# Towards Bitrate-Efficient and Noise-Robust Speech Coding with Variable Bitrate RVQ

arXiv: https://arxiv.org/abs/2506.16538 · HTML: https://mlsanity.com/paper/2506.16538/

## Key facts

- Cited by 2 papers in the map (data through 19 Oct 2026).
- First posted on arXiv 19 Jun 2025.

## Built on by (most cited first, 2 of 2)

- [SUNAC: Source-aware Unified Neural Audio Codec](https://mlsanity.com/paper/2511.16126/) (2025)
- [Noisy Environment Adaptation of Neural Speech Codec via Focal Mask and Noise Feature Separation](https://mlsanity.com/paper/2607.04195/) (2026)

## Abstract (arXiv)

Residual Vector Quantization (RVQ) has become a dominant approach in neural speech and audio coding, providing high-fidelity compression. However, speech coding presents additional challenges due to real-world noise, which degrades compression efficiency. Standard codecs allocate bits uniformly, wasting bitrate on noise components that do not contribute to intelligibility. This paper introduces a Variable Bitrate RVQ (VRVQ) framework for noise-robust speech coding, dynamically adjusting bitrate per frame to optimize rate-distortion trade-offs. Unlike constant bitrate (CBR) RVQ, our method prioritizes critical speech components while suppressing residual noise. Additionally, we integrate a feature denoiser to further improve noise robustness. Experimental results show that VRVQ improves rate-distortion trade-offs over conventional methods, achieving better compression efficiency and perceptual quality in noisy conditions. Samples are available at our project page: https://yoongi43.github.io/noise_robust_vrvq/.