismatched Devices Using CliqueNets and Mixup Data Augmentation.. [more info]
• Conference paper Rock J., Toth M., Messner E., Meissner P. & Pernkopf F. (2019) Complex Signal Denoising for Automotive Radar using Convolutional Neural Networks.. [more info]
• Conference paper Nguyen T. & Pernkopf F. (2019) Acoustic Scene Classification with Mismatched Recording Devices Using Mixture of Experts Layers.. [more info]
• Conference paper Aichinger P., Roesner I., Pernkopf F. & Schoentgen J. (2019) Glottal Area Waveform Modeling based Voice Quality Typing.. [more info]
• Conference paper Pfeifenberger L., Zöhrer M. & Pernkopf F. (2019) Deep Complex-valued Neural Beamformers.. [more info]
• Journal article Pfeifenberger L., Zöhrer M. & Pernkopf F. (2019) Eigenvector-based Speech Mask Estimation for Multi- Channel Speech Enhancement. in IEEE/ACM Transactions on Audio Speech and Language Processing, 27(12), p. 2162 - 2172. [more info] [doi]
• Conference paper Aichernig B., Pernkopf F., Schumi R. & Wurm A. (2019) Predicting and Testing Latencies with Deep Learning: An IoT Case Study. (pp. 93-111). [more info] [doi]
• Conference paper Knoll C., Kulmer F. & Pernkopf F. (2019) Guided Selection of Accurate Belief Propagation Fixed Points. in Machine Learning and the Physical Sciences. [more info]
• Conference paper Knoll C. & Pernkopf F. (2019) Belief Propagation: Accurate Marginals or Accurate Partition Function - Where is the Difference?. in 2019 Conference on Uncertainty in Artificial Intelligence. [more info]
• Conference paper Aichernig B., Bloem R., Ebrahimi M., Horn M., Pernkopf F., Roth W., Rupp A., Tappler M. & Tranninger M. (2019) Learning a Behavior Model of Hybrid Systems Through Combining Model-Based Testing and Machine Learning. in 31st IFIP International Conference on Testing Software and Systems (pp. 3-21). [more info] [doi]
• Conference paper Trapp M., Peharz R. & Pernkopf F. (2019) Optimisation of Overparametrized Sum-Product Networks. in Workshop on Tractable Probabilistic Modeling at ICML. [more info]
• Preprint Ratajczak M., Tschiatschek S. & Pernkopf F. (2018) Sum-Product Networks for Structured Prediction.. [more info]
• Journal article Lammer G., Lanzenberger R., Rom A., Hanna A., Forrer M., Feuerstein M., Pernkopf F. & Mutsam N. (2018) Advanced data mining for process optimizations and use of ai to predict refractory wear and to analyze refractory behavior. in Iron & Steel Technology, 15(9), p. 52-60. [more info]
• Poster Nguyen T. & Pernkopf F. (2018) Acoustic Scene Classification Using A Convolutional Neural Network Ensemble and Nearest Neighbor Filters.. [more info]
• Journal article Aichinger P., Pernkopf F. & Schoentgen J. (2018) Detection of Extra Pulses in Synthesized Glottal Area Waveforms of Dysphonic Voices. in Biomedical Signal Processing and Control, 50, p. 158-167. [more info] [doi]
• Journal article Messner E., Zöhrer M. & Pernkopf F. (2018) Heart Sound Segmentation - An Event Detection Approach using Deep Recurrent Neural Networks. in IEEE Transactions on Biomedical Engineering , 65(9), p. 1964-1974. [more info] [doi]
• Conference paper Trapp M., Peharz R., Rassmusen C. & Pernkopf F. (2018) Learning Deep Mixtures of Gaussian Process Experts Using Sum-Product Networks.. [more info]
• Conference paper Nguyen T. & Pernkopf F. (2018) Acoustic Scene Classification Using A Convolutional Neural Network Ensemble and Nearest Neighbor Filters.. [more info]
• Conference paper Harb R. & Pernkopf F. (2018) Sound Event Detection Using Weakly Labeled Semi-Supervised Data with GCRNNs, VAT, and self-adaptive label refinement.. [more info]
• Conference paper Schindler G., Zöhrer M., Pernkopf F. & Fröning H. (2018) Towards Efficient Forward Propagation on Resource-Constrained Systems.. [more info]
• Conference paper Aichinger P., Roesner I., Pernkopf F. & Schoentgen J. (2018) Auditory Discrimination of Different Types of Sonified Synthesized Glottal Area Waveforms.. [more info]
• Conference paper Schrank T. & Pernkopf F. (2018) Automatic clustering of a network protocol with weakly-supervised clustering.. [more info]
• Conference paper Zöhrer M., Pfeifenberger L., Schnindler G., Fröning H. & Pernkopf F. (2018) Resource Efficient Deep Eigenvector Beamforming. (pp. 3354-3358). [more info] [doi]
• Journal article Roth W., Peharz R., Tschiatschek S. & Pernkopf F. (2018) Hybrid generative-discriminative training of Gaussian mixture models. in Pattern Recognition Letters , 112, p. 131-137. [more info] [doi]
• Conference paper Messner E., Fediuk M., Swatek P., Scheidl S., Smolle-Juttner F., Olschewski H. & Pernkopf F. (2018) Crackle and Breathing Phase Detection in Lung Sounds with Deep Bidirectional Gated Recurrent Neural Networks. in 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (pp. 356-359). [more info] [doi]
• Journal article Knoll C., Chen T., Mehta D. & Pernkopf F. (2018) Fixed Points of Belief Propagation - An Analysis via Polynomial Homotopy Continuation. in IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(9), p. 2124-2136. [more info] [doi]
• Journal article Aichinger P., Hagmüller M., Schneider-Stickler B., Schoentgen J. & Pernkopf F. (2018) Tracking of Multiple Fundamental Frequencies in Diplophonic Voices. in IEEE/ACM Transactions on Audio Speech and Language Processing, 26(2), p. 330-341. [more info] [doi]
• Journal article AUTHOR U., Marschik P., Pokorny F., Peharz R., Zhang D., O'Muircheartaigh J., Roeyers H., Bölte S., Spittle A., Urlesberger B., Schuller B., Poustka L., Ozonoff S., Pernkopf F., Pock T., Tammimies K., Enzinger C., Krieber M., Tomantschger I., Bartl-Pokorny K., Sigafoos J., Roche L., Esposito G., Gugatschka M., Nielsen-Saines K., Einspieler C. & Kaufmann W. (2017) A Novel Way to Measure and Predict Development. in Current Neurology and Neuroscience Reports , 17(5), p. 43. [more info] [doi]
• Journal article Krieber M., Bartl-Pokorny K., Pokorny F., Zhang D., Landerl K., Körner C., Pernkopf F., Pock T., Einspieler C. & Marschik P. (2017) Eye Movements during silent and oral reading in a regular orthography. in PLoS ONE, 12(2). [more info] [doi]
• Journal article Lammer G., Lanzenberger R., Rom A., Hanna A., Forrer M., Feuerstein M., Pernkopf F. & Mutsam N. (2017) Digital Refractory Age. in Bulletin: the Journal of Refractory Innovations , 2017(1), p. 12-20. [more info]
• Conference paper Aichinger P., Roesner I., Schöntgen J. & Pernkopf F. (2017) Modelling of Random Extra Pulses During Quasi-Closed Glottal Cycle Phases. in 10th International on Workshop Models and Analysis of Vocal Emissions for Biomedical Applications. [more info]
• Conference paper Trapp M., Madl T., Peharz R., Pernkopf F. & Trappl R. (2017) Safe Semi-Supervised Learning of Sum-Product Networks.. [more info]
• Conference paper Pfeifenberger L., Zöhrer M. & Pernkopf F. (2017) Eigenvector-based Speech Mask Estimation using a Logistic Regression for Multi-Channel Speech Enhancement. in 18th Annual Conference of the International Speech Communication Association (pp. 2660 - 2664). [more info] [doi]
• Conference paper Ratajczak M., Tschiatschek S. & Pernkopf F. (2017) Frame and Segment Level Recurrent Neural Networks for Phone Classification.. [more info]
• Conference paper Zöhrer M. & Pernkopf F. (2017) Virtual Adversarial Training and Data Augmentation for Acoustic Event Detection with Gated Recurrent Neural Networks.. [more info]
• Conference paper Lammer G., Lanzenberger R., Rom A., Hanna A., Forrer M., Feuerstein M., Pernkopf F. & Mutsam N. (2017) Advanced Data Mining for Process Optimizations and Use of A.I. to Predict Refractory Wear and to Analyse Refractory Behavior. in Iron & Steel Technology Conference and Exposition . [more info]
• Conference paper Pfeifenberger L., Zöhrer M. & Pernkopf F. (2017) DNN-based Speech Mask Estimation for Eigenvector Beamforming.. [more info]
• Conference paper Messner E., Hagmüller M. & Pernkopf F. (2017) Impact of Airflow Rate on Amplitude and Regional Distribution of Normal Lung Sounds.. [more info]
• Conference paper Knoll C. & Pernkopf F. (2017) On Loopy Belief Propagation – Local Stability Analysis for Non-Vanishing Fields.. [more info]
• Conference paper Messner E., Hagmüller M., Swatek P., Smolle-Juttner F. & Pernkopf F. (2017) Respiratory airflow estimation from lung sounds based on regression. in 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing (pp. 1123-1127). [more info] [doi]
• Journal article Aichinger P., Hagmüller M., Roesner I., Schneider-Stickler B., Schoentgen J. & Pernkopf F. (2017) Fundamental Frequency Tracking in Diplophonic Voices. in Biomedical Signal Processing and Control, 37, p. 69-81. [more info] [doi]
• Journal article Peharz R., Gens R., Pernkopf F. & Domingos P. (2017) On the Latent Variable Interpretation in Sum-Product Networks. in IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(10), p. 2030-2044. [more info] [doi]
• Journal article Mutsam N. & Pernkopf F. (2016) Supplementary Material: Derivations and Pseudocode for Learning Maximum Margin Hidden Markov Models for Sequence Classification. in Pattern Recognition Letters , 77. [more info]
• Conference paper Schrank T., Pfeifenberger L., Zöhrer M., Stahl J., Mowlaee Beikzadehmahaleh P. & Pernkopf F. (2016) Deep Beamforming and Data Augmentation for Robust Speech Recognition: Results of the 4th CHiME Challenge.. [more info]
• Conference paper Knoll C., Pernkopf F., Mehta D. & Chen T. (2016) Fixed Points Solutions of Belief Propagation.. [more info]
• Conference paper Pokorny F., Peharz R., Roth W., Zöhrer M., Pernkopf F., Marschik P. & Schuller B. (2016) Manual Versus Automated: The Challenging Routine of Infant Vocalisation Segmentation in Home Videos to Study Neuro(mal)development. in 17th Annual Conference of the International Speech Communication Association (pp. 2997 - 3001). [more info] [doi]
• Journal article Mutsam N. & Pernkopf F. (2016) Maximum Margin Hidden Markov Models for Sequence Classification. in Pattern Recognition Letters , 77, p. 14-20. [more info] [doi]
• Conference paper Fahringer J., Schrank T., Stahl J., Mowlaee Beikzadehmahaleh P. & Pernkopf F. (2016) Phase-Aware Signal Processing for Automatic Speech Recognition. (pp. 3374-3378). [more info]
• Conference paper Aichernig B., Bloem R., Pernkopf F., Röck F., Schrank T. & Tappler M. (2016) Learning Models of a Network Protocol using Neural Network Language Models.. [more info]
• Conference paper Schuller B., Peharz R., Pernkopf F., Bartl-Pokorny K., Einspieler C., Marschik P. & Pokorny F. (2016) Retrospektive Analyse frühkindlicher Lautäußerungen in "Home- Videos": Ein signalanalytischer Ansatz zur Früherkennung von Entwicklungsstörungen.. [more info]
• Conference paper Trapp M., Peharz R., Skowron M., Madl T., Pernkopf F. & Trappl R. (2016) Structure Inference in Sum-Product Networks using Infinite Sum-Product Trees.. [more info]
• Conference paper Roth W. & Pernkopf F. (2016) Variational Inference in Neural Networks using an Approximate Closed-Form Objective.. [more info]
• Conference paper Ratajczak M., Tschiatschek S. & Pernkopf F. (2016) Virtual Adversarial Training Applied to Neural Higher-Order Factors for Phone Classification.. [more info]
• Conference paper Zöhrer M. & Pernkopf F. (2016) Gated Recurrent Networks applied to Acoustic Scene Classification.. [more info]
• Conference paper Pokorny F., Schuller B., Peharz R., Pernkopf F., Bartl-Pokorny K., Einspieler C. & Marschik P. (2016) Contributing to the early identification of neurodevelopmental disorders: The retrospective analysis of pre-linguistic vocalisations in home video material.. [more info]
• Poster Knoll C., Pernkopf F., Mehta D. & Chen T. (2016) Fixed Point Solutions of Belief Propagation.. [more info]
• Conference paper Messner E., Hagmüller M., Swatek P. & Pernkopf F. (2016) A Robust multichannel lung sound recording device. in 9th International Conference on Biomedical Electronics and Devices, BIODEVICES 2016 - Part of 9th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2016 (pp. 34-39). [more info]
• Conference paper Aichinger P., Hagmüller M., Roesner I., Bigenzahn W., Schneider-Stickler B., Schoentgen J. & Pernkopf F. (2015) Measurement of fundamental frequencies in diplophonic voices. in 9th International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications (pp. 21-24). [more info]
• Conference paper Aichinger P., Hagmüller M., Roesner I., Bigenzahn W., Schneider-Stickler B., Schoentgen J. & Pernkopf F. (2015) Measurement of Fundamental Frequencies in Diplophonic Voice. in 9th International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications (pp. 21-24). [more info]
• Conference paper Zöhrer M., Pernkopf F. & Peharz R. (2015) On Representation Learning for Artificial Bandwidth Extension. (pp. 791-795). [more info]
• Conference paper Knoll C., Rath M., Tschiatschek S. & Pernkopf F. (2015) Message Scheduling Methods for Belief Propagation. in European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (pp. 295). [more info] [doi]
• Conference paper Zöhrer M. & Pernkopf F. (2015) REPRESENTATION MODELS IN SINGLE CHANNEL SOURCE SEPARATION. (pp. 713-717). [more info] [doi]
• Conference paper Tschiatschek S. & Pernkopf F. (2015) Learning of Bayesian Network Classifiers Under Computational Constraints. (pp. x-x). [more info]
• Conference paper Ratajczak M., Tschiatschek S. & Pernkopf F. (2015) Structured Regularizer for Neural Higher-Order Sequence Models. (pp. x-x). [more info]
• Conference paper Pokorny F., Graf F., Pernkopf F. & Schuller B. (2015) Detection of Negative Emotions in Speech Signals Using Bags-of-Audio-Words. (pp. x-x). [more info]
• Conference paper Pfeifenberger L., Schrank T., Zöhrer M., Hagmüller M. & Pernkopf F. (2015) Multi-channel speech processing architectures for noise robust speech recognition: 3rd CHiME Challenge results. in IEEE Workshop on Automatic Speech Recognition & Understanding. [more info]
• Conference paper Ratajczak M., Tschiatschek S. & Pernkopf F. (2015) Neural Higher-Order Factors in Conditional Random Fields for Phoneme Classification. (pp. x-x). [more info]
• Conference paper Peharz R., Tschiatschek S., Pernkopf F. & Domingos P. (2015) On theoretical properties of sum-product networks. (pp. X-x). [more info]
• Conference paper Tschiatschek S. & Pernkopf F. (2015) Generatively Optimized Bayesian Network Classifiers Under Computational Constraints. (pp. x-x). [more info]
• Journal article Zöhrer M., Pernkopf F. & Peharz R. (2015) Representation Learning for Single-Channel Source Separation and Bandwidth Extension. in IEEE Transactions on Audio Speech and Language Processing , 23(12), p. 2398-2409. [more info] [doi]
• Journal article Tschiatschek S. & Pernkopf F. (2015) On Bayesian Network Classifiers with Reduced Precision Parameters. in IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(4), p. 774-785. [more info] [doi]
• Journal article Leitner C. & Pernkopf F. (2015) On pre-image iterations for speech enhancement. in SpringerPlus , 4, p. 243--. [more info] [doi]
• Conference paper Wohlmayr M., Mohr L. & Pernkopf F. (2014) On Self-Adaptation in Single-Channel Source Separation. (pp. x-x). [more info]
• Conference paper Zöhrer M. & Pernkopf F. (2014) Single-Channel Source Separation with General Stochastic Networks. (pp. x-x). [more info]
• Conference paper Zöhrer M. & Pernkopf F. (2014) General Stochastic Networks for Classication. (pp. x-x). [more info]
• Conference paper Pokorny F., Graf F. & Pernkopf F. (2014) Erkennung negativer Emotionen in Sprachsignalen mittels Bags-of-Audio-Words. (pp. x-x). [more info]
• Conference paper Zehetner A., Hagmüller M. & Pernkopf F. (2014) Wake-Up-Word Spotting for Mobile Systems. (pp. x-x). [more info]
• Conference paper Tschiatschek S., Paul K. & Pernkopf F. (2014) Integer Bayesian Networks. (pp. x-x). [more info]
• Conference paper Pfeifenberger L. & Pernkopf F. (2014) A Multi-channel Postlter based on the Ideal Diffuse Sound Field. (pp. x-x). [more info]
• Conference paper Pfeifenberger L. & Pernkopf F. (2014) Blind Source Extraction Based on a Direction-Dependent A-Priori SNR. (pp. x-x). [more info]
• Conference paper Leitner C., Cordovilla J. & Pernkopf F. (2014) Evaluation of Speech Enhancement Based on Pre-Image Iterations Using Automatic Speech Recognition. (pp. x-x). [more info]
• Conference paper Ratajczak M., Tschiatschek S. & Pernkopf F. (2014) Context-Specic Deep Conditional Random Fields for Structured Prediction. (pp. 1-8). [more info]
• Conference paper Peharz R., Kapeller G., Mowlaee Beikzadehmahaleh P. & Pernkopf F. (2014) Modeling Speech with Sum- Product Networks: Application to Bandwidth Extension. in 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing (pp. 3699-3703). [more info]
• Chapter Pernkopf F., Peharz R. & Tschiatschek S. (2014) Introduction to Probabilistic Graphical Models. . [more info]
• Conference paper Wohlmayr M. & Pernkopf F. (2013) Model Adaptation of Factorial HMMs for Multipitch Tracking. (pp. 26052013-31052013). [more info]
• Conference paper Mowlaee Beikzadehmahaleh P., Cordovilla J., 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. (pp. X-X). [more info]
• Conference paper Peharz R., Geiger B. & Pernkopf F. (2013) Greedy Part-wise Learning of Sum-Product Networks. (pp. 612-627). [more info]
• Conference paper Tschiatschek S. & Pernkopf F. (2013) On the Asymptotic Optimality of Maximum Margin Bayesian Networks. in International Conference on Artificial Intelligence and Statistics (pp. 590-598). [more info]
• Conference paper Leitner C. & Pernkopf F. (2013) Generalization of Pre-Image Iterations for Speech Enhancement. (pp. 7010-7014). [more info]
• Conference paper Peharz R., Tschiatschek S. & Pernkopf F. (2013) The Most Generative Maximum Margin Bayesian Networks. (pp. 235-243). [more info]
• Conference paper Tschiatschek S., Chacon C. & Pernkopf F. (2013) Bound for Bayesian Network Classifiers with Reduced Precision Parameters. (pp. 3357 -3361). [more info]
• Conference paper Cordovilla J., Pessentheiner H., Hagmüller M., Mowlaee Beikzadehmahaleh P., Pernkopf F. & Kubin G. (2013) A German distant speech recognizer based on 3D beamforming and harmonic missing data mask.. in Deutsche Jahrestagung für Akustik (pp. 2049-2052). [more info]
• Journal article Pernkopf F. & Wohlmayr M. (2013) Stochastic Margin-based Structure Learning of Bayesian Network Classiers. in Pattern Recognition, 46(2), p. 464-471. [more info]
• Journal article Wohlmayr M. & Pernkopf F. (2013) Model-Based Multiple Pitch Tracking Using Factorial HMMs: Model Adaptation and Inference. in IEEE Transactions on Audio Speech and Language Processing , 21(8), p. 1742-1754. [more info] [doi]
• Conference paper Peharz R. & Pernkopf F. (2012) Exact Maximum Margin Structure Learning of Bayesian Networks. (pp. X-X). [more info]
• Conference paper Tschiatschek S., Reinprecht P., Mücke M., Pernkopf F. & Mücke M. (2012) Discriminative Bayesian Network Classiers with Reduced Precision Parameters. (pp. 74-89). [more info]
• Conference paper Leitner C. & Pernkopf F. (2012) Extension of Pre-Image Speech De-Noising by Voice Activity Detection Using a Bone Conductive Microphone. in International Workshop on Acoustic Signal Enhancement (pp. 1-4). [more info]
• Conference paper Leitner C. & Pernkopf F. (2012) Speech Enhancement Using Pre-Image Iterations. (pp. 4665-4668). [more info]
• Conference paper Leitner C. & Pernkopf F. (2012) Musical Noise Suppression for Speech Enhancement Using Pre-Image Iterations. (pp. 478-481). [more info]
• Conference paper Peharz R. & Pernkopf F. (2012) On Linear and MIXMAX Interaction Models for Single Channel Source Separation. (pp. 249-252). [more info]
• Conference paper Leitner C. & Pernkopf F. (2012) Suppression of Musical Noise in Enhanced Speech Using Pre-Image Iterations. (pp. 345-349). [more info]
• Conference paper Tschiatschek S., Mutsam N. & Pernkopf F. (2012) Handling Missing Features in Maximum Margin Bayesian Network Classifiers. (pp. X-X). [more info]
• Patent Wohlmayr M., Stark M. & Pernkopf F. (2012) Verfahren zur Ermittlung von Grundfrequenz-Verläufen mehrerer Signalquellen.. [more info]
• Journal article Pernkopf F., Wohlmayr M. & Tschiatschek S. (2012) Maximum Margin Bayesian Network Classifiers. in IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(3), p. 521-532. [more info] [doi]
• Journal article Peharz R. & Pernkopf F. (2012) Sparse nonnegative matrix factorization with ℓ0-constraints. in Neurocomputing, 80, p. 38-46. [more info] [doi]
• Conference paper Tschiatschek S. & Pernkopf F. (2012) Convex Combinations of Maximum Margin Bayesian Network Classifiers.. [more info]
• Conference paper Peharz R., Wohlmayr M. & Pernkopf F. (2011) Gain-robust Multi-pitch Tracking Using Sparse Nonnegative Matrix Factorization. (pp. 5416-5419). [more info] [doi]
• Conference paper Wohlmayr M. & Pernkopf F. (2011) EM-based Gain Adaptation for Probabilistic Multipitch Tracking. in International Conference on Spoken Language Processing (pp. 1969-1972). [more info]
• Conference paper Leitner C. & Pernkopf F. (2011) The Pre-Image Problem and Kernel PCA for Speech Enhancement. in ISCA Tutorial and Research Workshop on Non-Linear Speech Processing (pp. 199-206). [more info]
• Conference paper Wohlmayr M., Peharz R. & Pernkopf F. (2011) Efficient Implementation of Probabilistic Multi-Pitch Tracking. in 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing (pp. 5412-5415). [more info]
• Conference paper Leitner C., Pernkopf F. & Kubin G. (2011) Kernel PCA for Speech Enhancement. (pp. 1221-1224). [more info]
• Conference paper Pernkopf F., Wohlmayr M. & Mücke M. (2011) Maximum Margin Structure Learning of Bayesian Network Classifiers. (pp. 2076-2079). [more info]
• Conference paper Pirker G., Wohlmayr M., Petrik S. & Pernkopf F. (2011) A Pitch Tracking Corpus with Evaluation on Multipitch Tracking Scenario. (pp. 1509-1512). [more info]
• Journal article Wohlmayr M., Stark M. & Pernkopf F. (2011) A Probabilistic Interaction Model for Multipitch Tracking With Factorial Hidden Markov Models. in IEEE Transactions on Audio Speech and Language Processing , 19(4), p. 799-810. [more info] [doi]
• Journal article Stark M., Wohlmayr M. & Pernkopf F. (2011) Source-Filter based Single Channel Speech Separation using Pitch Information. in IEEE Transactions on Audio Speech and Language Processing , 19(2), p. 242-255. [more info] [doi]
• Journal article Petrik S., Drexel C., Fessler L., Jancsary J., Klein A., Kubin G., Matiasek J., Pernkopf F. & Trost H. (2011) Semantic and Phonetic Automatic Reconstruction of Medical Dictations. in Computer Speech and Language , 25(2), p. 363-385. [more info] [doi]
• Conference paper Peharz R., Stark M. & Pernkopf F. (2010) A Factorial Sparse Coder Model for Single Channel Source Separation. in Interspeech - International Conference on Spoken Language Processing (pp. 386-389). [more info]
• Conference paper Peharz R., Stark M. & Pernkopf F. (2010) Sparse Nonnegative Matrix Factorization using ℓ0-Constraints. in IEEE International Workshop on Machine Learning for Signal Processing (pp. 83-88). [more info]
• Conference paper Stark M. & Pernkopf F. (2010) On Optimizing the Computational Complexity for VQ-Based Single Channel Source Separation. (pp. 237-240). [more info]
• Conference paper Pernkopf F. & Wohlmayr M. (2010) Large Margin Learning of Bayesian Classifiers based on Gaussian Mixture Models. in European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (pp. 50-55). [more info] [doi]
• Conference paper Pernkopf F. & Wohlmayr M. (2010) Maximum Margin Training for Gaussian Mixture Models with Application to Multipitch Tracking. (pp. X-X). [more info]
• Conference paper Wohlmayr M., Stark M. & Pernkopf F. (2010) A Mixture Maximization Approach to Multipitch Tracking With Factorial Hidden Markov Models. (pp. 5070-5073). [more info]
• Conference paper Stark M., Wohlmayr M. & Pernkopf F. (2010) Single Channel Speech Separation Using Source-Filter Representation. (pp. 826-829). [more info]
• Journal article Tantibundhit C., Pernkopf F. & Kubin G. (2010) Joint Time-Frequency Segmentation Algorithm for Transient Speech Decomposition and Speech Enhancement. in IEEE Transactions on Audio Speech and Language Processing , 18(6), p. 1417-1428. [more info] [doi]
• Journal article Pernkopf F. & Bilmes J. (2010) Efficient Heuristics for Discriminative Structure Learning of Bayesian Network Classifiers. in Journal of Machine Learning Research, p. 2323-2360. [more info]
• Conference paper Pernkopf F. & Wohlmayr M. (2009) On Discriminative Parameter Learning of Bayesian Network Classifiers. in European Conference on Machine Learning (ECML 2009) (pp. 221-237). [more info]
• Conference paper Stark M. & Pernkopf F. (2009) A Dictionary Based Noise Robust Pitch Tracker. in International Conference on Speech and Computer, SPECOM (pp. 211 -214). [more info]
• Conference paper Wohlmayr M. & Pernkopf F. (2009) Finite Mixture Spectrogram Modeling for Multipitch Tracking Using A Factorial Hidden Markov Model. in Interspeech - International Conference on Spoken Language Processing (pp. 1079-1082). [more info]
• Conference paper Böhm C. & Pernkopf F. (2009) Effective metric-based speaker segmentation in the frequency domain. in IEEE International Conference on Acoustics, Speech, and Signal Processing (pp. 4081-4084). [more info]
• Conference paper Wiesenegger M. & Pernkopf F. (2009) Wavelet-Based Speaker Change Detection in Single Channel Speech Data. in Interspeech - International Conference on Spoken Language Processing (pp. X-X). [more info]
• Conference paper Stark M. & Pernkopf F. (2009) Towards source-filter based single sensor speech separation. in IEEE International Conference on Acoustics, Speech, and Signal Processing (pp. 97-100). [more info] [doi]
• Conference paper Kranzler C., Pernkopf F., Muhr R., Pucher M. & Neubarth F. (2009) Text-To-Speech Engine with Austrian German Corpus. in International Conference on Speech and Computer, SPECOM (pp. X-X). [more info]
• Conference paper Tantibundhit C., Pernkopf F. & Kubin G. (2009) Speech Enhancement Based on Joint Time-Frequency Segmentation. in 2009 IEEE International Conference on Acoustics, Speech and Signal Processing (pp. 4673-4676). [more info]
• Habilitation Pernkopf F. (2009) Graphical Models: Discriminative Learning, Inference, and Applications.. [more info]
• Conference paper Pham V., Stadtschnitzer M., Pernkopf F. & Kubin G. (2008) Voice Activity Detection Algorihtms Using Subband Power Distance Feature for Noisy Environments. (pp. 1-4). [more info]
• Conference paper Pernkopf F. & Bilmes J. (2008) Order-based Discriminative Structure Learning for Bayesian network Classifiers. in International Symposium on Artificial Intelligence and Mathematics (pp. 1-8). [more info]
• Conference paper Stark M., Pernkopf F., Pham V. & Kubin G. (2008) Vocal-Tract Modeling For Speaker Independent Single Channel Source SEPARATION. in 1st IAPR Workshop on Cognitive Information Processing (pp. 217-220). [more info]
• Conference paper Wohlmayr M. & Pernkopf F. (2008) Multipitch Tracking Using A Factorial Hidden Markov Model. (pp. 1-4). [more info]
• Conference paper Petrik S. & Pernkopf F. (2008) Language Model Adaptation for Medical Dictations by Automatic Phonetics-Driven Transcript Reconstruction. in IASTED International Conference on Artificial Intelligence and Applications (pp. 194-199). [more info]
• Conference paper Petrik S. & Pernkopf F. (2008) Automatic Phonetics-Driven Reconstruction of Medical Dictations on Multiple Levels of Segmentation. (pp. 4317-4320). [more info] [doi]
• Conference paper Pernkopf F. (2008) Multiple Object Tracking Using Incremental Learning for Appearance Model Adaptation. in 3rd International Conference on Computer Vision Theory and Applications (pp. 1-6). [more info]
• Journal article Pernkopf F., Pham T. & Bilmes J. (2008) Broad Phonetic Classification Using Discriminative Bayesian Networks. in Speech Communication, 51(2), p. 151-166. [more info]
• Journal article Pernkopf F. (2008) Tracking of Multiple Targets Using On-Line Learning for Appearance Model Adaptation. in IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 38(6), p. 1465-1475. [more info]
• Conference paper Pernkopf F. (2007) Tracking of Multiple Targets using On-line Learning for Appearance Model Adaptation. (pp. 602-614). [more info]
• Conference paper Denchev V., Pernkopf F. & Radev D. (2007) Modeling and Clustering Analysis of Broadband Convergence Networks. (pp. 1-12). [more info]
• Conference paper Stark M., Pham V., Pernkopf F. & Kubin G. (2007) Robust Speaker Verification in Air Traffic Control using Improved Voice Activity Detection. in Signal Processing, Pattern Recognition, and Applications (pp. 298-303). [more info]
• Conference paper Kepesi M., Pernkopf F. & Wohlmayr M. (2007) Joint Position-Pitch Tracking for 2-Channel Audio. (pp. 303-306). [more info]
• (Old data) Lecture or Presentation Stark M., Pham V., Pernkopf F., Kubin G. & Hering H. (2006) Speaker Verification for Air Traffic Control.. [more info]
• Conference paper Pernkopf F. & Pham V. (2006) Bayesian Networks for Phonetic Classification Using Time-Scale Features. (pp. 1-4). [more info]
• Conference paper Pernkopf F. (2006) Discriminative Learning of Bayesian Network Classifiers. in IASTED International Conference on Artificial Intelligence and Soft Computing (pp. 1-6). [more info]
• Conference paper Pernkopf F. (2005) On Initialization of Gaussian Mixtures: A Hybrid Genetic EM Algorithm. (pp. 693-696). [more info]
• Conference paper Pernkopf F. & Bilmes J. (2005) Discriminative versus Generative Parameter and Structure Learning of Bayesian Network Classifiers. (pp. 657-664). [more info]
• Journal article Pernkopf F. & Bouchaffra D. (2005) Genetic-based EM Algorithm for Learning Gaussian Mixture Models. in IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(8), p. 1344-1348. [more info] [doi]
• Journal article Pernkopf F. (2005) 3D Surface Analysis using Coupled HMMs. in Machine Vision and Applications. [more info]
• Journal article Pernkopf F. (2005) 3D Surface Acquisition and Reconstruction for Inspection of Raw Steel Products. in Computers in Industry. [more info]
• Journal article Pernkopf F. (2005) Bayesian Network Classifiers versus Selective k-NN Classifier. in Pattern Recognition, 38(1), p. 1-10. [more info]
• Conference paper Baum M., Dizdarevic V., Hagmüller M., Kubin G. & Pernkopf F. (2004) Prosody-Based Recognition of Spoken German Varieties. in IEEE International Conference on Acoustics, Speech, and Signal Processing (pp. 929-932). [more info]
• Conference paper Pernkopf F. (2004) Bayesian Network Classifiers versus k-NN Classifier using Sequential Feature Selection. (pp. 360-365). [more info]
• Conference paper Pernkopf F. (2004) 3D Surface Inspection using Couples HMMs. (pp. 223-226). [more info]
• Journal article Pernkopf F. (2004) Detection of Surface Defects on Raw Steel Blocks using Bayesian Network Classifiers. in Pattern analysis and applications, 7(3), p. 333-342. [more info]
• Conference paper Pernkopf F. & O'Leary P. (2003) A Search-and-Score Structure Learning Algorithm for Bayesian Network Classifiers. (pp. 1-12). [more info]
• Conference paper Pernkopf F. & O'Leary P. (2003) Shape Description and Analysis of Range Data for Milled Steel Blocks. (pp. 74-81). [more info]
• Conference paper Pernkopf F. & O'Leary P. (2003) A Search-and-Score Structure Learning Algorithm for Bayesian Network Classifiers. (pp. X-X). [more info]
• Journal article Pernkopf F. & O'Leary P. (2003) Image Acquisition Techniques for Automatic Visual Inspection of Metallic Surfaces. in NDT & E international, 36(8), p. 609-617. [more info]
• Journal article Pernkopf F. & O'Leary P. (2003) Floating Search Algorithm for Structure Learning of Bayesian Network Classifiers. in Pattern Recognition Letters , 24, p. 2839-2848. [more info]
• Conference paper Pernkopf F., Pernkopf F. & O'Leary P. (2002) Dedection fo Surface Defects on Raw Milled Steel Blocks Using Range Imaging. (pp. 170-181). [more info]
• Conference paper Pernkopf F. & O'Leary P. (2002) Image Acquisition and Analysis Techniques for Automatic Visual Inspection of Surfaces. (pp. 180-187). [more info]
• Conference paper Pernkopf F., Pernkopf F. & O'Leary P. (2002) Automatic Surface Inspection of Raw Milled Steel Blocks Using Range Imaging.. [more info]
• Journal article Pernkopf F. & O'Leary P. (2002) Visual Inspection of Machined Metallic High-Precision Surfaces. in EURASIP Journal on Applied Signal Processing, 2002(7), p. 667-678. [more info]
• Book Pernkopf F. (2002) Automatic Visual Inspection of Metallic Surfaces. Reihe 8, Nr. 949 ed.. [more info]
• Doctoral Thesis Pernkopf F. (2002) Automatic Visual Inspection of Metallic Surfaces.. [more info]
• Conference paper Pernkopf F. & O'Leary P. (2001) Feature Selection and Classification using Genetic Algorithms with a novel Encoding. (pp. 161-168). [more info]
• Conference paper Pernkopf F. & O'Leary P. (2001) Automatic Inspection System for Detection and Classification of Flaws on Turned Parts. (pp. 359-364). [more info]
• Conference paper Pernkopf F., Schiller A. & O'Leary P. (2001) Quality Control of Metallic Surfaces by means of Digital Image Processing. (pp. 138-151). [more info]
• Diploma Thesis Pernkopf F. (1999) Control Software for a 64 by 64 pixel Spatial Light Modulator.. [more info]