Name
Abstract | ||
|---|---|---|
lot of efforts have been made in the Ideal Binary Mask (IBM) estimation via statistical learning methods. The Bayesian method is a common one. However, one drawback is that the mask is estimated for each time-frequency (T-F) unit independently. The correlation between units has not been fully taken into account. In this paper, we attempt to consider the local correlation information from two aspects to improve the performance. On one hand, a T-F segmentation based potential function is proposed to depict the local correlation between the mask labels of adjacent units directly. It is derived from a demonstrated assumption that units which belong to one segment are mainly dominated by one source. On the other hand, a local noise level tracking stage is incorporated. The local level is obtained by averaging among several adjacent units and can be considered as an approach to true noise energy. It is used as the intermediary auxiliary variable to indicate the correlation. While some secondary factors are omitted, the high dimensional posterior distribution is simulated by a Markov Chain Monte Carlo (MCMC) method. In iterations, the correlation is fully considered to compute the acceptance ratio. The estimate of IBM is obtained by the expectation. Our system is evaluated and compared with previous Bayesian system, and it yields substantially better performance in terms of HIT-FA rates and SNR gain. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/TASL.2012.2226156 | IEEE Transactions on Audio, Speech, and Language Processing |
Keywords | Field | DocType |
ideal binary mask (ibm),markov chain monte carlo method,t-f segmentation,ibm estimation,intermediary auxiliary variable,ideal binary mask estimation,statistical analysis,learning (artificial intelligence),hit-fa rate,statistical learning method,monte carlo methods,local correlation information,other local noise level tracking stage,bayesian rule,time-frequency estimation,estimation theory,markov processes,high dimensional posterior distribution,bayes methods,iteration method,bayesian method,t-f estimation,markov chain monte carlo (mcmc),speech enhancement,mcmc method,correlation methods,computational auditory scene analysis (casa),iterative methods,time-frequency analysis,snr gain,correlation,feature extraction,speech,reliability,bayesian methods,signal to noise ratio,learning artificial intelligence,time frequency analysis | Monte Carlo method,Markov process,Markov chain Monte Carlo,Pattern recognition,Computer science,Iterative method,Segmentation,Speech recognition,Posterior probability,Artificial intelligence,Estimation theory,Bayesian probability | Journal |
Volume | Issue | ISSN |
21 | 3 | 1558-7916 |
Citations | PageRank | References |
6 | 0.48 | 20 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Shan Liang | 1 | 8 | 1.88 |
| Wenju Liu | 2 | 214 | 39.32 |
| Wei Jiang | 3 | 44 | 6.02 |