LILAC: An Idempotent Neural Speech Codec

arXiv:2608.05727 · cs.SD, cs.LG, eess.AS · Submitted 2026-08-06 · Read on arXiv

cs.SD, cs.LG, eess.AS

Submitted: 2026-08-06

Updated: 2026-08-26

Comments: 22 pages, 4 figures

Code: https://github.com/Rick-McCoy/lilac-codec

Project page: https://rick-mccoy.github.io/lilac-demo

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Decoder — 15× in this paper · explained in 2 episodes
• Quantization — 14× in this paper · explained in 15 episodes
• Decode — 11× in this paper · explained in 2 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Coherence — 5× in this paper · explained in 2 episodes
• Fidelity — 5× in this paper · explained in 2 episodes
• Augmentation — 4× in this paper · explained in 2 episodes
• Finite Scalar Quantization — 4× in this paper
• Generalization — 3× in this paper · explained in 14 episodes
• Generator — 3× in this paper · explained in 2 episodes
• Loss Function — 3× in this paper · explained in 2 episodes
• AI Agents — 2× in this paper · explained in 2 episodes
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• In International Conference on Learning Representations — 2× in this paper
• Transformer — 2× in this paper · explained in 2 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Abundance — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Domain Shift — 1× in this paper · explained in 7 episodes
• Equal Error Rate — 1× in this paper
• Evaluation Protocol — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Hinge Loss — 1× in this paper · explained in 2 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Lifting-Inspired Low-rate Audio Codec — 1× in this paper
• Normalizing Flow — 1× in this paper · explained in 4 episodes
• Normalizing Flows — 1× in this paper · explained in 4 episodes
• Pareto Frontier — 1× in this paper · explained in 2 episodes
• Perceptual Evaluation of Speech Quality — 1× in this paper
• Regularization — 1× in this paper · explained in 3 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Transformers — 1× in this paper · explained in 2 episodes
• Wavelet Transform — 1× in this paper · explained in 2 episodes
• Weight Decay — 1× in this paper · explained in 2 episodes

Sources

• High Fidelity Neural Audio Compression
• Moshi: a speech-text foundation model for real-time dialogue
• NICE: Non-linear Independent Components Estimation
• SNAC: Multi-Scale Neural Audio Codec
• BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec

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