Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204992386> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3204992386 abstract "State of the art audio source separation models rely on supervised data-driven approaches, which can be expensive in terms of labeling resources. On the other hand, approaches for training these models without any direct supervision are typically high-demanding in terms of memory and time requirements, and remain impractical to be used at inference time. We aim to tackle these limitations by proposing a simple yet effective unsupervised separation algorithm, which operates directly on a latent representation of time-domain signals. Our algorithm relies on deep Bayesian priors in the form of pre-trained autoregressive networks to model the probability distributions of each source. We leverage the low cardinality of the discrete latent space, trained with a novel loss term imposing a precise arithmetic structure on it, to perform exact Bayesian inference without relying on an approximation strategy. We validate our approach on the Slakh dataset arXiv:1909.08494, demonstrating results in line with state of the art supervised approaches while requiring fewer resources with respect to other unsupervised methods." @default.
- W3204992386 created "2021-10-25" @default.
- W3204992386 creator A5034849830 @default.
- W3204992386 creator A5046548985 @default.
- W3204992386 creator A5069620223 @default.
- W3204992386 creator A5076690986 @default.
- W3204992386 creator A5085428440 @default.
- W3204992386 creator A5087051832 @default.
- W3204992386 date "2021-10-11" @default.
- W3204992386 modified "2023-09-26" @default.
- W3204992386 title "Unsupervised Source Separation via Bayesian Inference in the Latent Domain." @default.
- W3204992386 cites W1594771616 @default.
- W3204992386 cites W2099741732 @default.
- W3204992386 cites W2135181320 @default.
- W3204992386 cites W2162514423 @default.
- W3204992386 cites W2168793898 @default.
- W3204992386 cites W2669032454 @default.
- W3204992386 cites W2892365986 @default.
- W3204992386 cites W2949382160 @default.
- W3204992386 cites W2963799213 @default.
- W3204992386 cites W2971074500 @default.
- W3204992386 cites W2990594533 @default.
- W3204992386 cites W2991107219 @default.
- W3204992386 cites W2998490864 @default.
- W3204992386 cites W3021164770 @default.
- W3204992386 cites W3030191531 @default.
- W3204992386 cites W3035369987 @default.
- W3204992386 cites W3093725184 @default.
- W3204992386 cites W3160695487 @default.
- W3204992386 cites W3090496396 @default.
- W3204992386 hasPublicationYear "2021" @default.
- W3204992386 type Work @default.
- W3204992386 sameAs 3204992386 @default.
- W3204992386 citedByCount "0" @default.
- W3204992386 crossrefType "posted-content" @default.
- W3204992386 hasAuthorship W3204992386A5034849830 @default.
- W3204992386 hasAuthorship W3204992386A5046548985 @default.
- W3204992386 hasAuthorship W3204992386A5069620223 @default.
- W3204992386 hasAuthorship W3204992386A5076690986 @default.
- W3204992386 hasAuthorship W3204992386A5085428440 @default.
- W3204992386 hasAuthorship W3204992386A5087051832 @default.
- W3204992386 hasConcept C107673813 @default.
- W3204992386 hasConcept C119857082 @default.
- W3204992386 hasConcept C153083717 @default.
- W3204992386 hasConcept C153180895 @default.
- W3204992386 hasConcept C154945302 @default.
- W3204992386 hasConcept C160234255 @default.
- W3204992386 hasConcept C177769412 @default.
- W3204992386 hasConcept C2776214188 @default.
- W3204992386 hasConcept C2776864781 @default.
- W3204992386 hasConcept C41008148 @default.
- W3204992386 hasConceptScore W3204992386C107673813 @default.
- W3204992386 hasConceptScore W3204992386C119857082 @default.
- W3204992386 hasConceptScore W3204992386C153083717 @default.
- W3204992386 hasConceptScore W3204992386C153180895 @default.
- W3204992386 hasConceptScore W3204992386C154945302 @default.
- W3204992386 hasConceptScore W3204992386C160234255 @default.
- W3204992386 hasConceptScore W3204992386C177769412 @default.
- W3204992386 hasConceptScore W3204992386C2776214188 @default.
- W3204992386 hasConceptScore W3204992386C2776864781 @default.
- W3204992386 hasConceptScore W3204992386C41008148 @default.
- W3204992386 hasLocation W32049923861 @default.
- W3204992386 hasOpenAccess W3204992386 @default.
- W3204992386 hasPrimaryLocation W32049923861 @default.
- W3204992386 hasRelatedWork W2042990026 @default.
- W3204992386 hasRelatedWork W2248934801 @default.
- W3204992386 hasRelatedWork W2275207081 @default.
- W3204992386 hasRelatedWork W2619415666 @default.
- W3204992386 hasRelatedWork W2920987997 @default.
- W3204992386 hasRelatedWork W2948421839 @default.
- W3204992386 hasRelatedWork W2950187163 @default.
- W3204992386 hasRelatedWork W2950767550 @default.
- W3204992386 hasRelatedWork W2951771921 @default.
- W3204992386 hasRelatedWork W2953096735 @default.
- W3204992386 hasRelatedWork W2998028256 @default.
- W3204992386 hasRelatedWork W3014266848 @default.
- W3204992386 hasRelatedWork W3034097097 @default.
- W3204992386 hasRelatedWork W3036118961 @default.
- W3204992386 hasRelatedWork W3126327443 @default.
- W3204992386 hasRelatedWork W3134908072 @default.
- W3204992386 hasRelatedWork W3186814551 @default.
- W3204992386 hasRelatedWork W586715238 @default.
- W3204992386 hasRelatedWork W81081615 @default.
- W3204992386 hasRelatedWork W2187960569 @default.
- W3204992386 isParatext "false" @default.
- W3204992386 isRetracted "false" @default.
- W3204992386 magId "3204992386" @default.
- W3204992386 workType "article" @default.