Book Chapters

  • Franz Pernkopf, Robert Peharz, and Sebastian Tschiatschek,
    Introduction to probabilistic graphical models,
    Academic Press Library Signal Process, 1, pp. 989-1064, 2014

Journal papers

  • Peter B. Marschik, Florian Pokorny, Robert Peharz, et al. (23 more authors),
    A Novel Way to Measure and Predict Development: A Heuristic Approach to Facilitate the Early Detection of Neurodevelopmental Disorders,
    Current Neurology and Neuroscience Reports, 17(5), 43 pages, 2017.
  • Robert Peharz, Robert Gens, Franz Pernkopf, and Pedro Domingos,
    On the latent variable interpretation in sum-product networks,
    IEEE Transactions on Pattern Analysis and Machine Intelligence, in press, 2017.
  • Christa Einspieler, Robert Peharz, and Peter B. Marschik,
    Fidgety movements–tiny in appearance, but huge in impact,
    Jornal de Pediatria
    , 92(3), pp. 64-70, 2016.
  • Matthias Zöhrer, Robert Peharz, and Franz Pernkopf,
    Representation learning for single-channel source separation and bandwidth extension,
    IEEE/ACM Transactions on Audio, Speech, and Language Processing
    , 23(12), pp. 2398-2409, 2015.
  • Robert Peharz and Franz Pernkopf,
    Sparse nonnegative matrix factorization with ℓ0-constraints,
    Elsevier Neurocomputing, 80, pp. 38-46, 2012.

Conference Papers

  • Antonio Vergari, Robert Peharz, Nicola Di Mauro, Alejandro Molina, Kristian Kersting, Floariana Esposito,
    Sum-Product Autoencoding: Encoding and Decoding Representations using Sum-Product Networks,
    AAAI, accepted, 2018.
  • Martin Trapp, Tamas Madl, Robert Peharz, Franz Pernkopf, and Robert Trappl,
    Safe Semi-Supervised Learning of Sum-Product Networks,
    UAI, accepted, 2017.
  • Florian Pokorny, Robert Peharz, Wolfgang Roth, Matthias Zöhrer, Franz Pernkopf, Peter B. Marschik, and Björn W. Schuller,
    Manual versus automated: the challenging routine of infant vocalisation segmentation in home videos to study neuro(mal)development,
    Interspeech, pp. 2997–3001, 2016.
  • Matthias Zöhrer, Robert Peharz, and Franz Pernkopf,
    On representation learning for artificial bandwidth extension,
    Interspeech, pp. 791–795, 2015.
  • Robert Peharz, Sebastian Tschiatschek, Franz Pernkopf, and Pedro Domingos,
    On theoretical properties of sum-product networks,
    AISTATS, pp. 744–752, 2015.
  • Robert Peharz, Georg Kapeller, Pejman Mowlaee, and Franz Pernkopf,
    Modeling speech with sum-product networks: application to bandwidth extension,
    ICASSP, pp. 3699–3703, 2014.
  • Robert Peharz, Bernhard C. Geiger, and Franz Pernkopf,
    Greedy part-wise learning of sum-product networks,
    ECML/PKDD, pp. 612–627, 2013.
  • Robert Peharz, Sebastian Tschiatschek, and Franz Pernkopf,
    The most generative maximum margin Bayesian networks,
    ICML, pp. 235–243, 2013.
  • Robert Peharz and Franz Pernkopf,
    Exact maximum margin structure learning of Bayesian networks,
    ICML, pp. 1047–1054, 2012.
  • Robert Peharz and Franz Pernkopf,
    On linear and mixmax interaction models for single channel source separation,
    ICASSP, pp. 249–252, 2012.
  • Robert Peharz, Michael Wohlmayr, and Franz Pernkopf,
    Gain-robust multi-pitch tracking using sparse nonnegative matrix factorization,
    ICASSP, pp. 5416–5419, 2011.
  • Michael Wohlmayr, Robert Peharz, and Franz Pernkopf,
    Efficient implementation of probabilistic multi-pitch tracking,
    ICASSP, pp. 5412–5415, 2011.
  • Robert Peharz, Michael Stark, and Franz Pernkopf,
    A factorial sparse coder model for single channel source separation,
    Interspeech, pp. 386–389, 2010.
  • Robert Peharz, Michael Stark, and Franz Pernkopf,
    Sparse nonnegative matrix factorization using ℓ0-constraints,
    IEEE MLSP, pp. 83–88, 2010.

Workshop papers

  • Martin Trapp, Robert Peharz, Marcin Skowron, Tamas Madl, Franz Pernkopf and Robert Trappl,
    Structure inference in sum-product networks using infinite sum-product trees,
    NIPS Workshop on Practical Bayesian Nonparametrics, 2016.
  • Robert Peharz, Robert Gens, and Pedro Domingos,
    Learning selective sum-product networks,
    ICML Workshop on Learning Tractable Probabilistic Models, 2014.