Name
Title | ||
|---|---|---|
Integrating Binary Mask Estimation With MRF Priors of Cochleagram for Speech Separation |
Abstract | ||
|---|---|---|
In present binary masking based speech separation systems, it is almost impossible to obtain the ideal binary mask (IBM). The error in IBM estimation usually results in energy absence in many speech-dominated time-frequency (T-F) units. It violates smooth evolution nature of the speech signal and creates great artefacts. Markov random field (MRF) is one of the promising approaches to model smooth evolution nature which has been extensively applied to image smoothing applications. In this letter, an MRF prior for modeling the spatial dependencies in audio cochleagram is introduced. With this prior model, we further smooth the binary mask based cochleagram and generalize binary mask to ratio mask via a Bayesian framework. Our algorithm is systematically evaluated and compared with other counterpart methods, and it yields substantially better performance, especially on suppressing artefacts. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1109/LSP.2012.2209643 | IEEE Signal Process. Lett. |
Keywords | Field | DocType |
iterated conditional modes (icm),speech processing,binary mask estimation,audio cochleagram,speech separation systems,speech-dominated time-frequency units,ideal binary mask,markov random field,ideal ratio mask,binary masking,energy absence,markov processes,bayesian framework | Speech processing,Markov process,Masking (art),Pattern recognition,Markov random field,Computer science,Smoothing,Artificial intelligence,Prior probability,Binary number,Bayesian probability | Journal |
Volume | Issue | ISSN |
19 | 10 | 1070-9908 |
Citations | PageRank | References |
6 | 0.50 | 8 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Shan Liang | 1 | 6 | 0.84 |
| Wenju Liu | 2 | 7 | 0.90 |
| Wei Jiang | 3 | 44 | 6.02 |