Monaural speech segregation based on pitch tracking and amplitude modulation
IEEE Transactions on Neural Networks
IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP)
Speech Intelligibility Prediction Based on Mutual Information
IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP)
| Hi-index | 0.00 |
Classical speech intelligibility models, such as the speech transmission index (STI) and the speech intelligibility index (SII) are based on calculations on the physical acoustic signals. The present study predicts speech intelligibility by combining a psychoacoustically validated model of auditory preprocessing [Dau et al., 1997. J. Acoust. Soc. Am. 102, 2892-2905] with a simple central stage that describes the similarity of the test signal with the corresponding reference signal at a level of the internal representation of the signals. The model was compared with previous approaches, whereby a speech in noise experiment was used for training and an ideal binary mask experiment was used for evaluation. All three models were able to capture the trends in the speech in noise training data well, but the proposed model provides a better prediction of the binary mask test data, particularly when the binary masks degenerate to a noise vocoder.