Phase Continuity: Learning Derivatives Of Phase Spectrum For Speech Enhancement

Abstract

Modern neural speech enhancement models usually include various forms of phase information in their training loss terms, either explicitly or implicitly. However, these loss terms are typically designed to reduce the distortion of phase spectrum values at specific frequencies, which ensures they do not significantly affect the quality of the enhanced speech. In this paper, we propose an effective phase reconstruction strategy for neural speech enhancement that can operate in noisy environments. Specifically, we introduce a phase continuity loss that considers relative phase variations across the time and frequency axes. By including this phase continuity loss in a state-of-the-art neural speech enhancement system trained with reconstruction loss and a number of magnitude spectral losses, we show that our proposed method further improves the quality of enhanced speech signals over the baseline, especially when training is done jointly with a magnitude spectrum loss.

Stats

• citations7
• S2 citations—
• github stars0
• HF likes0
• heat score6.77
• arxiv keykim2022phase

Related papers

• An Explicit Consistency-preserving Loss Function For Phase Reconstruction And Speech Enhancement (2024)2.26
• A Consolidated View Of Loss Functions For Supervised Deep Learning-based Speech Enhancement (2020)13.93
• Long-frame-shift Neural Speech Phase Prediction With Spectral Continuity Enhancement And Interpolation Error Compensation (2023)0.00
• Phase-aware Speech Enhancement With Deep Complex U-net (2019)0.00
• DCCRN: Deep Complex Convolution Recurrent Network For Phase-aware Speech Enhancement (2020)20.78
• PHASEN: A Phase-and-harmonics-aware Speech Enhancement Network (2019)18.20
• Explicit Estimation Of Magnitude And Phase Spectra In Parallel For High-quality Speech Enhancement (2023)11.19
• Progressive Speech Enhancement With Residual Connections (2019)5.24