ISCA Archive Interspeech 2013
ISCA Archive Interspeech 2013

Prediction of intelligibility of noisy and time-frequency weighted speech based on mutual information between amplitude envelopes

Jesper Jensen, Cees H. Taal

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.


doi: 10.21437/Interspeech.2013-14

Cite as: Jensen, J., Taal, C.H. (2013) Prediction of intelligibility of noisy and time-frequency weighted speech based on mutual information between amplitude envelopes. Proc. Interspeech 2013, 1174-1178, doi: 10.21437/Interspeech.2013-14

@inproceedings{jensen13_interspeech,
  author={Jesper Jensen and Cees H. Taal},
  title={{Prediction of intelligibility of noisy and time-frequency weighted speech based on mutual information between amplitude envelopes}},
  year=2013,
  booktitle={Proc. Interspeech 2013},
  pages={1174--1178},
  doi={10.21437/Interspeech.2013-14}
}