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

This paper deals with a multichannel audio source separation problem underunderdetermined conditions. Multichannel Non-negative Matrix Factorization(MNMF) is one of powerful approaches, which adopts the NMF concept for sourcepower spectrogram modeling. This concept is also employed in IndependentLow-Rank Matrix Analysis (ILRMA), a special class of the MNMF frameworkformulated under determined conditions. While these methods work reasonablywell for particular types of sound sources, one limitation is that they canfail to work for sources with spectrograms that do not comply with the NMFmodel. To address this limitation, an extension of ILRMA called theMultichannel Variational Autoencoder (MVAE) method was recently proposed, wherea Conditional VAE (CVAE) is used instead of the NMF model for source powerspectrogram modeling. This approach has shown to perform impressively indetermined source separation tasks thanks to the representation power of DNNs.While the original MVAE method was formulated under determined mixingconditions, this paper generalizes it so that it can also deal withunderdetermined cases. We call the proposed framework the Generalized MVAE(GMVAE). The proposed method was evaluated on a underdetermined sourceseparation task of separating out three sources from two microphone inputs.Experimental results revealed that the GMVAE method achieved better performancethan the MNMF method.

Generalized Multichannel Variational Autoencoder for Underdetermined Source Separation