# Speech enhancement and noise suppression

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

## Key facts

- Speech enhancement and noise suppression: 892 papers on arXiv since 2021 (data through 19 Oct 2026).
- 148 of its 892 mapped papers (17%) cite “Speech Enhancement and Dereverberation with Diffusion-based Generative Models” (2022, arXiv 2208.05830).
- 123 of its 892 mapped papers (14%) cite “MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement” (2021, arXiv 2104.03538).
- 6 new papers 2 Oct–19 Oct.

## Most cited here

- [Speech Enhancement and Dereverberation with Diffusion-based Generative Models](https://mlsanity.com/paper/2208.05830/) (2022), cited by 148 papers here
- [MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement](https://mlsanity.com/paper/2104.03538/) (2021), cited by 123 papers here
- [Conditional Diffusion Probabilistic Model for Speech Enhancement](https://mlsanity.com/paper/2202.05256/) (2022), cited by 117 papers here
- [StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation](https://mlsanity.com/paper/2212.11851/) (2022), cited by 102 papers here
- [Speech Enhancement with Score-Based Generative Models in the Complex STFT Domain](https://mlsanity.com/paper/2203.17004/) (2022), cited by 75 papers here
- [MP-SENet: A Speech Enhancement Model with Parallel Denoising of Magnitude and Phase Spectra](https://mlsanity.com/paper/2305.13686/) (2023), cited by 62 papers here
- [CMGAN: Conformer-based Metric GAN for Speech Enhancement](https://mlsanity.com/paper/2203.15149/) (2022), cited by 57 papers here
- [Universal Speech Enhancement with Score-based Diffusion](https://mlsanity.com/paper/2206.03065/) (2022), cited by 55 papers here
- [An Investigation of Incorporating Mamba for Speech Enhancement](https://mlsanity.com/paper/2405.06573/) (2024), cited by 55 papers here
- [TSTNN: Two-stage Transformer based Neural Network for Speech Enhancement in the Time Domain](https://mlsanity.com/paper/2103.09963/) (2021), cited by 45 papers here

## New (2 Oct–19 Oct)

- [Rethinking Batch Composition: Promoting Feature Diversity for Speech Enhancement](https://mlsanity.com/paper/2610.21803/) (2026-10-15)
- [CF-AVSS: A Coarse-to-Fine Audio-Visual Speech Separation Framework with Target-Speaker Refinement and Post-Fusion for Real-World AVSE Challenge](https://mlsanity.com/paper/2610.21773/) (2026-10-15)
- [Spiking Neural Beamforming for Multichannel Speech Enhancement on the Edge](https://mlsanity.com/paper/2610.16430/) (2026-10-12)
- [Efficient Audio-Visual Speech Enhancement via Reinforcement Learning-Based Neural Architecture Search](https://mlsanity.com/paper/2610.12796/) (2026-10-08)
- [LIFT-SE: Linguistic Inference Followed by Flow Transformation for Generative Speech Enhancement](https://mlsanity.com/paper/2610.09963/) (2026-10-07)
- [UltraM2M: Leveraging Text Transcripts and Mixture Constraints for Weakly-Supervised Speech Enhancement](https://mlsanity.com/paper/2610.05155/) (2026-10-04)