Abstract | ||
---|---|---|
In this study, we propose a reconstruction method to restore the degraded features for robust speaker identification. The proposed method is based on a hybrid generative model which consists of deep belief network (DBN) and restricted Boltzmann machine (RBM). Specifically, the noisy speech is firstly decomposed into time-frequency (T-F) representations. Then ideal binary mask (IBM) is computed to indicate each T-F point as reliable or unreliable. We reconstruct the unreliable ones by the proposed model iteratively. Finally, reconstructed feature is utilized to conventional speaker identification system. Experiments demonstrate that the proposed method achieves significant performance improvements over previous missing feature techniques under a wide range of signal-to-noise ratios. |
Year | Venue | Keywords |
---|---|---|
2014 | EUSIPCO | restricted Boltzmann machine,signal representation,Restricted Boltzmann machine,signal-to-noise ratios,signal restoration,DBN,missing feature reconstruction methods,Robust speaker identification,Missing feature techniques,deep belief network,Deep belief network,speaker recognition,IBM,RBM,hybrid generative model,T-F point,signal reconstruction,T-F representations,ideal binary mask,noisy speech,robust speaker identification system,time-frequency representations,time-frequency analysis |
Field | DocType | ISSN |
Speaker identification,Pattern recognition,Computer science,Speech recognition,Speaker recognition,Artificial intelligence | Conference | 2076-1465 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xueliang Zhang | 1 | 80 | 19.41 |
Hui Zhang | 2 | 13 | 6.39 |
Guanglai Gao | 3 | 78 | 24.57 |