3 papers
cs.SD2025
Désentrelacement Fréquentiel Doux pour les Codecs Audio Neuronaux
Benoît Giniès, Xiaoyu Bie, Olivier Fercoq +1
While neural-based models have led to significant advancements in audio feature extraction, the interpretability of the learned representations remains a critical challenge. To add…
cs.SD2025
Soft Disentanglement in Frequency Bands for Neural Audio Codecs
Benoit Ginies, Xiaoyu Bie, Olivier Fercoq +1
In neural-based audio feature extraction, ensuring that representations capture disentangled information is crucial for model interpretability. However, existing disentanglement me…
cs.SD2025
Diff-TONE: Timestep Optimization for iNstrument Editing in Text-to-Music Diffusion Models
Teysir Baoueb, Xiaoyu Bie, Xi Wang +1
Breakthroughs in text-to-music generation models are transforming the creative landscape, equipping musicians with innovative tools for composition and experimentation like never b…