The benefit of combining a deep neural network architecture with ideal ratio mask estimation in computational speech segregation to improve speech intelligibility

Contains all the data:

Bentsen, T., T.May, A. A. Kresnner, and T. Dau. The benefit of combining
a deep neural network architecture with ideal ratio mask estimation
in computational speech segregation to improve speech intelligibility.
PLOS ONE., in review.

There are two folders:

1. WRSs: the Word Recognition Scores (WRSs) from the listener study. The matrix has dimensions 9 conditions x 20 subjects. Data is ordered corresponding to the following condition order:
   'UP', 'GMM', 'GMM (3 subbands)', 'GMM (7 subbands)', 'GMM (11 subbands)', 'DNN (IBM)'; 'DNN (IBM, 40 ms)'; 'DNN (IRM)'; 'DNN (IRM, 40 ms)'
2. Masks:
   • GMM-IBMs: IBMs and estimated IBMs for the models 'GMM', 'GMM (3 subbands)', 'GMM (7 subbands)', 'GMM (11 subbands)'
   • DNN-IBMs: IBMs and estimated IBMs for the models 'DNN (IBM)'; 'DNN (IBM, 40 ms)'
   • DNN-IRMs: IRMs and estimated IRMs for the models  'DNN (IRM)'; 'DNN (IRM, 40 ms)'