Print Email Facebook Twitter An intelligibility metric based on a simple model of speech communication Title An intelligibility metric based on a simple model of speech communication Author van Kuyk, Steven (Victoria University of Wellington) Kleijn, W.B. (Victoria University of Wellington) Hendriks, R.C. (TU Delft Signal Processing Systems) Date 2016-10-24 Abstract Instrumental measures of speech intelligibility typically produce an index between 0 and 1 that is monotonically related to listening test scores. As such, these measures are dimensionless and do not represent physical quantities. In this paper, we propose a new instrumental intelligibility metric that describes speech intelligibility using bits per second. The proposed metric builds upon an existing intelligibility metric that was motivated by information theory. Our main contribution is that we use a statistical model of speech communication that accounts for noise inherent in the speech production process. Experiments show that the proposed metric performs at least as well as existing state-of-the-art intelligibility metrics. Subject mutual informationIntelligibility To reference this document use: http://resolver.tudelft.nl/uuid:d3f5ef82-1a60-432e-86c8-1280014a7866 DOI https://doi.org/10.1109/iwaenc.2016.7602933 Publisher IEEE, Piscataway, NJ ISBN 978-1-5090-2007-2 Source 2016 IEEE International Workshop on Acoustic Signal Enhancement (IWAENC) Event 2016 IEEE International Workshop on Acoustic Signal Enhancement, 2016-09-13 → 2016-09-16, Xi'an, China Bibliographical note (Best student paper award) Part of collection Institutional Repository Document type conference paper Rights © 2016 Steven van Kuyk, W.B. Kleijn, R.C. Hendriks Files PDF kuyk_iwaenc16.pdf 328.64 KB Close viewer /islandora/object/uuid:d3f5ef82-1a60-432e-86c8-1280014a7866/datastream/OBJ/view