Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312857524> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4312857524 abstract "In some DNNs for audio source separation, the relevant model parameters are independent of the sampling frequency of the audio used for training. Considering the application of dialogue separation, this is shown for two DNN architectures: a U-Net and a fully-convolutional model. The models are trained with audio sampled at 8 kHz. The learned parameters are transferred to models for processing audio at 48 kHz. The separated audio sources are compared with the ones produced by the same model architectures trained with 48 kHz versions of the same training data. A listening test and computational measures show that there is no significant perceptual difference between the models trained with 8 kHz or with 48 kHz. This transferability of the learned parameters allows for a faster and computationally less costly training. It also enables using training datasets available at a lower sampling frequency than the one needed by the application at hand, or using data collections with multiple sampling frequencies." @default.
- W4312857524 created "2023-01-05" @default.
- W4312857524 creator A5021417399 @default.
- W4312857524 creator A5054389422 @default.
- W4312857524 date "2022-08-29" @default.
- W4312857524 modified "2023-09-27" @default.
- W4312857524 title "Sampling Frequency Independent Dialogue Separation" @default.
- W4312857524 cites W2127851351 @default.
- W4312857524 cites W2938709889 @default.
- W4312857524 cites W2952218014 @default.
- W4312857524 cites W2964058413 @default.
- W4312857524 cites W2968860202 @default.
- W4312857524 cites W2972411915 @default.
- W4312857524 cites W2975955714 @default.
- W4312857524 cites W2998733532 @default.
- W4312857524 cites W3037149862 @default.
- W4312857524 cites W3145029257 @default.
- W4312857524 cites W3185389098 @default.
- W4312857524 cites W3197676764 @default.
- W4312857524 cites W4205366310 @default.
- W4312857524 doi "https://doi.org/10.23919/eusipco55093.2022.9909824" @default.
- W4312857524 hasPublicationYear "2022" @default.
- W4312857524 type Work @default.
- W4312857524 citedByCount "4" @default.
- W4312857524 countsByYear W43128575242022 @default.
- W4312857524 countsByYear W43128575242023 @default.
- W4312857524 crossrefType "proceedings-article" @default.
- W4312857524 hasAuthorship W4312857524A5021417399 @default.
- W4312857524 hasAuthorship W4312857524A5054389422 @default.
- W4312857524 hasBestOaLocation W43128575242 @default.
- W4312857524 hasConcept C106131492 @default.
- W4312857524 hasConcept C119857082 @default.
- W4312857524 hasConcept C127220857 @default.
- W4312857524 hasConcept C13895895 @default.
- W4312857524 hasConcept C140331021 @default.
- W4312857524 hasConcept C140779682 @default.
- W4312857524 hasConcept C144024400 @default.
- W4312857524 hasConcept C153180895 @default.
- W4312857524 hasConcept C154945302 @default.
- W4312857524 hasConcept C177291462 @default.
- W4312857524 hasConcept C2776864781 @default.
- W4312857524 hasConcept C28490314 @default.
- W4312857524 hasConcept C31972630 @default.
- W4312857524 hasConcept C41008148 @default.
- W4312857524 hasConcept C46312422 @default.
- W4312857524 hasConcept C61272859 @default.
- W4312857524 hasConcept C64922751 @default.
- W4312857524 hasConceptScore W4312857524C106131492 @default.
- W4312857524 hasConceptScore W4312857524C119857082 @default.
- W4312857524 hasConceptScore W4312857524C127220857 @default.
- W4312857524 hasConceptScore W4312857524C13895895 @default.
- W4312857524 hasConceptScore W4312857524C140331021 @default.
- W4312857524 hasConceptScore W4312857524C140779682 @default.
- W4312857524 hasConceptScore W4312857524C144024400 @default.
- W4312857524 hasConceptScore W4312857524C153180895 @default.
- W4312857524 hasConceptScore W4312857524C154945302 @default.
- W4312857524 hasConceptScore W4312857524C177291462 @default.
- W4312857524 hasConceptScore W4312857524C2776864781 @default.
- W4312857524 hasConceptScore W4312857524C28490314 @default.
- W4312857524 hasConceptScore W4312857524C31972630 @default.
- W4312857524 hasConceptScore W4312857524C41008148 @default.
- W4312857524 hasConceptScore W4312857524C46312422 @default.
- W4312857524 hasConceptScore W4312857524C61272859 @default.
- W4312857524 hasConceptScore W4312857524C64922751 @default.
- W4312857524 hasLocation W43128575241 @default.
- W4312857524 hasLocation W43128575242 @default.
- W4312857524 hasOpenAccess W4312857524 @default.
- W4312857524 hasPrimaryLocation W43128575241 @default.
- W4312857524 hasRelatedWork W2033914206 @default.
- W4312857524 hasRelatedWork W2146076056 @default.
- W4312857524 hasRelatedWork W2151155390 @default.
- W4312857524 hasRelatedWork W2516392987 @default.
- W4312857524 hasRelatedWork W2562176306 @default.
- W4312857524 hasRelatedWork W2893763841 @default.
- W4312857524 hasRelatedWork W3107474891 @default.
- W4312857524 hasRelatedWork W3203816112 @default.
- W4312857524 hasRelatedWork W4281728463 @default.
- W4312857524 hasRelatedWork W4312857524 @default.
- W4312857524 isParatext "false" @default.
- W4312857524 isRetracted "false" @default.
- W4312857524 workType "article" @default.