Magnitude-phase Dual-path Speech Enhancement Network Based On Self-supervised Embedding And Perceptual Contrast Stretch Boosting

Abstract

Speech self-supervised learning (SSL) has made great progress in various speech processing tasks, but there is still room for improvement in speech enhancement (SE). This paper presents BSP-MPNet, a dual-path framework that combines self-supervised features with magnitude-phase information for SE. The approach starts by applying the perceptual contrast stretching (PCS) algorithm to enhance the magnitude-phase spectrum. A magnitude-phase 2D coarse (MP-2DC) encoder then extracts coarse features from the enhanced spectrum. Next, a feature-separating self-supervised learning (FS-SSL) model generates self-supervised embeddings for the magnitude and phase components separately. These embeddings are fused to create cross-domain feature representations. Finally, two parallel RNN-enhanced multi-attention (REMA) mask decoders refine the features, apply them to the mask, and reconstruct the speech signal. We evaluate BSP-MPNet on the VoiceBank+DEMAND and WHAMR! datasets. Experimental results show

Stats

• citations1
• S2 citations—
• github stars2
• HF likes0
• heat score3.21
• arxiv keymattursun2025magnitude

Related papers

• Mp-senet: A Speech Enhancement Model With Parallel Denoising Of Magnitude And Phase Spectra (2023)15.51
• Explicit Estimation Of Magnitude And Phase Spectra In Parallel For High-quality Speech Enhancement (2023)11.19
• Magnitude-and-phase-aware Speech Enhancement With Parallel Sequence Modeling (2023)3.58
• BSS-CFFMA: Cross-domain Feature Fusion And Multi-attention Speech Enhancement Network Based On Self-supervised Embedding (2024)4.52
• Exploiting Consistency-preserving Loss And Perceptual Contrast Stretching To Boost Ssl-based Speech Enhancement (2024)6.77
• Espnet-se++: Speech Enhancement For Robust Speech Recognition, Translation, And Understanding (2022)18.72
• Investigating Self-supervised Learning For Speech Enhancement And Separation (2022)13.44
• Multi-objective Learning And Mask-based Post-processing For Deep Neural Network Based Speech Enhancement (2017)9.76