AIConfPaper
← Search

Franz Pernkopf

22 accepted papers

2025

Avoiding Domain Drift and Constant Predictions with Diffusion Enhanced Vector-Quantized Autoencoders for Temperature Predictions

Nina Lampl, João Machado de Freitas, Alexander Fuchs, Benedikt Brezina, Michael Klitzsch, Franz Pernkopf
ICASSP 2025accepted

Accurate temperature prediction in rotary cement kilns is crucial for process stability and equipment longevity. However, the repeated application of the predicted values creates an error accumulation over the length of the forecast, causing a domain drift of the predictions. This issue is exacerbat…

Cited by 0Source ↗Scholar ↗
2025

Effective Bayesian Causal Inference via Structural Marginalisation and Autoregressive Orders

Christian Toth, Christian Knoll, Franz Pernkopf, Robert Peharz
AISTATS 2025poster

The traditional two-stage approach to causal inference first identifies a *single* causal model (or equivalence class of models), which is then used to answer causal queries. However, this neglects any epistemic model uncertainty. In contrast, *Bayesian* causal inference does incorporate epistemic u…

Cited by 0Source ↗code ↗Scholar ↗
2025

Input Uncertainty Attribution by Uncertainty Propagation

Benedikt Kantz, Sophie Steger, Clemens Staudinger, Christoph Feilmayr, Johannes Wachlmayr, Alexander Haberl +2
ICASSP 2025accepted

Attributing uncertainties to the input space elevates the trustworthiness and explainability of machine learning applications. This paper proposes a novel method called Smoothness Constrained Attribution (SCA), which uses the uncertainty propagation mechanism to propagate the output uncertainty back…

Cited by 0Source ↗Scholar ↗
2025

Uncertainty prediction for prominence classification with chroma features

Julian Linke, Sophie Steger, Philipp Steinwender, Gernot Kubin, Franz Pernkopf, Barbara Schuppler
ICASSP 2025accepted

This paper presents methods for prominence classification in conversational speech. Most existing tools rely on prosodic features extracted at syllable- or phone-level, performing well on read speech. This is not the case for conversational speech, where the quality of automatic segmentation is sign…

Cited by 0Source ↗Scholar ↗
2024

Data-Scarce Condition Modeling Requires Model-Based Prior Regularization

Nikolaus Mutsam, Alexander Fuchs, Fabio Ziegler, Franz Pernkopf
ICASSP 2024accepted

In the metallurgical industry, taking measurements during production can be infeasible or undesired, and only the terminated process can be measured. This poses problems for regression models, as the intermediate target values for a time series are hidden in the accumulated end-of-process measuremen…

Cited by 0Source ↗Scholar ↗
2023

Self-Attention for Enhanced OAMP Detection in MIMO Systems

Alexander Fuchs, Christian Knoll, Nima N. Moghadam, Alexey Pak, Jinliang Huang, Erik Leitinger +1
ICASSP 2023accepted

Multiple-Input Multiple-Output (MIMO) systems are essential for wireless communications. Since classical algorithms for symbol detection in MIMO setups require large computational resources or provide poor results, data-driven algorithms are becoming more popular. Most of the proposed algorithms, ho…

Cited by 2Source ↗Scholar ↗
2023

Variational Message Passing-Based Respiratory Motion Estimation and Detection Using Radar Signals

Jakob Möderl, Erik Leitinger, Franz Pernkopf, Klaus Witrisal
ICASSP 2023accepted

We present a variational message passing (VMP)-based approach to detect the presence of a person based on their respiratory chest motion using multistatic ultra-wideband (UWB) radar. In the process, the respiratory motion is estimated for contact-free vital sign monitoring. The received signal is mo…

Cited by 0Source ↗Scholar ↗
2022

Active Bayesian Causal Inference

Christian Toth, Lars Lorch, Christian Knoll, Andreas Krause, Franz Pernkopf, Robert Peharz +1
NeurIPS 2022accept

Causal discovery and causal reasoning are classically treated as separate and consecutive tasks: one first infers the causal graph, and then uses it to estimate causal effects of interventions. However, such a two-stage approach is uneconomical, especially in terms of actively collected intervention…

Cited by 42Source ↗PDF ↗code ↗Scholar ↗
2022

End-to-End Keyword Spotting Using Neural Architecture Search and Quantization

David Peter, Wolfgang Roth, Franz Pernkopf
ICASSP 2022accepted

This paper introduces neural architecture search (NAS) for the automatic discovery of end-to-end keyword spotting (KWS) models for limited resource environments. We employ a differentiable NAS approach to optimize the structure of convolutional neural networks (CNNs) operating on raw audio waveforms…

Cited by 0Source ↗Scholar ↗
2022

Fixing the Bethe approximation: How structural modifications in a graph improve belief propagation

Harald Leisenberger, Franz Pernkopf, Christian Knoll
UAI 2022poster

Belief propagation is an iterative method for inference in probabilistic graphical models. Its well-known relationship to a classical concept from statistical physics, the Bethe free energy, puts it on a solid theoretical foundation. If belief propagation fails to approximate the marginals, then thi…

Cited by 5Source ↗PDF ↗Scholar ↗
2021

Convergence behavior of belief propagation: estimating regions of attraction via Lyapunov functions

Harald Leisenberger, Christian Knoll, Richard Seeber, Franz Pernkopf
UAI 2021poster

In this work, we estimate the regions of attraction for belief propagation. This extends existing stability analysis and provides initial message values for which belief propagation is guaranteed to converge. Our approach utilizes the theory of Lyapunov functions that, however, does not readily yiel…

Cited by 5Source ↗PDF ↗Scholar ↗
2020

Acoustic Scene Classification for Mismatched Recording Devices Using Heated-Up Softmax and Spectrum Correction

Truc Nguyen, Franz Pernkopf, Michal Kosmider
ICASSP 2020accepted

Deep neural networks (DNNs) are successful in applications with matching inference and training distributions. In realworld scenarios, DNNs have to cope with truly new data samples during inference, potentially coming from a shifted data distribution. This usually causes a drop in performance. Acous…

Cited by 0Source ↗Scholar ↗
2020

Deep Structured Mixtures of Gaussian Processes

Martin Trapp, Robert Peharz, Franz Pernkopf, Carl Edward Rasmussen
AISTATS 2020poster

Gaussian Processes (GPs) are powerful non-parametric Bayesian regression models that allow exact posterior inference, but exhibit high computational and memory costs. In order to improve scalability of GPs, approximate posterior inference is frequently employed, where a prominent class of approximat…

Cited by 43Source ↗PDF ↗code ↗Scholar ↗
2020

Towards Real-Time Single-Channel Singing-Voice Separation with Pruned Multi-Scaled Densenets

Markus Huber, Günther Schindler, Christian Schörkhuber, Wolfgang Roth, Franz Pernkopf, Holger Fröning
ICASSP 2020accepted

Modern musical source separation systems based on deep neural networks reach unprecedented levels of separation quality. However, harnessing the power of these large-scale models in typical audio production environments, which frequently offer only limited computing resources while demanding real-ti…

Cited by 0Source ↗Scholar ↗
2019

Bayesian Learning of Sum-Product Networks

Martin Trapp, Robert Peharz, Hong Ge, Franz Pernkopf, Zoubin Ghahramani
NeurIPS 2019poster

Sum-product networks (SPNs) are flexible density estimators and have received significant attention due to their attractive inference properties. While parameter learning in SPNs is well developed, structure learning leaves something to be desired: Even though there is a plethora of SPN structure le…

Cited by 61Source ↗PDF ↗code ↗Scholar ↗
2019

Belief Propagation: Accurate Marginals or Accurate Partition Function – Where is the Difference?

Christian Knoll, Franz Pernkopf
UAI 2019poster

We analyze belief propagation on patch potential models – these are attractive models with varying local potentials – obtain all of the possibly many fixed points, and gather novel insights into belief propagation’s properties. In particular, we observe and theoretically explain several regions in t…

Cited by 12Source ↗PDF ↗Scholar ↗
2018

Resource Efficient Deep Eigenvector Beamforming

Matthias Zöhrer, Lukas Pfeifenberger, Günther Schindler, Holger Fröning, Franz Pernkopf
ICASSP 2018accepted

We propose binary neural networks (BNN s) for acoustic beamforming. This makes the speech enhancement approach resource efficient and applicable for embedded applications. Using CHiME4 data, we use BNN s to estimate the speech presence probability mask for GEV-PAN beamformers. By doing so, we achiev…

Cited by 0Source ↗Scholar ↗
2017

Respiratory airflow estimation from lung sounds based on regression

Elmar Messner, Martin Hagmüller, Paul Swatek, Freyja-Maria Smolle-Jüttner, Franz Pernkopf
ICASSP 2017accepted

The aim of this work is the estimation of respiratory flow from lung sound recordings, i.e. acoustic airflow estimation. With a 16-channel lung sound recording device, we simultaneously record the respiratory flow and the lung sounds on the posterior chest from six lung-healthy subjects in supine po…

Cited by 0Source ↗Scholar ↗
2015

On Theoretical Properties of Sum-Product Networks

Robert Peharz, Sebastian Tschiatschek, Franz Pernkopf, Pedro Domingos
AISTATS 2015poster

Sum-product networks (SPNs) are a promising avenue for probabilistic modeling and have been successfully applied to various tasks. However, some theoretic properties about SPNs are not yet well understood. In this paper we fill some gaps in the theoretic foundation of SPNs. First, we show that the w…

Cited by 147Source ↗PDF ↗Scholar ↗