Back to Search Start Over

Exploring Tradeoffs in Models for Low-latency Speech Enhancement

Authors :
Wilson, Kevin
Chinen, Michael
Thorpe, Jeremy
Patton, Brian
Hershey, John
Saurous, Rif A.
Skoglund, Jan
Lyon, Richard F.
Publication Year :
2018

Abstract

We explore a variety of neural networks configurations for one- and two-channel spectrogram-mask-based speech enhancement. Our best model improves on previous state-of-the-art performance on the CHiME2 speech enhancement task by 0.4 decibels in signal-to-distortion ratio (SDR). We examine trade-offs such as non-causal look-ahead, computation, and parameter count versus enhancement performance and find that zero-look-ahead models can achieve, on average, within 0.03 dB SDR of our best bidirectional model. Further, we find that 200 milliseconds of look-ahead is sufficient to achieve equivalent performance to our best bidirectional model.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.1811.07030
Document Type :
Working Paper