# Spectrogram Patch Codec: A 2D Block-Quantized VQ-VAE and HiFi-GAN for Neural Speech Coding

arXiv: https://arxiv.org/abs/2509.02244 · HTML: https://mlsanity.com/paper/2509.02244/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 15 references that are in the map.
- First posted on arXiv 2 Sep 2025.

## Builds on (most cited first, 11 of 11)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation](https://mlsanity.com/paper/2406.06525/) (2024)
- [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)
- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [ViSQOL v3: An Open Source Production Ready Objective Speech and Audio Metric](https://mlsanity.com/paper/2004.09584/) (2020)
- [SNAC: Multi-Scale Neural Audio Codec](https://mlsanity.com/paper/2410.14411/) (2024)

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

- [SoundBreak: A Systematic Study of Audio-Only Adversarial Attacks on Trimodal Models](https://mlsanity.com/paper/2601.16231/) (2026)
- [LatinX: Aligning a Multilingual TTS Model with Direct Preference Optimization](https://mlsanity.com/paper/2509.05863/) (2025)

## Abstract (arXiv)

We present a neural speech codec that challenges the need for complex residual vector quantization (RVQ) stacks by introducing a simpler, single-stage quantization approach. Our method operates directly on the mel-spectrogram, treating it as a 2D data and quantizing non-overlapping 4x4 patches into a single, shared codebook. This patchwise design simplifies the architecture, enables low-latency streaming, and yields a discrete latent grid. To ensure high-fidelity synthesis, we employ a late-stage adversarial fine-tuning for the VQ-VAE and train a HiFi-GAN vocoder from scratch on the codec's reconstructed spectrograms. Operating at approximately 7.5 kbits/s for 16 kHz speech, our system was evaluated against several state-of-the-art neural codecs using objective metrics such as STOI, PESQ, MCD, and ViSQOL. The results demonstrate that our simplified, non-residual architecture achieves competitive perceptual quality and intelligibility, validating it as an effective and open foundation for future low-latency codec designs.