← Search

Michael Ungersböck

2 accepted papers

2025

High-Fidelity Music Vocoder using Neural Audio Codecs

ICASSP 2025accepted

While neural vocoders have made significant progress in high-fidelity speech synthesis, their application on polyphonic music has remained underexplored. In this work, we propose DisCoder, a neural vocoder that leverages a generative adversarial encoder-decoder architecture informed by a neural audi…

Cited by 0SourceScholar
2025

SAO-Instruct: Free-form Audio Editing using Natural Language Instructions

NeurIPS 2025poster

Generative models have made significant progress in synthesizing high-fidelity audio from short textual descriptions. However, editing existing audio using natural language has remained largely underexplored. Current approaches either require the complete description of the edited audio or are const…

Cited by 0SourceScholar