# MARS: Sound Generation via Multi-Channel Autoregression on Spectrograms

arXiv: https://arxiv.org/abs/2509.26007 · HTML: https://mlsanity.com/paper/2509.26007/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 27 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Builds on (most cited first, 24 of 24)

- [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)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [Conditional Image Generation with PixelCNN Decoders](https://mlsanity.com/paper/1606.05328/) (2016)
- [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016)
- [AudioLDM: Text-to-Audio Generation with Latent Diffusion Models](https://mlsanity.com/paper/2301.12503/) (2023)
- [Simple and Controllable Music Generation](https://mlsanity.com/paper/2306.05284/) (2023)
- [PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications](https://mlsanity.com/paper/1701.05517/) (2017)
- [Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram](https://mlsanity.com/paper/1910.11480/) (2019)
- [AudioGen: Textually Guided Audio Generation](https://mlsanity.com/paper/2209.15352/) (2022)
- [Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders](https://mlsanity.com/paper/1704.01279/) (2017)
- [DDSP: Differentiable Digital Signal Processing](https://mlsanity.com/paper/2001.04643/) (2020)
- [GANSynth: Adversarial Neural Audio Synthesis](https://mlsanity.com/paper/1902.08710/) (2019)
- [ImageFolder: Autoregressive Image Generation with Folded Tokens](https://mlsanity.com/paper/2410.01756/) (2024)
- [High Fidelity Speech Synthesis with Adversarial Networks](https://mlsanity.com/paper/1909.11646/) (2019)
- [On GANs and GMMs](https://mlsanity.com/paper/1805.12462/) (2018)
- [MelNet: A Generative Model for Audio in the Frequency Domain](https://mlsanity.com/paper/1906.01083/) (2019)
- [Evaluating generative audio systems and their metrics](https://mlsanity.com/paper/2209.00130/) (2022)
- [EDMSound: Spectrogram Based Diffusion Models for Efficient and High-Quality Audio Synthesis](https://mlsanity.com/paper/2311.08667/) (2023)
- [Comparing Representations for Audio Synthesis Using Generative Adversarial Networks](https://mlsanity.com/paper/2006.09266/) (2020)

## Abstract (arXiv)

Research on audio generation has progressively developed along both waveform-based and spectrogram-based directions, giving rise to diverse strategies for representing and generating audio. At the same time, advances in image synthesis have shown that autoregression across scales, rather than tokens, improves coherence and detail. Building on these ideas, we introduce MARS (Multi-channel AutoRegression on Spectrograms), which, to the best of our knowledge, is the first adaptation of next-scale autoregressive modeling to the spectrogram domain. MARS treats spectrograms as multi-channel images and employs channel multiplexing (CMX), a reshaping strategy that reduces spatial resolution without information loss. A shared tokenizer provides consistent discrete representations across scales, enabling a transformer-based autoregressor to refine spectrograms from coarse to fine resolutions efficiently. Experiments on a large-scale dataset demonstrate that MARS performs comparably or better than state-of-the-art baselines across multiple evaluation metrics, establishing an efficient and scalable paradigm for high-fidelity sound generation.