# High-quality speech coding with SampleRNN

arXiv: https://arxiv.org/abs/1811.03021 · HTML: https://mlsanity.com/paper/1811.03021/

## Key facts

- Cited by 14 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 7 Nov 2018.

## Built on by (most cited first, 14 of 14)

- [Boomerang: Local sampling on image manifolds using diffusion models](https://mlsanity.com/paper/2210.12100/) (2022)
- [FlowDec: A flow-based full-band general audio codec with high perceptual quality](https://mlsanity.com/paper/2503.01485/) (2025)
- [Disentangled Feature Learning for Real-Time Neural Speech Coding](https://mlsanity.com/paper/2211.11960/) (2022)
- [Weight, Block or Unit? Exploring Sparsity Tradeoffs for Speech Enhancement on Tiny Neural Accelerators](https://mlsanity.com/paper/2111.02351/) (2021)
- [End-to-End Neural Speech Coding for Real-Time Communications](https://mlsanity.com/paper/2201.09429/) (2022)
- [Latent-Domain Predictive Neural Speech Coding](https://mlsanity.com/paper/2207.08363/) (2022)
- [A Streamwise GAN Vocoder for Wideband Speech Coding at Very Low Bit Rate](https://mlsanity.com/paper/2108.04051/) (2021)
- [Ultra-Low-Bitrate Speech Coding with Pretrained Transformers](https://mlsanity.com/paper/2207.02262/) (2022)
- [Gull: A Generative Multifunctional Audio Codec](https://mlsanity.com/paper/2404.04947/) (2024)
- [Cross-Scale Vector Quantization for Scalable Neural Speech Coding](https://mlsanity.com/paper/2207.03067/) (2022)
- [PSCodec: A Series of High-Fidelity Low-bitrate Neural Speech Codecs Leveraging Prompt Encoders](https://mlsanity.com/paper/2404.02702/) (2024)
- [Audio Decoding by Inverse Problem Solving](https://mlsanity.com/paper/2409.07858/) (2024)
- [Low Bit-Rate Wideband Speech Coding: A Deep Generative Model based Approach](https://mlsanity.com/paper/2102.02640/) (2021)
- [Learning source-aware representations of music in a discrete latent space](https://mlsanity.com/paper/2111.13321/) (2021)

## Abstract (arXiv)

We provide a speech coding scheme employing a generative model based on SampleRNN that, while operating at significantly lower bitrates, matches or surpasses the perceptual quality of state-of-the-art classic wide-band codecs. Moreover, it is demonstrated that the proposed scheme can provide a meaningful rate-distortion trade-off without retraining. We evaluate the proposed scheme in a series of listening tests and discuss limitations of the approach.