Neural Morphing: Sequence-Optimized Token-Level Morphing in Neural Audio Codecs
Abstract
A training-free audio effect uses sequence matching in neural codec token space to transfer timbral detail while preserving the rhythmic organization of the source.
Type
Publication
Proceedings of the International Conference on Digital Audio Effects
Emmanouil Karystinaios
Senior Machine Learning Engineer and Postdoctoral Researcher
I work in music information retrieval as a Senior Machine Learning Engineer at Muse Group and a part-time Postdoctoral Researcher at Johannes Kepler University Linz.