Skip to main content

Research Repository

Advanced Search

A neural network model for speech intelligibility quantification

Li, FF; Cox, TJ

Authors

FF Li



Abstract

A neural network based model is developed to quantify speech intelligibility by blind-estimating speech transmission index, an objective rating index for speech intelligibility of transmission channels, from transmitted speech signals without resort to knowledge of original speech signals. It consists of a Hilbert transform processor for speech envelope detection, a Welch average periodogram algorithm for envelope spectrum estimation, a principal components analysis (PCA) network for speech feature extraction and a multi-layer back-propagation network for non-linear mapping and case generalisation. The developed model circumvents the use of artificial test signals by exploiting naturally occurring speech signals as probe stimuli, reduces measurement channels from two to one and hence facilitates in situ assessment of speech intelligibility. From a cognitive science viewpoint, the proposed method might be viewed as a successful paradigm of mimicking human perception of speech intelligibility using a hybrid model built around artificial neural networks.

Citation

Li, F., & Cox, T. (2007). A neural network model for speech intelligibility quantification. Applied Soft Computing, 7(1), 145-155. https://doi.org/10.1016/j.asoc.2005.05.002

Journal Article Type Article
Publication Date Jan 1, 2007
Deposit Date Sep 11, 2007
Journal Applied Soft Computing
Print ISSN 1568-4946
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 7
Issue 1
Pages 145-155
DOI https://doi.org/10.1016/j.asoc.2005.05.002