INTERSPEECH 2013 14thAnnual Conference of the International Speech Communication Association Lyon, France August 25-29, 2013

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

Jesper Jensen (1), Cees H. Taal (2)

(1) Oticon A/S, Denmark
(2) LUMC, The Netherlands

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 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 (ƒÏ > 0.95) in predicting the intelligibility of speech signals contaminated by additive noise and potentially non-linearly processed using time-frequency weighting.

Full Paper

Bibliographic reference.  Jensen, Jesper / Taal, Cees H. (2013): "Prediction of intelligibility of noisy and time-frequency weighted speech based on mutual information between amplitude envelopes", In INTERSPEECH-2013, 1174-1178.