English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Here we propose FastFCA-AS, an accelerated algorithm for Full-rank spatialCovariance Analysis (FCA), which is a robust audio source separation methodproposed by Duong et al. ["Under-determined reverberant audio source separationusing a full-rank spatial covariance model," IEEE Trans. ASLP, vol. 18, no. 7,pp. 1830-1840, Sept. 2010]. In the conventional FCA, matrix inversion andmatrix multiplication are required at each time-frequency point in eachiteration of an iterative parameter estimation algorithm. This causes a heavycomputational load, thereby rendering the FCA infeasible in many applications.To overcome this drawback, we take a joint diagonalization approach, wherebymatrix inversion and matrix multiplication are reduced to mere inversion andmultiplication of diagonal entries. This makes the FastFCA-AS significantlyfaster than the FCA and even applicable to observed data of long duration or asituation with restricted computational resources. Although we have alreadyproposed another acceleration of the FCA for two sources, the proposedFastFCA-AS is applicable to an arbitrary number of sources. In an experimentwith three sources and three microphones, the FastFCA-AS was over 420 timesfaster than the FCA with a slightly better source separation performance.

FastFCA-AS: Joint Diagonalization Based Acceleration of Full-Rank Spatial Covariance Analysis for Separating Any Number of Sources