FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285203473> ?p ?o ?g. }

• W4285203473 endingPage "2382" @default.
• W4285203473 startingPage "2368" @default.
• W4285203473 abstract "This paper describes a computationally-efficient statistical approach to joint (semi-)blind source separation and dereverberation for multichannel noisy reverberant mixture signals. A standard approach to source separation is to formulate a generative model of a multichannel mixture spectrogram that consists of source and spatial models representing the time-frequency power spectral densities (PSDs) and spatial covariance matrices (SCMs) of source images, respectively, and find the maximum-likelihood estimates of these parameters. A state-of-the-art blind source separation method in this thread of research is fast multichannel nonnegative matrix factorization (FastMNMF) based on the low-rank PSDs and jointly-diagonalizable full-rank SCMs. To perform mutually-dependent separation and dereverberation jointly, in this paper we integrate both moving average (MA) and autoregressive (AR) models that represent the early reflections and late reverberations of sources, respectively, into the FastMNMF formalism. Using a pretrained deep generative model of speech PSDs as a source model, we realize semi-blind joint speech separation and dereverberation. We derive an iterative optimization algorithm based on iterative projection or iterative source steering for jointly and efficiently updating the AR parameters and the SCMs. Our experimental results showed the superiority of the proposed ARMA extension over its AR- or MA-ablated version in a speech separation and/or dereverberation task." @default.
• W4285203473 created "2022-07-14" @default.
• W4285203473 creator A5007353694 @default.
• W4285203473 creator A5038044080 @default.
• W4285203473 creator A5067956319 @default.
• W4285203473 creator A5069659508 @default.
• W4285203473 creator A5082272880 @default.
• W4285203473 creator A5082784886 @default.
• W4285203473 date "2022-01-01" @default.
• W4285203473 modified "2023-10-09" @default.
• W4285203473 title "Autoregressive Moving Average Jointly-Diagonalizable Spatial Covariance Analysis for Joint Source Separation and Dereverberation" @default.
• W4285203473 cites W108815450 @default.
• W4285203473 cites W1543386260 @default.
• W4285203473 cites W1552314771 @default.
• W4285203473 cites W1845880232 @default.
• W4285203473 cites W1983812858 @default.
• W4285203473 cites W1989314204 @default.
• W4285203473 cites W2002146237 @default.
• W4285203473 cites W2014768838 @default.
• W4285203473 cites W2021196544 @default.
• W4285203473 cites W2039844283 @default.
• W4285203473 cites W2040782121 @default.
• W4285203473 cites W2072548008 @default.
• W4285203473 cites W2099741732 @default.
• W4285203473 cites W2113990625 @default.
• W4285203473 cites W2117332620 @default.
• W4285203473 cites W2127851351 @default.
• W4285203473 cites W2143027228 @default.
• W4285203473 cites W2144404214 @default.
• W4285203473 cites W2164502538 @default.
• W4285203473 cites W2168273590 @default.
• W4285203473 cites W2398042854 @default.
• W4285203473 cites W2412956798 @default.
• W4285203473 cites W2517616541 @default.
• W4285203473 cites W2766672686 @default.
• W4285203473 cites W2800675406 @default.
• W4285203473 cites W2889224938 @default.
• W4285203473 cites W2901552243 @default.
• W4285203473 cites W2922004249 @default.
• W4285203473 cites W2936446744 @default.
• W4285203473 cites W2937284863 @default.
• W4285203473 cites W2963375116 @default.
• W4285203473 cites W2964080410 @default.
• W4285203473 cites W2979850772 @default.
• W4285203473 cites W2982471419 @default.
• W4285203473 cites W2987027330 @default.
• W4285203473 cites W2987410580 @default.
• W4285203473 cites W2997688633 @default.
• W4285203473 cites W3015564447 @default.
• W4285203473 cites W3015678657 @default.
• W4285203473 cites W3016114588 @default.
• W4285203473 cites W3081267827 @default.
• W4285203473 cites W3099177480 @default.
• W4285203473 cites W3106955634 @default.
• W4285203473 cites W3127348940 @default.
• W4285203473 cites W3130736950 @default.
• W4285203473 cites W3163542373 @default.
• W4285203473 doi "https://doi.org/10.1109/taslp.2022.3190734" @default.
• W4285203473 hasPublicationYear "2022" @default.
• W4285203473 type Work @default.
• W4285203473 citedByCount "1" @default.
• W4285203473 countsByYear W42852034732023 @default.
• W4285203473 crossrefType "journal-article" @default.
• W4285203473 hasAuthorship W4285203473A5007353694 @default.
• W4285203473 hasAuthorship W4285203473A5038044080 @default.
• W4285203473 hasAuthorship W4285203473A5067956319 @default.
• W4285203473 hasAuthorship W4285203473A5069659508 @default.
• W4285203473 hasAuthorship W4285203473A5082272880 @default.
• W4285203473 hasAuthorship W4285203473A5082784886 @default.
• W4285203473 hasBestOaLocation W42852034731 @default.
• W4285203473 hasConcept C105795698 @default.
• W4285203473 hasConcept C11413529 @default.
• W4285203473 hasConcept C120317606 @default.
• W4285203473 hasConcept C121332964 @default.
• W4285203473 hasConcept C127162648 @default.
• W4285203473 hasConcept C152671427 @default.
• W4285203473 hasConcept C158693339 @default.
• W4285203473 hasConcept C159877910 @default.
• W4285203473 hasConcept C2776864781 @default.
• W4285203473 hasConcept C28490314 @default.
• W4285203473 hasConcept C30072841 @default.
• W4285203473 hasConcept C31258907 @default.
• W4285203473 hasConcept C33923547 @default.
• W4285203473 hasConcept C41008148 @default.
• W4285203473 hasConcept C42355184 @default.
• W4285203473 hasConcept C45273575 @default.
• W4285203473 hasConcept C54848796 @default.
• W4285203473 hasConcept C62520636 @default.
• W4285203473 hasConceptScore W4285203473C105795698 @default.
• W4285203473 hasConceptScore W4285203473C11413529 @default.
• W4285203473 hasConceptScore W4285203473C120317606 @default.
• W4285203473 hasConceptScore W4285203473C121332964 @default.
• W4285203473 hasConceptScore W4285203473C127162648 @default.
• W4285203473 hasConceptScore W4285203473C152671427 @default.
• W4285203473 hasConceptScore W4285203473C158693339 @default.
• W4285203473 hasConceptScore W4285203473C159877910 @default.
• W4285203473 hasConceptScore W4285203473C2776864781 @default.
• W4285203473 hasConceptScore W4285203473C28490314 @default.

• next