TY - GEN
T1 - Denoising Gravitational Waves with Enhanced Deep Recurrent Denoising Auto-encoders
AU - Shen, Hongyu
AU - George, Daniel
AU - Huerta, Eliu A.
AU - Zhao, Zhizhen
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/5
Y1 - 2019/5
N2 - Denoising of time domain data is a crucial task for many applications such as communication, translation, virtual assistants etc. For this task, a combination of a recurrent neural net (RNNs) with a Denoising Auto-Encoder (DAEs) has shown promising results. However, this combined model is challenged when operating with low signal-to-noise ratio (SNR) data embedded in non-Gaussian and non-stationary noise. To address this issue, we design a novel model, referred to as 'Enhanced Deep Recurrent Denoising Auto-Encoder' (EDR-DAE), that incorporates a signal amplifier layer, and applies curriculum learning by first denoising high SNR signals, before gradually decreasing the SNR until the signals become noise dominated. We showcase the performance of EDR-DAE using time-series data that describes gravitational waves embedded in very noisy backgrounds. In addition, we show that EDRDAE can accurately denoise signals whose topology is significantly more complex than those used for training, demonstrating that our model generalizes to new classes of gravitational waves that are beyond the scope of established denoising algorithms.
AB - Denoising of time domain data is a crucial task for many applications such as communication, translation, virtual assistants etc. For this task, a combination of a recurrent neural net (RNNs) with a Denoising Auto-Encoder (DAEs) has shown promising results. However, this combined model is challenged when operating with low signal-to-noise ratio (SNR) data embedded in non-Gaussian and non-stationary noise. To address this issue, we design a novel model, referred to as 'Enhanced Deep Recurrent Denoising Auto-Encoder' (EDR-DAE), that incorporates a signal amplifier layer, and applies curriculum learning by first denoising high SNR signals, before gradually decreasing the SNR until the signals become noise dominated. We showcase the performance of EDR-DAE using time-series data that describes gravitational waves embedded in very noisy backgrounds. In addition, we show that EDRDAE can accurately denoise signals whose topology is significantly more complex than those used for training, demonstrating that our model generalizes to new classes of gravitational waves that are beyond the scope of established denoising algorithms.
KW - RNN
KW - denoising algorithm
KW - gravitational waves
KW - time series
UR - http://www.scopus.com/inward/record.url?scp=85068996607&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85068996607&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2019.8683061
DO - 10.1109/ICASSP.2019.8683061
M3 - Conference contribution
AN - SCOPUS:85068996607
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 3237
EP - 3241
BT - 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
Y2 - 12 May 2019 through 17 May 2019
ER -