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

facebooktwittermailshare

The effect of gain thresholds on speech intelligibility for statistical model based noise reduction for cochlear implants:A simulation based verification

Abstract: 

Noise corruption can dramatically decrease the speech intelligibility for listeners with cochlear implants (CI). Noise reduction is a key point in CI speech processing strategy. This paper proposes a statistical model based noise reduction algorithm forCIs. A realistic noise estimator, which requires no prior knowledge of the noise, is adopted for noise estimation. An improved method for determining the user-specific gain function is proposed, in which the apparent gain threshold is incorporated to compute the optimal parameters, with which the optimal gain function for noise suppression can be determined accordingly. Vocoder simulation perceptual experiments with normal hearing listeners shows that the proposed algorithm can significantly improve the speech intelligibility of the denoised speech.

up
0 users have voted:

Paper Details

Authors:
wenzhi He, nengheng Zheng, qinglin Meng
Submitted On:
13 October 2016 - 10:57pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Wenzhi, He
Paper Code:
140
Document Year:
2016
Cite

Document Files

cochlear implant

(41)

Subscribe

[1] wenzhi He, nengheng Zheng, qinglin Meng, "The effect of gain thresholds on speech intelligibility for statistical model based noise reduction for cochlear implants:A simulation based verification", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/1177. Accessed: Aug. 24, 2019.
@article{1177-16,
url = {http://sigport.org/1177},
author = {wenzhi He; nengheng Zheng; qinglin Meng },
publisher = {IEEE SigPort},
title = {The effect of gain thresholds on speech intelligibility for statistical model based noise reduction for cochlear implants:A simulation based verification},
year = {2016} }
TY - EJOUR
T1 - The effect of gain thresholds on speech intelligibility for statistical model based noise reduction for cochlear implants:A simulation based verification
AU - wenzhi He; nengheng Zheng; qinglin Meng
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/1177
ER -
wenzhi He, nengheng Zheng, qinglin Meng. (2016). The effect of gain thresholds on speech intelligibility for statistical model based noise reduction for cochlear implants:A simulation based verification. IEEE SigPort. http://sigport.org/1177
wenzhi He, nengheng Zheng, qinglin Meng, 2016. The effect of gain thresholds on speech intelligibility for statistical model based noise reduction for cochlear implants:A simulation based verification. Available at: http://sigport.org/1177.
wenzhi He, nengheng Zheng, qinglin Meng. (2016). "The effect of gain thresholds on speech intelligibility for statistical model based noise reduction for cochlear implants:A simulation based verification." Web.
1. wenzhi He, nengheng Zheng, qinglin Meng. The effect of gain thresholds on speech intelligibility for statistical model based noise reduction for cochlear implants:A simulation based verification [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/1177