Prediction of Intelligibility of Noisy and Time-Frequency Weighted Speech based on Mutual Information Between Amplitude Envelopes

Jesper Jensen, C.H. Taal

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

213 Downloads (Pure)

Abstract

This paper deals with the problem of predicting the average intelligibility of noisy and potentially processed speech signals, as observed by a group of normal hearing listeners. We propose a prediction model based on the hypothesis that intelligibility is monotonically related to the the amount of Shannon information the critical-band amplitude envelopes of the noisy/processed signal convey about the corresponding clean signal envelopes. The resulting intelligibility predictor turns out to be a simple function of the correlation between noisy/processed and clean amplitude envelopes. The proposed predictor performs well (ρ>0.95) in predicting the intelligibility of speech signals contaminated by additive noise and potentially non-linearly processed using time-frequency weighting.
Original languageEnglish
Title of host publication14th Annual Conference of the International Speech Communication Association (INTERSPEECH 2013) : Speech in Life Sciences and Human Societies
Number of pages5
PublisherInternational Speech Communications Association
Publication date2013
Pages1174-1178
ISBN (Print)978-1-62993-443-3
Publication statusPublished - 2013
EventInterspeech 2013 - Lyon, France
Duration: 25 Aug 201329 Aug 2013
http://www.interspeech2013.org/

Conference

ConferenceInterspeech 2013
Country/TerritoryFrance
CityLyon
Period25/08/201329/08/2013
Internet address
SeriesProceedings of the International Conference on Spoken Language Processing
ISSN1990-9772

Fingerprint

Dive into the research topics of 'Prediction of Intelligibility of Noisy and Time-Frequency Weighted Speech based on Mutual Information Between Amplitude Envelopes'. Together they form a unique fingerprint.

Cite this