Share Email Print
cover

Proceedings Paper

Multi-objective noisy-based deep feature loss for speech enhancement
Author(s): Rafal Pilarczyk; Władysław Skarbek
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Deep neural networks have become a great tool for creating solutions to denoise the speech signal, improving the intelligibility, speech quality and signal-to-noise ratio. An important element during training deep speech networks is the use of an appropriate loss function that allows to improvement the subjective and objective measures. In our work, we used the loss function based on a well-trained deep network to classify whether the signal is noisy and clean. Thanks to this, the deep network responsible for denoising is based on minimizing the difference of deep features of the pure and enhanced signal. Our work shows that the use of only deep features in the loss function allows a significant improvement in the measurement of speech signal quality. Novelty is also feature extractor, which has been trained as a multi-objective noise classifier. We believe that deep-feature loss could help in the optimization of functions difficult to differentiate.

Paper Details

Date Published: 6 November 2019
PDF: 8 pages
Proc. SPIE 11176, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2019, 111762W (6 November 2019); doi: 10.1117/12.2536967
Show Author Affiliations
Rafal Pilarczyk, BabbleLabs, Inc. (United States)
Warsaw Univ. of Technology (Poland)
Władysław Skarbek, Warsaw Univ. of Technology (Poland)


Published in SPIE Proceedings Vol. 11176:
Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2019
Ryszard S. Romaniuk; Maciej Linczuk, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray