ISAC: An Invertible and Stable Auditory Filter Bank with Customizable Kernels for ML Integration

Daniel Haider, Felix Perfler, Peter Balazs, Clara Hollomey, Nicki Holighaus

Proceeding of the IEEE International Conference on Sampling Theory and Applications (SampTA), 2025, Vienna

[Paper] [Code]

Parametric model of the human pinna based on Bézier curves and concave deformations

Felix Perfler, Florian Pausch, Katharina Pollack, Nicki Holighaus, and Piotr Majdak

Computers in Biology and Medicine, Volume 188, April 2025, 109817.

[Paper] doi:10.1016/j.compbiomed.2025.109817

Hold Me Tight: Stable Encoder–Decoder Design for Speech Enhancement

Daniel Haider, Felix Perfler, Vincent Lostanlen, Martin Ehler, Peter Balazs

Proceedings of the Interspeech, 2024, Kos.

[Paper] [Code] doi:10.21437/Interspeech.2024-1622

Trainable signal encoders that are robust against noise

Peter Balazs, Daniel Haider, Vincent Lostanlen, Felix Perfler

Proceedings of the Inter-Noise, 2024, Nantes.

[Paper] hal-04697953

Concepts for the evaluation of a parametric pinna model

Felix Perfler, Piotr Majdak, Florian Pausch, Katharina Pollack

Proceedings of the Forum Acusticum, 2023, Turin.

doi:10.61782/fa.2023.1072

Comparison of deep-neural-network architectures for the prediction of head-related transfer functions using a parametric pinna model

Florian Pausch, Felix Perfler, Nicki Holighaus, Piotr Majdak

Proceedings of the Forum Acusticum, 2023, Turin.

doi:10.61782/fa.2023.0795