# Neural Vocoders as Speech Enhancers

arXiv: https://arxiv.org/abs/2501.13465 · HTML: https://mlsanity.com/paper/2501.13465/

## Key facts

- Cited by 3 papers in the map (data through 19 Oct 2026).
- Placed in Speech enhancement and noise suppression, one of 11 directions in Speech and audio language models.
- First posted on arXiv 23 Jan 2025.

## Placed in

- Speech and audio language models / [Speech enhancement and noise suppression](https://mlsanity.com/speech/speech-enhancement-and-noise-suppression/)

## Built on by (most cited first, 3 of 3)

- [FNSE-SBGAN: Far-field Speech Enhancement with Schrodinger Bridge and Generative Adversarial Networks](https://mlsanity.com/paper/2503.12936/) (2025)
- [BridgeVoC: Revitalizing Neural Vocoder from a Restoration Perspective](https://mlsanity.com/paper/2511.07116/) (2025)
- [PhaseGAN: High-Fidelity Vocoder via Decoupled Amplitude and GAN-Driven Phase Reconstruction](https://mlsanity.com/paper/2609.12918/) (2026)

## Abstract (arXiv)

Speech enhancement (SE) and neural vocoding are traditionally viewed as separate tasks. In this work, we observe them under a common thread: the rank behavior of these processes. This observation prompts two key questions: textitCan a model designed for one task's rank degradation be adapted for the other? and textitIs it possible to address both tasks using a unified model? Our empirical findings demonstrate that existing speech enhancement models can be successfully trained to perform vocoding tasks, and a single model, when jointly trained, can effectively handle both tasks with performance comparable to separately trained models. These results suggest that speech enhancement and neural vocoding can be unified under a broader framework of speech restoration. Code: https://github.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers.