Real-time Denoising and Dereverberation with Tiny Recurrent U-Net
release_u45c2d5lqrajvixt4hftemv5fq
by
Hyeong-Seok Choi, Sungjin Park, Jie Hwan Lee, Hoon Heo, Dongsuk Jeon, Kyogu Lee
2021
Abstract
Modern deep learning-based models have seen outstanding performance
improvement with speech enhancement tasks. The number of parameters of
state-of-the-art models, however, is often too large to be deployed on devices
for real-world applications. To this end, we propose Tiny Recurrent U-Net
(TRU-Net), a lightweight online inference model that matches the performance of
current state-of-the-art models. The size of the quantized version of TRU-Net
is 362 kilobytes, which is small enough to be deployed on edge devices. In
addition, we combine the small-sized model with a new masking method called
phase-aware β-sigmoid mask, which enables simultaneous denoising and
dereverberation. Results of both objective and subjective evaluations have
shown that our model can achieve competitive performance with the current
state-of-the-art models on benchmark datasets using fewer parameters by orders
of magnitude.
In text/plain
format
Archived Files and Locations
application/pdf 681.8 kB
file_uwzzypiz6nb7jmx2wrsk4excjm
|
arxiv.org (repository) web.archive.org (webarchive) |
2102.03207v3
access all versions, variants, and formats of this works (eg, pre-prints)