Title | ||
---|---|---|
Blind speech deconvolution via pretrained polynomial dictionary and sparse representation |
Abstract | ||
---|---|---|
Blind speech deconvolution aims to estimate both the source speech and acoustic channel from a reverberant speech signal. The problem is ill-posed and underdetermined, which often requires prior knowledge for the estimation of the source and channel. In this paper, we propose a blind speech deconvolution method via a pretrained polynomial dictionary and sparse representation. A polynomial dictionary learning technique is employed to train the dictionary from room impulse responses, which is then used as prior information to estimate the source and the acoustic impulse responses via an alternating optimization strategy. Simulations are provided to demonstrate the performance of the proposed method. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1007/978-3-319-77380-3_39 | ADVANCES IN MULTIMEDIA INFORMATION PROCESSING - PCM 2017, PT I |
Keywords | Field | DocType |
Blind deconvolution,Speech dereverberation,Polynomial dictionary learning,Acoustic channel estimation | Dictionary learning,Underdetermined system,Pattern recognition,Polynomial,Blind deconvolution,Computer science,Sparse approximation,Deconvolution,Communication channel,Impulse (physics),Artificial intelligence | Conference |
Volume | ISSN | ISBN |
10735 | 0302-9743 | 9783319773797 |
Citations | PageRank | References |
0 | 0.34 | 10 |
Authors | ||
5 |