Speech Enhancement Based on Drifting Models
We propose Speech Enhancement based on Drifting Models (DriftSE), a novel generative framework that formulates denoising as an equilibrium problem. Rather than relying on iterative sampling, DriftSE natively achieves one-step inference by evolving the pushforward distribution of a mapping function to directly match the clean speech distribution. This evolution is driven by a Drifting Field, a learned correction vector that guides samples toward the high-density regions of the clean distribution, which naturally facilitates training on unpaired data by matching distributions rather than paired samples. We investigate the framework under two formulations: a direct mapping from the noisy observation, and a stochastic conditional generative model from a Gaussian prior. Experiments on the VoiceBank-DEMAND benchmark demonstrate that DriftSE achieves high-fidelity enhancement in a single step, outperforming multi-step diffusion baselines and establishing a new paradigm for speech enhancement.
Code (0)
등록된 구현이 없습니다.
Tasks
Speech EnhancementSimilar Papers 제목 키워드 기반
Fast-ULCNet: A fast and ultra low complexity network for single-channel speech enhancement
Single-channel speech enhancement algorithms are often used in resource-constrained embedded devices, where low latency and low complexity designs gain more importance. In recent years, researchers have proposed a wide v…
Speech EnhancementPlugin Speech Enhancement: A Universal Speech Enhancement Framework Inspired by Dynamic Neural Network
The expectation to deploy a universal neural network for speech enhancement, with the aim of improving noise robustness across diverse speech processing tasks, faces challenges due to the existing lack of awareness withi…
Data AugmentationSpeech EnhancementTime-Domain Speech Enhancement for Robust Automatic Speech Recognition
It has been shown that the intelligibility of noisy speech can be improved by speech enhancement algorithms. However, speech enhancement has not been established as an effective frontend for robust automatic speech recog…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Speech Enhancementspeech-recognition+1Phoneme-based Distribution Regularization for Speech Enhancement
Existing speech enhancement methods mainly separate speech from noises at the signal level or in the time-frequency domain. They seldom pay attention to the semantic information of a corrupted signal. In this paper, we a…
Speech EnhancementInvestigating self-supervised learning for speech enhancement and separation
Speech enhancement and separation are two fundamental tasks for robust speech processing. Speech enhancement suppresses background noise while speech separation extracts target speech from interfering speakers. Despite a…
Self-Supervised LearningSpeech EnhancementSpeech Separation