Differentiable Consistency Constraints for Improved Deep Speech Enhancement
Scott Wisdom, John R. Hershey, Kevin W. Wilson, Jeremy Thorpe, Michael Chinen, Brian Patton, Rif A. Saurous
Abstract
In recent years, deep networks have led to dramatic improvements in speech enhancement by framing it as a data-driven pattern recognition problem. In many modern enhancement systems, large amounts of data are used to train a deep network to estimate masks for complex-valued short-time Fourier transforms (STFTs) to suppress noise and preserve speech. However, current masking approaches often neglect two important constraints: STFT consistency and mixture consistency. Without STFT consistency, the system's output is not necessarily the STFT of a time-domain signal, and without mixture consistency, the sum of the estimated sources does not necessarily equal the input mixture. Furthermore, the only previous approaches that apply mixture consistency use real-valued masks; mixture consistency has been ignored for complex-valued masks.
BibTeX
@inproceedings{icassp2019_differentiableco,
title = {Differentiable Consistency Constraints for Improved Deep Speech Enhancement},
author = {Scott Wisdom and John R. Hershey and Kevin W. Wilson and Jeremy Thorpe and Michael Chinen and Brian Patton and Rif A. Saurous},
booktitle = {ICASSP 2019},
year = {2019}
}