Peter Balazs
Role at IT:U:
As a Fellow Professor of Acoustics, Analysis, and AI (3AI) at IT:U, Peter Balazs is actively engaged in research at the IT:U Sound and Acoustics Lab and collaborates with the ARI Lab at the ÖAW. His work focuses on harmonic analysis, signal processing, and machine learning, contributing to advanced models in acoustics.
Research group:
The Acoustics, Analysis & AI (3AI) group at the IT:U Austria in Linz explores how mathematics, acoustics, and artificial intelligence can work together. We study interpretable, hybrid AI systems for sound analysis—combining deep learning with mathematical structure and human insight. Our research ranges from signal processing and hearing models to bioacoustics and mathematical foundations, aiming to bridge human and machine understanding of acoustic phenomena.
Short bio:
Peter Balazs is the Director of the Acoustics Research Institute at the ÖAW. He possesses extensive expertise in acoustics, signal processing, and mathematical methods. His research has led to significant contributions to frame theory and time-frequency analysis, with applications in numerical acoustics, mathematical physics, psychoacoustics and bioacoustics.
His vision is bridging (deep theoretical) mathematics to more applied scientific topics. He has long been passionately committed to application-oriented mathematics for acoustics, signal-processing and machine learning. This commitment was already evident in 2011, when his project Frames and Linear Operators for Acoustical Modeling and Parameter Estimation was awarded the prestigious START Prize.
His interdisciplinary work integrates mathematical models with acoustic applications, as demonstrated in current projects such as Frames and Time-Frequency Analysis in Machine Learning or Decoding Elephant Communication with AI.
His extensive experience in teaching and supervision, his ability to present complex theoretical concepts in an accessible applied way significantly enriches the academic environment at IT:U. His affiliation with the Austrian Academy of Sciences and his active involvement in international scientific organization – he currently serves the treasurer of the International Commission for Acoustics, e.g. – further strengthen research and mentorship at IT:U.
“My vision is bridging (deep theoretical) mathematics to more applied scientific topics. I am passionately committed to application-oriented mathematics for acoustics, signal-processing and machine learning. This allows the full usage of mathematical rigor and controllability of parameters for models and methods in the applied sciences on one hand. On the other hand, this creates new mathematical topics and concepts, raises novel questions within mathematics that are interesting and inspiring per-se”.
Peter Balazs
Potential Projects
Potential Master and Off-Lab Projects:
- Building a 3D Audio Recorder from scratch
- Building a 3D Audio Sound system from scratch
- Building a Measurement System for HRTFs from scratch
- Improve 3D Audio in other IT-U labs
- Build an Audiometry (from scratch)
- Do a sub-project of PhD projects focusing on certain details, e.g.
Development of bioacoustics and movement monitoring collar mounted sensors for African Savannah elephants (Loxodonta Africana) – MSc thesis project
Supervision: Prof. Dr. Peter Balazs & Prof. Dr. Angela Stöger
Co-supervision: Dr. Daniel Haider & Jure Železnik
Collar-mounted wildlife sensors enable continuous, minimally invasive monitoring of behavior, habitat use, and inter-individual acoustic communication. Yet, attributing specific vocalizations to the correct individual in free-ranging groups remains challenging when audio is collected without tightly synchronized motion and position data. The candidate in this project will design and prototype a field-ready elephant collar that integrates wide-band acoustic recording, high-rate tri-axial accelerometery (X/Y/Z), and GPS positioning in a time-synchronized, low-power package. The system will feature precise clocking and sensor fusion pipelines so that subtle body movements and collar vibrations can be aligned with acoustic onsets, while GPS trajectories provide spatial constraints, together enabling robust focal-caller attribution. Emphasis will be placed on the ability to detect focal callers as well as power budgeting for longer deployments, rugged enclosure and microphone placement to minimize environmental noise, and serviceable data logging. The outcome will be a validated hardware prototype with open documentation, calibration and synchronization procedures, and a thesis evaluating focal-caller detection accuracy from combined sensors versus audio-only baselines.
Development of sound event annotating tool with incorporated few-shot and active learning – MSc thesis project
Supervision: Prof. Dr. Peter Balazs & Prof. Dr. Angela Stöger
Co-supervision: Dr. Daniel Haider & Jure Železnik
The use of long-term autonomous recorders has been steadily increasing over the past few decades in the field of bioacoustics. This means that wildlife researchers and bioacousticians are collecting thousands of hours of recordings, after which they manually extract sound events of their interest. Although the development and use of machine learning algorithms for automatic sound event extraction and analysis are promising, these generally only work well on large well-defined curated datasets with previously identified sounds events that can be used for training and validating. To make this available to the dataset at hand, the candidate in this project will design and prototype a modern annotation platform for audio and bioacoustics research that can couple an intuitive labelling UI with state-of-the-art machine learning. The tool will provide waveform/spectrogram views, rapid keyboard/mouse labelling, and flexible schema management, facilitating few-shot learners to “cold-start” models from just a handful of examples per class. An active-learning loop will continuously surface the most informative or uncertain clips for review, maximizing annotation efficiency and model quality with minimal human effort. Emphasis will be placed on the development of a tool which can be used for wildlife monitoring and/or environmental soundscape analysis. The outcome will be a usable, extensible open-source tool, and a thesis evaluating gains in labelling speed/accuracy versus conventional workflows.
