Name
Title | ||
|---|---|---|
A novel normalization and regularization scheme for broadband convolutive blind source separation |
Abstract | ||
|---|---|---|
In this paper we propose a novel blind source separation (BSS) algorithm for convolutive mixtures combining advantages of broadband algorithms with the computational efficiency of narrowband techniques. It is based on a recently presented generic broadband algorithm. By selective application of the Szegö theorem which relates properties of Toeplitz and circulant matrices, a new normalization is derived which approximates well the exact normalization of the generic broadband algorithm presented in [2]. The new scheme thus results in a computationally efficient and fast converging algorithm while still avoiding typical narrowband problems such as the internal permutation problem or circularity effects. Moreover, a novel regularization method for the generic broadband algorithm is proposed and subsequently also derived for the proposed algorithm. Experimental results in realistic acoustic environments show improved performance of the novel algorithm compared to previous approximations. |
Year | DOI | Venue |
|---|---|---|
2006 | 10.1007/11679363_66 | ICA |
Keywords | Field | DocType |
new normalization,novel regularization method,broadband algorithm,novel blind source separation,novel normalization,regularization scheme,generic broadband algorithm,proposed algorithm,converging algorithm,narrowband technique,exact normalization,novel algorithm,broadband convolutive blind source,circulant matrices,blind source separation | Approximation algorithm,Narrowband,Normalization (statistics),Computer science,Algorithm,Toeplitz matrix,Regularization (mathematics),Discrete Fourier transform,Blind signal separation,Source separation | Conference |
Volume | ISSN | ISBN |
3889 | 0302-9743 | 3-540-32630-8 |
Citations | PageRank | References |
3 | 0.62 | 4 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Robert Aichner | 1 | 208 | 16.18 |
| Herbert Buchner | 2 | 435 | 40.57 |
| Walter Kellermann | 3 | 535 | 45.32 |