FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2994867748> ?p ?o ?g. }

• W2994867748 abstract "Sound event detection (SED) is a task to detect sound events in an audio recording. One challenge of the SED task is that many datasets such as the Detection and Classification of Acoustic Scenes and Events (DCASE) datasets are weakly labelled. That is, there are only audio tags for each audio clip without the onset and offset times of sound events. qk{We compare segment-wise and clip-wise training for SED that is lacking in previous works. We propose a convolutional neural network transformer (CNN-Transfomer) for audio tagging and SED, and show that CNN-Transformer performs similarly to a convolutional recurrent neural network (CRNN)}. Another challenge of SED is that thresholds are required for detecting sound events. Previous works set thresholds empirically, and are not an optimal approaches. To solve this problem, we propose an automatic threshold optimization method. The first stage is to optimize the system with respect to metrics that do not depend on thresholds, such as mean average precision (mAP). The second stage is to optimize the thresholds with respect to metrics that depends on those thresholds. Our proposed automatic threshold optimization system achieves a state-of-the-art audio tagging F1 of 0.646, outperforming that without threshold optimization of 0.629, and a sound event detection F1 of 0.584, outperforming that without threshold optimization of 0.564." @default.
• W2994867748 created "2019-12-26" @default.
• W2994867748 creator A5010277066 @default.
• W2994867748 creator A5037691180 @default.
• W2994867748 creator A5066967599 @default.
• W2994867748 creator A5072482416 @default.
• W2994867748 date "2019-12-10" @default.
• W2994867748 modified "2023-10-14" @default.
• W2994867748 title "Sound Event Detection of Weakly Labelled Data with CNN-Transformer and Automatic Threshold Optimization" @default.
• W2994867748 cites W1650531274 @default.
• W2994867748 cites W1665214252 @default.
• W2994867748 cites W179875071 @default.
• W2994867748 cites W1836465849 @default.
• W2994867748 cites W1995562189 @default.
• W2994867748 cites W2008415856 @default.
• W2994867748 cites W2062227835 @default.
• W2994867748 cites W2064675550 @default.
• W2994867748 cites W2086384421 @default.
• W2994867748 cites W2157331557 @default.
• W2994867748 cites W2163605009 @default.
• W2994867748 cites W2191779130 @default.
• W2994867748 cites W2354870669 @default.
• W2994867748 cites W2408239454 @default.
• W2994867748 cites W2526050071 @default.
• W2994867748 cites W2566935005 @default.
• W2994867748 cites W2591013610 @default.
• W2994867748 cites W2592944988 @default.
• W2994867748 cites W2593116425 @default.
• W2994867748 cites W2618269622 @default.
• W2994867748 cites W2654517624 @default.
• W2994867748 cites W2723513260 @default.
• W2994867748 cites W2745616976 @default.
• W2994867748 cites W2775505379 @default.
• W2994867748 cites W2778014476 @default.
• W2994867748 cites W2807788374 @default.
• W2994867748 cites W2883935097 @default.
• W2994867748 cites W2885392124 @default.
• W2994867748 cites W2903539539 @default.
• W2994867748 cites W2929983093 @default.
• W2994867748 cites W2952395326 @default.
• W2994867748 cites W2959539607 @default.
• W2994867748 cites W2963099423 @default.
• W2994867748 cites W2963158330 @default.
• W2994867748 cites W2963341956 @default.
• W2994867748 cites W2963369619 @default.
• W2994867748 cites W2963399829 @default.
• W2994867748 cites W2963403868 @default.
• W2994867748 cites W2963451564 @default.
• W2994867748 cites W2963493667 @default.
• W2994867748 cites W2963723765 @default.
• W2994867748 cites W2964121744 @default.
• W2994867748 cites W2964891022 @default.
• W2994867748 cites W2973109987 @default.
• W2994867748 cites W2997266872 @default.
• W2994867748 cites W2998304428 @default.
• W2994867748 cites W3027169863 @default.
• W2994867748 doi "https://doi.org/10.48550/arxiv.1912.04761" @default.
• W2994867748 hasPublicationYear "2019" @default.
• W2994867748 type Work @default.
• W2994867748 sameAs 2994867748 @default.
• W2994867748 citedByCount "2" @default.
• W2994867748 countsByYear W29948677482020 @default.
• W2994867748 countsByYear W29948677482021 @default.
• W2994867748 crossrefType "posted-content" @default.
• W2994867748 hasAuthorship W2994867748A5010277066 @default.
• W2994867748 hasAuthorship W2994867748A5037691180 @default.
• W2994867748 hasAuthorship W2994867748A5066967599 @default.
• W2994867748 hasAuthorship W2994867748A5072482416 @default.
• W2994867748 hasBestOaLocation W29948677481 @default.
• W2994867748 hasConcept C121332964 @default.
• W2994867748 hasConcept C153180895 @default.
• W2994867748 hasConcept C154945302 @default.
• W2994867748 hasConcept C165801399 @default.
• W2994867748 hasConcept C175291020 @default.
• W2994867748 hasConcept C199360897 @default.
• W2994867748 hasConcept C28490314 @default.
• W2994867748 hasConcept C41008148 @default.
• W2994867748 hasConcept C62520636 @default.
• W2994867748 hasConcept C66322947 @default.
• W2994867748 hasConcept C81363708 @default.
• W2994867748 hasConceptScore W2994867748C121332964 @default.
• W2994867748 hasConceptScore W2994867748C153180895 @default.
• W2994867748 hasConceptScore W2994867748C154945302 @default.
• W2994867748 hasConceptScore W2994867748C165801399 @default.
• W2994867748 hasConceptScore W2994867748C175291020 @default.
• W2994867748 hasConceptScore W2994867748C199360897 @default.
• W2994867748 hasConceptScore W2994867748C28490314 @default.
• W2994867748 hasConceptScore W2994867748C41008148 @default.
• W2994867748 hasConceptScore W2994867748C62520636 @default.
• W2994867748 hasConceptScore W2994867748C66322947 @default.
• W2994867748 hasConceptScore W2994867748C81363708 @default.
• W2994867748 hasLocation W29948677481 @default.
• W2994867748 hasLocation W29948677482 @default.
• W2994867748 hasOpenAccess W2994867748 @default.
• W2994867748 hasPrimaryLocation W29948677481 @default.
• W2994867748 hasRelatedWork W2175746458 @default.
• W2994867748 hasRelatedWork W2732542196 @default.
• W2994867748 hasRelatedWork W2738221750 @default.
• W2994867748 hasRelatedWork W2758063741 @default.
• W2994867748 hasRelatedWork W2760085659 @default.

• next