# Quantizer Redundancy and Exact Index Recoding in a Frozen Neural Audio Codec

arXiv: https://arxiv.org/abs/2610.20471 · HTML: https://mlsanity.com/paper/2610.20471/

## Key facts

- No citing papers in the map yet (data through 19 Oct 2026).
- Builds on 10 of its 15 references that are in the map.
- First posted on arXiv 14 Oct 2026.

## Placed in

- Speech and audio language models

## Builds on (most cited first, 10 of 10)

- [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)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [Finite Scalar Quantization: VQ-VAE Made Simple](https://mlsanity.com/paper/2309.15505/) (2023)
- [Scaling Transformers for Low-Bitrate High-Quality Speech Coding](https://mlsanity.com/paper/2411.19842/) (2024)
- [Robust Residual Finite Scalar Quantization for Neural Compression](https://mlsanity.com/paper/2508.15860/) (2025)
- [MLVC: Multi-platform Learned Video Codec for Real-World Deployment](https://mlsanity.com/paper/2606.28027/) (2026)
- [Benchmarking Neural Speech Compression from a Rate-Distortion Perspective](https://mlsanity.com/paper/2606.11631/) (2026)
- [Opportunistic Conditional Entropy Coding with Frozen Analysis and Synthesis Transforms](https://mlsanity.com/paper/2609.21816/) (2026)

## Abstract (arXiv)

Residual scalar quantization can produce highly dependent indices when successive stages reuse identical, unscaled grids. This case study examines that behavior in a frozen neural audio codec and develops an exact recoding procedure that reduces storage while preserving its decoder inputs. Analysis of the repeated-grid recurrence identifies predictable stage sequences; finite-precision checks motivate preserving every original index through explicit exception records. The model weights and reconstruction graph remain fixed. On the studied 62- and 512-file cohorts, a predictor, adaptive coding and explicit file selection reduce complete stored bytes. The final 512-file rate is 129.591 kbps including headers, 25.943% below an original-index XZ control. Original recorded CPU runs establish bitwise latent and waveform preservation; independent readers verify exact index and metadata recovery in subsequent saved-stream experiments. Later coding choices use previously studied cohorts, and fresh encoding requires generating three alternatives. The engineering result is implementation-specific storage reduction with exact index recovery; the underlying lossy reconstruction quality remains unchanged.