Deep Learning Based Phase Reconstruction for Speaker Separation: A Trigonometric Perspective
Year: 2019
Type: conference-paper
Abstract: This study investigates phase reconstruction for deep learning based monaural talker-independent speaker separation in the short-time Fourier transform (STFT) domain. The key observation is that, for a mixture oftwo sources, with their magnitudes accurately estimated and under a geometric constraint, the absolute phase difference between each source and the mixture can be uniquely determined; in addition, the source phases at each time-frequency T - F unit can be narrowed down to only two candidates. To pick the right candidate, we propose three algorithms based on iterative phase reconstruction, group delay estimation, and phase-difference sign prediction. State-of-the-art results are obtained on the publicly available wsj0-2mix and 3 mix corpus.
Authors: Zhong-Qiu Wang, Ke Tan, DeLiang Wang
Institution: The Ohio State University
Language: English
Topic: Speech and Audio Processing
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2963317762