Title | ||
---|---|---|
A NEW MASK-BASED OBJECTIVE MEASURE FOR PREDICTING THE INTELLIGIBILITY OF BINARY MASKED SPEECH. |
Abstract | ||
---|---|---|
Mask-based objective speech-intelligibility measures have been successfully proposed for evaluating the performance of binary masking algorithms. These objective measures were computed directly by comparing the estimated binary mask against the ground truth ideal binary mask (IdBM). Most of these objective measures, however, assign equal weight to all time-frequency (T-F) units. In this study, we propose to improve the existing mask-based objective measures by weighting each T-F unit according to its target or masker loudness. The proposed objective measure shows significantly better performance than two other existing mask-based objective measures. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/ICASSP.2013.6639025 | ICASSP |
Keywords | Field | DocType |
objective measure,binary mask estimation,binary masked speech,binary masking algorithms,speech intelligibility,speech separation,idbm,mask-based objective speech-intelligibility measures,ideal binary mask,mask-based objective measure,bioinformatics,noise,measurement uncertainty,speech,biomedical research,spectrogram,time frequency analysis | Loudness,Weighting,Pattern recognition,Masking (art),Computer science,Speech recognition,Ground truth,Artificial intelligence,Binary number,Intelligibility (communication) | Conference |
ISSN | Citations | PageRank |
1520-6149 | 0 | 0.34 |
References | Authors | |
3 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chengzhu Yu | 1 | 88 | 5.10 |
Kamil K. Wójcicki | 2 | 39 | 4.22 |
Philipos C. Loizou | 3 | 991 | 71.00 |
John H. L. Hansen | 4 | 3215 | 365.75 |