Efficient Low-Latency Speech Enhancement with Mobile Audio Streaming Networks
Abstract
We propose Mobile Audio Streaming Networks (MASnet) for efficient low-latency speech enhancement, which is particularly suitable for mobile devices and other applications where computational capacity is a limitation. MASnet processes linear-scale spectrograms, transforming successive noisy frames into complex-valued ratio masks which are then applied to the respective noisy frames. MASnet can operate in a low-latency incremental inference mode which matches the complexity of layer-by-layer batch mode. Compared to a similar fully-convolutional architecture, MASnet incorporates depthwise and pointwise convolutions for a large reduction in fused multiply-accumulate operations per second (FMA/s), at the cost of some reduction in SNR.
Cite
@article{arxiv.2008.07244,
title = {Efficient Low-Latency Speech Enhancement with Mobile Audio Streaming Networks},
author = {Michał Romaniuk and Piotr Masztalski and Karol Piaskowski and Mateusz Matuszewski},
journal= {arXiv preprint arXiv:2008.07244},
year = {2020}
}
Comments
Accepted for INTERSPEECH 2020