Ednet: A Versatile Speech Enhancement Framework With Gating Mamba Mechanism And Phase Shift-invariant Training

Abstract

Speech signals in real-world environments are frequently affected by various distortions such as additive noise, reverberation, and bandwidth limitation, which may appear individually or in combination. Traditional speech enhancement methods typically rely on either masking, which focuses on suppressing non-speech components while preserving observable structure, or mapping, which seeks to recover clean speech through direct transformation of the input. Each approach offers strengths in specific scenarios but may be less effective outside its target conditions. We propose the Erase and Draw Network (EDNet), a versatile speech enhancement framework designed to handle a broad range of distortion types without prior assumptions about task or input characteristics. EDNet consists of two main components: (1) the Gating Mamba (GM) module, which adaptively combines masking and mapping through a learnable gating mechanism that selects between suppression (Erase) and reconstruction (Draw) based

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykwak2025ednet

Related papers

• Dbnet: A Dual-branch Network Architecture Processing On Spectrum And Waveform For Single-channel Speech Enhancement (2021)8.09
• Parallel Gated Neural Network With Attention Mechanism For Speech Enhancement (2022)0.00
• Mp-senet: A Speech Enhancement Model With Parallel Denoising Of Magnitude And Phase Spectra (2023)15.51
• Do We Need EMA For Diffusion-based Speech Enhancement? Toward A Magnitude-preserving Network Architecture (2025)0.00
• Explicit Estimation Of Magnitude And Phase Spectra In Parallel For High-quality Speech Enhancement (2023)11.19
• A Multiscale Autoencoder (MSAE) Framework For End-to-end Neural Network Speech Enhancement (2023)6.34
• Towards Generalized Speech Enhancement With Generative Adversarial Networks (2019)10.35
• Cheapnet: Improving Light-weight Speech Enhancement Network By Projected Loss Function (2023)0.00