Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Weighted Speech Distortion Losses for Real-time Speech Enhancement

Abstract: 

This paper investigates several aspects of training a RNN (recurrent neural network) that impact the objective and subjective quality of enhanced speech for real-time single-channel speech enhancement. Specifically, we focus on a RNN that enhances short-time speech spectra on a single-frame-in, single-frame-out basis, a framework adopted by most classical signal processing methods. We propose two novel mean-squared-error-based learning objectives that enable separate control over the importance of speech distortion versus noise reduction. The proposed loss functions are evaluated by widely accepted objective quality and intelligibility measures and compared to other competitive online methods. In addition, we study the impact of feature normalization and varying batch sequence lengths on the objective quality of enhanced speech. Finally, we show subjective ratings for the proposed approach and a state-of-the-art real-time RNN-based method.

up
0 users have voted:

Paper Details

Authors:
Ivan Tashev
Submitted On:
17 May 2020 - 7:34pm
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Yangyang Xia
Document Year:
2020
Cite

Document Files

dns-public-v2short.pptx

(39)

Subscribe

[1] Ivan Tashev, "Weighted Speech Distortion Losses for Real-time Speech Enhancement", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5388. Accessed: Jul. 14, 2020.
@article{5388-20,
url = {http://sigport.org/5388},
author = {Ivan Tashev },
publisher = {IEEE SigPort},
title = {Weighted Speech Distortion Losses for Real-time Speech Enhancement},
year = {2020} }
TY - EJOUR
T1 - Weighted Speech Distortion Losses for Real-time Speech Enhancement
AU - Ivan Tashev
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5388
ER -
Ivan Tashev. (2020). Weighted Speech Distortion Losses for Real-time Speech Enhancement. IEEE SigPort. http://sigport.org/5388
Ivan Tashev, 2020. Weighted Speech Distortion Losses for Real-time Speech Enhancement. Available at: http://sigport.org/5388.
Ivan Tashev. (2020). "Weighted Speech Distortion Losses for Real-time Speech Enhancement." Web.
1. Ivan Tashev. Weighted Speech Distortion Losses for Real-time Speech Enhancement [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5388