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

facebooktwittermailshare

BACKGROUND ADAPTATION FOR IMPROVED LISTENING EXPERIENCE IN BROADCASTING

Abstract: 

The intelligibility of speech in noise can be improved by modifying the speech. But with object-based audio, there
is the possibility of altering the background sound while leaving the speech unaltered. This may prove a less intrusive approach, affording good speech intelligibility without overly compromising the perceived sound quality. In this
study, the technique of spectral weighting was applied to the background. The frequency-dependent weightings for adaptation were learnt by maximising a weighted combination of two perceptual objective metrics for speech intelligibility and
audio quality. The balance between the two objective metrics was determined by the perceptual relationship between
intelligibility and quality. A neural network was trained to provide a fast solution for real-time processing. Tested in a
variety of background sounds and speech-to-background ratios (SBRs), the proposed method led to a large intelligibility
gain over the unprocessed baseline. Compared to an approach using constant weightings, the proposed method was able to
dynamically preserve the overall audio quality better with respect to SBR changes.

up
0 users have voted:

Paper Details

Authors:
Yan Tang, Qingju Liu, Bruno Fazenda, Weuwu Wang
Submitted On:
14 May 2019 - 2:49am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Trevor Cox
Paper Code:
1878
Document Year:
2019
Cite

Document Files

ICASSP_TJC.pdf

(36)

Subscribe

[1] Yan Tang, Qingju Liu, Bruno Fazenda, Weuwu Wang, "BACKGROUND ADAPTATION FOR IMPROVED LISTENING EXPERIENCE IN BROADCASTING", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4501. Accessed: Oct. 17, 2019.
@article{4501-19,
url = {http://sigport.org/4501},
author = {Yan Tang; Qingju Liu; Bruno Fazenda; Weuwu Wang },
publisher = {IEEE SigPort},
title = {BACKGROUND ADAPTATION FOR IMPROVED LISTENING EXPERIENCE IN BROADCASTING},
year = {2019} }
TY - EJOUR
T1 - BACKGROUND ADAPTATION FOR IMPROVED LISTENING EXPERIENCE IN BROADCASTING
AU - Yan Tang; Qingju Liu; Bruno Fazenda; Weuwu Wang
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4501
ER -
Yan Tang, Qingju Liu, Bruno Fazenda, Weuwu Wang. (2019). BACKGROUND ADAPTATION FOR IMPROVED LISTENING EXPERIENCE IN BROADCASTING. IEEE SigPort. http://sigport.org/4501
Yan Tang, Qingju Liu, Bruno Fazenda, Weuwu Wang, 2019. BACKGROUND ADAPTATION FOR IMPROVED LISTENING EXPERIENCE IN BROADCASTING. Available at: http://sigport.org/4501.
Yan Tang, Qingju Liu, Bruno Fazenda, Weuwu Wang. (2019). "BACKGROUND ADAPTATION FOR IMPROVED LISTENING EXPERIENCE IN BROADCASTING." Web.
1. Yan Tang, Qingju Liu, Bruno Fazenda, Weuwu Wang. BACKGROUND ADAPTATION FOR IMPROVED LISTENING EXPERIENCE IN BROADCASTING [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4501