Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367000209> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4367000209 abstract "In a multi-channel separation task with multiple speakers, we aim to recover all individual speech signals from the mixture. In contrast to single-channel approaches, which rely on the different spectro-temporal characteristics of the speech signals, multi-channel approaches should additionally utilize the different spatial locations of the sources for a more powerful separation especially when the number of sources increases. To enhance the spatial processing in a multi-channel source separation scenario, in this work, we propose a deep neural network (DNN) based spatially selective filter (SSF) that can be spatially steered to extract the speaker of interest by initializing a recurrent neural network layer with the target direction. We compare the proposed SSF with a common end-to-end direct separation (DS) approach trained using utterance-wise permutation invariant training (PIT), which only implicitly learns to perform spatial filtering. We show that the SSF has a clear advantage over a DS approach with the same underlying network architecture when there are more than two speakers in the mixture, which can be attributed to a better use of the spatial information. Furthermore, we find that the SSF generalizes much better to additional noise sources that were not seen during training." @default.
- W4367000209 created "2023-04-27" @default.
- W4367000209 creator A5073497010 @default.
- W4367000209 creator A5087022569 @default.
- W4367000209 date "2023-04-24" @default.
- W4367000209 modified "2023-09-24" @default.
- W4367000209 title "Multi-channel Speech Separation Using Spatially Selective Deep Non-linear Filters" @default.
- W4367000209 doi "https://doi.org/10.48550/arxiv.2304.12023" @default.
- W4367000209 hasPublicationYear "2023" @default.
- W4367000209 type Work @default.
- W4367000209 citedByCount "0" @default.
- W4367000209 crossrefType "posted-content" @default.
- W4367000209 hasAuthorship W4367000209A5073497010 @default.
- W4367000209 hasAuthorship W4367000209A5087022569 @default.
- W4367000209 hasBestOaLocation W43670002091 @default.
- W4367000209 hasConcept C106131492 @default.
- W4367000209 hasConcept C114466953 @default.
- W4367000209 hasConcept C119857082 @default.
- W4367000209 hasConcept C121475858 @default.
- W4367000209 hasConcept C127162648 @default.
- W4367000209 hasConcept C153180895 @default.
- W4367000209 hasConcept C154945302 @default.
- W4367000209 hasConcept C199360897 @default.
- W4367000209 hasConcept C2776061190 @default.
- W4367000209 hasConcept C2776864781 @default.
- W4367000209 hasConcept C28490314 @default.
- W4367000209 hasConcept C31972630 @default.
- W4367000209 hasConcept C41008148 @default.
- W4367000209 hasConcept C50644808 @default.
- W4367000209 hasConcept C76155785 @default.
- W4367000209 hasConceptScore W4367000209C106131492 @default.
- W4367000209 hasConceptScore W4367000209C114466953 @default.
- W4367000209 hasConceptScore W4367000209C119857082 @default.
- W4367000209 hasConceptScore W4367000209C121475858 @default.
- W4367000209 hasConceptScore W4367000209C127162648 @default.
- W4367000209 hasConceptScore W4367000209C153180895 @default.
- W4367000209 hasConceptScore W4367000209C154945302 @default.
- W4367000209 hasConceptScore W4367000209C199360897 @default.
- W4367000209 hasConceptScore W4367000209C2776061190 @default.
- W4367000209 hasConceptScore W4367000209C2776864781 @default.
- W4367000209 hasConceptScore W4367000209C28490314 @default.
- W4367000209 hasConceptScore W4367000209C31972630 @default.
- W4367000209 hasConceptScore W4367000209C41008148 @default.
- W4367000209 hasConceptScore W4367000209C50644808 @default.
- W4367000209 hasConceptScore W4367000209C76155785 @default.
- W4367000209 hasLocation W43670002091 @default.
- W4367000209 hasOpenAccess W4367000209 @default.
- W4367000209 hasPrimaryLocation W43670002091 @default.
- W4367000209 hasRelatedWork W1995163783 @default.
- W4367000209 hasRelatedWork W2061502286 @default.
- W4367000209 hasRelatedWork W2072817066 @default.
- W4367000209 hasRelatedWork W2360355564 @default.
- W4367000209 hasRelatedWork W2936423518 @default.
- W4367000209 hasRelatedWork W2953368614 @default.
- W4367000209 hasRelatedWork W3016066622 @default.
- W4367000209 hasRelatedWork W4205367281 @default.
- W4367000209 hasRelatedWork W4206652807 @default.
- W4367000209 hasRelatedWork W4288055416 @default.
- W4367000209 isParatext "false" @default.
- W4367000209 isRetracted "false" @default.
- W4367000209 workType "article" @default.