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

facebooktwittermailshare

DETECTION OF SPOKEN WORDS IN NOISE: COMPARISON OF HUMAN PERFORMANCE TO MAXIMUM LIKELIHOOD DETECTION

Abstract: 

In this work, we are interested in assessing the optimality of the human auditory system, when the input stimuli is natural speech that is affected by additive noise. In order to do this, we consider the DANTALE II listening test paradigm of Wagener et al., which has been used to evaluate the intelligibility of noisy speech by exposing human listeners to a selection of constructed noisy sentences. Inspired by this test, we propose a simple model for the communication and classification of noisy speech that takes place in the test. We then identify a number of key properties that the test subjects satisfy, and combine these with our proposed model in order to derive optimal classifiers in the sense of maximum a posteriori estimation. We finally compare the performance of the classifiers to that of humans on the same noisy test sentences. The results reveal that at low SNRs, the human performance is inferior to that of the optimal classifiers. We conclude that in this special task, the human auditory system is not optimal.

up
0 users have voted:

Paper Details

Authors:
Mohsen Zareian Jahromi, Jan Ostergaard, Jesper Jensen
Submitted On:
6 December 2016 - 12:09pm
Short Link:
Type:
Presentation Slides
Event:
Paper Code:
GS-3.2
Document Year:
2016
Cite

Document Files

GS16.pdf

(336)

Subscribe

[1] Mohsen Zareian Jahromi, Jan Ostergaard, Jesper Jensen, "DETECTION OF SPOKEN WORDS IN NOISE: COMPARISON OF HUMAN PERFORMANCE TO MAXIMUM LIKELIHOOD DETECTION", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/1365. Accessed: Aug. 24, 2019.
@article{1365-16,
url = {http://sigport.org/1365},
author = {Mohsen Zareian Jahromi; Jan Ostergaard; Jesper Jensen },
publisher = {IEEE SigPort},
title = {DETECTION OF SPOKEN WORDS IN NOISE: COMPARISON OF HUMAN PERFORMANCE TO MAXIMUM LIKELIHOOD DETECTION},
year = {2016} }
TY - EJOUR
T1 - DETECTION OF SPOKEN WORDS IN NOISE: COMPARISON OF HUMAN PERFORMANCE TO MAXIMUM LIKELIHOOD DETECTION
AU - Mohsen Zareian Jahromi; Jan Ostergaard; Jesper Jensen
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/1365
ER -
Mohsen Zareian Jahromi, Jan Ostergaard, Jesper Jensen. (2016). DETECTION OF SPOKEN WORDS IN NOISE: COMPARISON OF HUMAN PERFORMANCE TO MAXIMUM LIKELIHOOD DETECTION. IEEE SigPort. http://sigport.org/1365
Mohsen Zareian Jahromi, Jan Ostergaard, Jesper Jensen, 2016. DETECTION OF SPOKEN WORDS IN NOISE: COMPARISON OF HUMAN PERFORMANCE TO MAXIMUM LIKELIHOOD DETECTION. Available at: http://sigport.org/1365.
Mohsen Zareian Jahromi, Jan Ostergaard, Jesper Jensen. (2016). "DETECTION OF SPOKEN WORDS IN NOISE: COMPARISON OF HUMAN PERFORMANCE TO MAXIMUM LIKELIHOOD DETECTION." Web.
1. Mohsen Zareian Jahromi, Jan Ostergaard, Jesper Jensen. DETECTION OF SPOKEN WORDS IN NOISE: COMPARISON OF HUMAN PERFORMANCE TO MAXIMUM LIKELIHOOD DETECTION [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/1365