A factorial sparse coder model for single channel source separation

Robert Peharz, Michael Stark, Franz Pernkopf, Yannis Stylianou

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

3 Citaten (Scopus)

Samenvatting

We propose a probabilistic factorial sparse coder model for single channel source separation in the magnitude spectrogram domain. The mixture spectrogram is assumed to be the sum of the sources, which are assumed to be generated frame-wise as the output of sparse coders plus noise. For dictionary training we use an algorithm which can be described as non-negative matrix factorization with ℓ 0 sparseness constraints. In order to infer likely source spectrogram candidates, we approximate the intractable exact inference by maximizing the posterior over a plausible subset of solutions. We compare our system to the factorial-max vector quantization model, where the proposed method shows a superior performance in terms of signal-to-interference ratio. Finally, the low computational requirements of the algorithm allows close to real time applications.

Originele taal-2Engels
TitelAnnual Conference of the International Speech Communication Association (INTERSPEECH)
UitgeverijISCA
Pagina's386-389
Aantal pagina's4
StatusGepubliceerd - 1 dec 2010
Extern gepubliceerdJa
Evenement11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010 - Makuhari, Chiba, Japan
Duur: 26 sep 201030 sep 2010

Congres

Congres11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010
Land/RegioJapan
StadMakuhari, Chiba
Periode26/09/1030/09/10

Vingerafdruk

Duik in de onderzoeksthema's van 'A factorial sparse coder model for single channel source separation'. Samen vormen ze een unieke vingerafdruk.

Citeer dit