# ArtiFree: Detecting and Reducing Generative Artifacts in Diffusion-based Speech Enhancement

arXiv: https://arxiv.org/abs/2509.19495 · HTML: https://mlsanity.com/paper/2509.19495/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 23 Sep 2025.

## Builds on (most cited first, 13 of 13)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Speech Enhancement and Dereverberation with Diffusion-based Generative Models](https://mlsanity.com/paper/2208.05830/) (2022)
- [DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement](https://mlsanity.com/paper/2008.00264/) (2020)
- [StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation](https://mlsanity.com/paper/2212.11851/) (2022)
- [Speech Enhancement with Score-Based Generative Models in the Complex STFT Domain](https://mlsanity.com/paper/2203.17004/) (2022)
- [An Investigation of Incorporating Mamba for Speech Enhancement](https://mlsanity.com/paper/2405.06573/) (2024)
- [PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Network](https://mlsanity.com/paper/1911.04697/) (2019)
- [Diffusion Models for Audio Restoration](https://mlsanity.com/paper/2402.09821/) (2024)
- [Schr"odinger Bridge for Generative Speech Enhancement](https://mlsanity.com/paper/2407.16074/) (2024)
- [Investigating Training Objectives for Generative Speech Enhancement](https://mlsanity.com/paper/2409.10753/) (2024)
- [Lost in Transcription, Found in Distribution Shift: Demystifying Hallucination in Speech Foundation Models](https://mlsanity.com/paper/2502.12414/) (2025)
- [Diffusion-based Speech Enhancement with Schr"odinger Bridge and Symmetric Noise Schedule](https://mlsanity.com/paper/2409.05116/) (2024)
- [On the Behavior of Intrusive and Non-intrusive Speech Enhancement Metrics in Predictive and Generative Settings](https://mlsanity.com/paper/2306.03014/) (2023)

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

- [Predictive-Generative Drift Decomposition for Speech Enhancement and Separation](https://mlsanity.com/paper/2605.06189/) (2026)
- [Transcript-Supervised Post-Training of Generative Speech Enhancement on Real Recordings via Reinforce Adjoint Matching](https://mlsanity.com/paper/2609.29405/) (2026)

## Abstract (arXiv)

Diffusion-based speech enhancement (SE) achieves natural-sounding speech and strong generalization, yet suffers from key limitations like generative artifacts and high inference latency. In this work, we systematically study artifact prediction and reduction in diffusion-based SE. We show that variance in speech embeddings can be used to predict phonetic errors during inference. Building on these findings, we propose an ensemble inference method guided by semantic consistency across multiple diffusion runs. This technique reduces WER by 15% in low-SNR conditions, effectively improving phonetic accuracy and semantic plausibility. Finally, we analyze the effect of the number of diffusion steps, showing that adaptive diffusion steps balance artifact suppression and latency. Our findings highlight semantic priors as a powerful tool to guide generative SE toward artifact-free outputs.