# Variable Bitrate Residual Vector Quantization for Audio Coding

arXiv: https://arxiv.org/abs/2410.06016 · HTML: https://mlsanity.com/paper/2410.06016/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 28 references that are in the map.
- First posted on arXiv 8 Oct 2024.

## Builds on (most cited first, 16 of 16)

- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [Vector-quantized Image Modeling with Improved VQGAN](https://mlsanity.com/paper/2110.04627/) (2021)
- [Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks](https://mlsanity.com/paper/1602.07868/) (2016)
- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [Conditional Probability Models for Deep Image Compression](https://mlsanity.com/paper/1801.04260/) (2018)
- [Neural Networks Fail to Learn Periodic Functions and How to Fix It](https://mlsanity.com/paper/2006.08195/) (2020)
- [ViSQOL v3: An Open Source Production Ready Objective Speech and Audio Metric](https://mlsanity.com/paper/2004.09584/) (2020)
- [Learning Convolutional Networks for Content-weighted Image Compression](https://mlsanity.com/paper/1703.10553/) (2017)
- [ICASSP 2022 Deep Noise Suppression Challenge](https://mlsanity.com/paper/2202.13288/) (2022)
- [Learning Content-Weighted Deep Image Compression](https://mlsanity.com/paper/1904.00664/) (2019)
- [Variable-rate discrete representation learning](https://mlsanity.com/paper/2103.06089/) (2021)
- [Selective compression learning of latent representations for variable-rate image compression](https://mlsanity.com/paper/2211.04104/) (2022)

## Built on by (most cited first, 6 of 6)

- [Recent Advances in Discrete Speech Tokens: A Review](https://mlsanity.com/paper/2502.06490/) (2025)
- [Unlocking Temporal Flexibility: Neural Speech Codec with Variable Frame Rate](https://mlsanity.com/paper/2505.16845/) (2025)
- [Large Speech Model Enabled Semantic Communication](https://mlsanity.com/paper/2512.04711/) (2025)
- [Elastic Time: Dynamic Frame Rate Bottlenecks for Neural Audio Coding](https://mlsanity.com/paper/2606.27320/) (2026)
- [Towards a Densing Law for User Representation Learning at Billion-Scale Capacity](https://mlsanity.com/paper/2608.23392/) (2026)
- [TokenMapper: A Step Toward Interoperable Speech Token Translation](https://mlsanity.com/paper/2609.12563/) (2026)

## Abstract (arXiv)

Recent state-of-the-art neural audio compression models have progressively adopted residual vector quantization (RVQ). Despite this success, these models employ a fixed number of codebooks per frame, which can be suboptimal in terms of rate-distortion tradeoff, particularly in scenarios with simple input audio, such as silence. To address this limitation, we propose variable bitrate RVQ (VRVQ) for audio codecs, which allows for more efficient coding by adapting the number of codebooks used per frame. Furthermore, we propose a gradient estimation method for the non-differentiable masking operation that transforms from the importance map to the binary importance mask, improving model training via a straight-through estimator. We demonstrate that the proposed training framework achieves superior results compared to the baseline method and shows further improvement when applied to the current state-of-the-art codec.