Blind Non-Intrusive Speech Intelligibility Prediction Using Twin-HMMs

Abstract

Automatic prediction of speech intelligibility is highly desirable in the speech research community, since listening tests are timeconsuming and can not be used online. Most of the available objective speech intelligibility measures are intrusive methods, as they require a clean reference signal in addition to the corresponding noisy/processed signal at… (More)
DOI: 10.21437/Interspeech.2016-155

Topics

4 Figures and Tables

Slides referencing similar topics