Multi-objective noisy-based deep feature loss for speech enhancement

Rafal Pilarczyk; Władysław Skarbek

doi:10.1117/12.2536967

6 November 2019 Multi-objective noisy-based deep feature loss for speech enhancement

Rafal Pilarczyk, Władysław Skarbek

Proceedings Volume 11176, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2019; 111762W (2019) https://doi.org/10.1117/12.2536967
Event: Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2019, 2019, Wilga, Poland

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.

Citation Download Citation

Rafal Pilarczyk and Władysław Skarbek "Multi-objective noisy-based deep feature loss for speech enhancement", Proc. SPIE 11176, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2019, 111762W (6 November 2019); https://doi.org/10.1117/12.2536967

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available