AudioCodex: Streaming Autoencoders for Live Audio
cs.SD, cs.LG, eess.AS
Submitted: 2026-11-09
Updated: 2026-11-09
Project page: https://sonycslparis.github.io/audiocodex-companion
Terminology
Sources
- MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training
- Diffusion Transformers with Representation Autoencoders
- Perceptually Aligning Representations of Music via Noise-Augmented Autoencoders
- A Tilted Seesaw: Revisiting Autoencoder Trade-off for Controllable Diffusion
- Streaming Generation for Music Accompaniment
- Latent Granular Resynthesis using Neural Audio Codecs
- Auto-Encoding Variational Bayes
- Mean Flows for One-step Generative Modeling
- Continuous Autoregressive Models with Noise Augmentation Avoid Error Accumulation
- Diffusion Autoencoders are Scalable Image Tokenizers
- Image Generation with a Sphere Encoder
- MusicLM: Generating Music From Text
- Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram
- Improved Mean Flows: On the Challenges of Fastforward Generative Models
- FMA: A Dataset For Music Analysis
- Hi-Fi Multi-Speaker English TTS Dataset
- Cautious Optimizers: Improving Training with One Line of Code
- Adam: A Method for Stochastic Optimization
- Back to Basics: Let Denoising Generative Models Denoise
Related papers
- Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play
- MuLaCover: Flexible Cover Song Generation via Symbolic Tonal Control
- Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning
- 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