Online Phase Reconstruction via DNN-based Phase Differences Estimation

TL;DR

This paper introduces a causal, two-stage online phase reconstruction method using DNNs to estimate phase differences between adjacent time-frequency bins, improving real-time phase recovery from magnitude spectrograms.

Contribution

The paper proposes a novel causal DNN-based framework for online phase reconstruction that estimates phase differences directly, avoiding iterative procedures and outperforming existing methods.

Findings

Outperforms existing online phase reconstruction methods.

Uses DNNs to estimate phase differences effectively.

Operates causally without iterative refinement.

Abstract

This paper presents a two-stage online phase reconstruction framework using causal deep neural networks (DNNs). Phase reconstruction is a task of recovering phase of the short-time Fourier transform (STFT) coefficients only from the corresponding magnitude. However, phase is sensitive to waveform shifts and not easy to estimate from the magnitude even with a DNN. To overcome this problem, we propose to use DNNs for estimating differences of phase between adjacent time-frequency bins. We show that convolutional neural networks are suitable for phase difference estimation, according to the theoretical relation between partial derivatives of STFT phase and magnitude. The estimated phase differences are used for reconstructing phase by solving a weighted least squares problem in a frame-by-frame manner. In contrast to existing DNN-based phase reconstruction methods, the proposed framework is causal and does not require any iterative procedure. The experiments showed that the proposed method outperforms existing online methods and a DNN-based method for phase reconstruction.