New One-Step Speech Enhancement Method Using Drifting Models Outperforms Multi-Step Diffusion Approaches
Researchers have proposed DriftSE, a generative framework that reformulates speech denoising as an equilibrium problem, enabling high-quality enhancement in a single inference step. Unlike conventional diffusion-based methods that require multiple iterative sampling steps, DriftSE uses a learned 'Drifting Field' to guide noisy audio directly toward the clean speech distribution. The approach outperforms multi-step diffusion baselines on a standard benchmark and can train on unpaired data, potentially lowering data collection barriers.
DriftSE (Speech Enhancement based on Drifting Models) is a novel generative framework introduced by Liang Xu and colleagues that recasts the speech denoising problem as an equilibrium problem rather than a sequential denoising process. The core mechanism is a learned correction vector called the Drifting Field, which evolves the pushforward distribution of a mapping function until it matches the clean speech distribution, achieving one-step inference natively without iterative sampling. The authors explore two formulations: a direct mapping from the noisy observation and a stochastic conditional generative model initialized from a Gaussian prior. A notable practical advantage is the framework's ability to train on unpaired noisy-clean data by matching distributions rather than requiring aligned sample pairs, which relaxes a common data requirement in supervised speech enhancement. Experiments on the VoiceBank-DEMAND benchmark show DriftSE achieves high-fidelity results in a single step while surpassing multi-step diffusion-based baselines. The paper is six pages with two figures and has undergone four revisions on arXiv since its initial submission in late April 2026.
What's missing
The paper has not yet undergone formal peer review, as it is a preprint hosted on arXiv.
What different sources said
- arXiv cs.AICenter
Speech Enhancement Based on Drifting Models
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.