# DriftSE: Speech Enhancement with Generative Drifting

arXiv: https://arxiv.org/abs/2609.12252 · HTML: https://mlsanity.com/paper/2609.12252/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 46 of its 65 references that are in the map.
- First posted on arXiv 10 Sep 2026.

## Builds on (most cited first, 30 of 46)

- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition](https://mlsanity.com/paper/1912.10211/) (2019)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [BEATs: Audio Pre-Training with Acoustic Tokenizers](https://mlsanity.com/paper/2212.09058/) (2022)
- [Layer-wise Analysis of a Self-supervised Speech Representation Model](https://mlsanity.com/paper/2107.04734/) (2021)
- [NeMo: a toolkit for building AI applications using Neural Modules](https://mlsanity.com/paper/1909.09577/) (2019)
- [Supervised Speech Separation Based on Deep Learning: An Overview](https://mlsanity.com/paper/1708.07524/) (2017)
- [Speech Enhancement and Dereverberation with Diffusion-based Generative Models](https://mlsanity.com/paper/2208.05830/) (2022)
- [NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets](https://mlsanity.com/paper/2104.09494/) (2021)
- [SEGAN: Speech Enhancement Generative Adversarial Network](https://mlsanity.com/paper/1703.09452/) (2017)
- [WHAM!: Extending Speech Separation to Noisy Environments](https://mlsanity.com/paper/1907.01160/) (2019)
- [DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT](https://mlsanity.com/paper/2110.01900/) (2021)
- [The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results](https://mlsanity.com/paper/2005.13981/) (2020)
- [Pyroomacoustics: A Python package for audio room simulations and array processing algorithms](https://mlsanity.com/paper/1710.04196/) (2017)
- [Generative Modeling via Drifting](https://mlsanity.com/paper/2602.04770/) (2026)
- [MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement](https://mlsanity.com/paper/2104.03538/) (2021)
- [StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation](https://mlsanity.com/paper/2212.11851/) (2022)
- [QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions](https://mlsanity.com/paper/1910.10261/) (2019)
- [EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation](https://mlsanity.com/paper/2406.06185/) (2024)
- [HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement](https://mlsanity.com/paper/2203.13086/) (2022)
- [TF-GridNet: Making Time-Frequency Domain Models Great Again for Monaural Speaker Separation](https://mlsanity.com/paper/2209.03952/) (2022)
- [Raw Waveform-based Speech Enhancement by Fully Convolutional Networks](https://mlsanity.com/paper/1703.02205/) (2017)

## Abstract (arXiv)

We propose DriftSE, a novel one-step generative framework for speech enhancement formulated as a latent distribution equilibrium problem. During training, the drifting field aligns the generator's pushforward distribution with the clean speech manifold through drifting in a latent domain. During inference, the drifting process is discarded, enabling one-step generation. We establish that its enhancement quality depends fundamentally on the choice of latent representation. Semantic latents preserve phonetic structure but fail to capture physical acoustic cues, whereas acoustic latents reconstruct the physical signal but risk linguistic hallucination. Therefore, we introduce dual-latent drifting, performing parallel drifting in both semantic and acoustic latents to simultaneously preserve phonetic intelligibility and acoustic fidelity. Additionally, we demonstrate that DriftSE enables fully unpaired training by aligning latent distributions rather than exact point-wise targets. Consequently, DriftSE facilitates cross-dataset learning in the absence of paired noisy-clean samples. Moreover, DriftSE exhibits broad architectural flexibility across different generator backbones. Extensive evaluations on additive denoising and convolutive dereverberation demonstrate robust one-step enhancement across both offline and real-time causal settings. Notably, DriftSE achieves state-of-the-art word error rates across all four evaluated datasets while strictly operating at 1 NFE. Code and audio examples are available online.