Feature Encoding in VAE-based Audio Decoders: Effects of Input, Depth and Distribution
cs.SD, cs.LG
Submitted: 2026-10-06
Updated: 2026-10-06
Code: https://github.com/Louismac/rave-activations
Sources
- RAVE: A variational autoencoder for fast and high-quality neural audio synthesis
- Music Transformer
- A Large-Scale Probing Analysis of Speaker-Specific Attributes in Self-Supervised Speech Representations
- AudioLM: a Language Modeling Approach to Audio Generation
- Understanding intermediate layers using linear classifier probes
- Neural Activation Patterns (NAPs): Visual Explainability of Learned Concepts
- Streamable Neural Audio Synthesis With Non-Causal Convolutions
- DiffWave: A Versatile Diffusion Model for Audio Synthesis
- ACE-Step: A Step Towards Music Generation Foundation Model
Related papers
- Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
- Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
- Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems
- Harmonic Representations in Symbolic Music Transformers are Localized and Controllable
- AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
- SoundWeaver: Compositional Warm-Starting for Text-to-Audio Diffusion Serving