English

PURE Codec: Progressive Unfolding of Residual Entropy for Speech Codec Learning

Sound 2025-12-01 v1 Audio and Speech Processing

Abstract

Neural speech codecs have achieved strong performance in low-bitrate compression, but residual vector quantization (RVQ) often suffers from unstable training and ineffective decomposition, limiting reconstruction quality and efficiency. We propose PURE Codec (Progressive Unfolding of Residual Entropy), a novel framework that guides multi-stage quantization using a pre-trained speech enhancement model. The first quantization stage reconstructs low-entropy, denoised speech embeddings, while subsequent stages encode residual high-entropy components. This design improves training stability significantly. Experiments demonstrate that PURE consistently outperforms conventional RVQ-based codecs in reconstruction and downstream speech language model-based text-to-speech, particularly under noisy training conditions.

Keywords

Cite

@article{arxiv.2511.22687,
  title  = {PURE Codec: Progressive Unfolding of Residual Entropy for Speech Codec Learning},
  author = {Jiatong Shi and Haoran Wang and William Chen and Chenda Li and Wangyou Zhang and Jinchuan Tian and Shinji Watanabe},
  journal= {arXiv preprint arXiv:2511.22687},
  year   = {2025}
}

Comments

Accepted by ASRU2025

R2 v1 2026-07-01T07:58:28.036Z