Tobias Morocutti — accepted AI-conference papers

2026

Multi-Stage Music Source Restoration with BandSplit-RoFormer Separation and HiFi++ GAN

ICASSP 2026poster

Music Source Restoration (MSR) targets recovery of original, unprocessed instrument stems from fully mixed and mastered audio, where production effects and distribution artifacts violate common linear-mixture assumptions. This technical report presents the CP-JKU team's system for the MSR ICASSP Cha…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Effective Pre-Training of Audio Transformers for Sound Event Detection

Florian Schmid, Tobias Morocutti, Francesco Foscarin, Jan Schlüter, Paul Primus, Gerhard Widmer

ICASSP 2025accepted

We propose a pre-training pipeline for audio spectrogram transformers for frame-level sound event detection tasks. On top of common pre-training steps, we add a meticulously designed training routine on AudioSet frame-level annotations. This includes a balanced sampler, aggressive data augmentation,…

Cited by 0 Source ↗Scholar ↗