Paper Info
Title
Why Do Speech-Enhancement Algorithms Not Improve Speech Intelligibility?
Abstract
While most speech enhancement algorithms improve speech quality, they do not improve speech intelligibility in noise. The reasons for that remain unclear. In this paper, we present a theoretical framework that can be used to analyze potential factors influencing the intelligibility of processed speech. It is hypothesized that if distortions are properly controlled, then large gains in intelligibility can be achieved. To assess the perceptual effect of the various distortions that can be introduced by speech enhancement algorithms, intelligibility tests are conducted with human listeners. The results indicated that certain distortions are more critical than others. The result of listening tests suggested that when these distortions are properly controlled, substantial gains in intelligibility can be obtained.
Year
DOI
Venue
2010
10.1109/ICASSP.2010.5495169
2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING
Keywords
Field
DocType
Speech intelligibility, speech distortion, speech enhancement
Speech enhancement,Speech processing,Background noise,Noise measurement,Computer science,Signal-to-noise ratio,Active listening,Algorithm,Speech recognition,Perception,Intelligibility (communication)
Conference
ISSN
Citations 
PageRank 
1520-6149
4
0.61
References 
Authors
3
2
Name
Order
Citations
PageRank
Gibak Kim11037.38
Philipos C. Loizou299171.00