FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385164055> ?p ?o ?g. }

• W4385164055 endingPage "109541" @default.
• W4385164055 startingPage "109541" @default.
• W4385164055 abstract "The goal of sound event localization and detection (SELD) is to detect the temporal occurrence activity of a known set of sound events and locate them in the spatial space. We argue that acquiring a large audio dataset is essential for one deep neural network-based SELD system learned as one supervised task. Nonetheless, gathering and annotating such datasets is a costly and time-intensive process. Hence, various data augmentation methods have attracted attention as a solution to increase sample diversity from the limited collections. In this paper, we propose to augment the limited audio samples for the deep neural network-based SELD system in two ways. One is the hierarchical audio augmentation chain (HAAC) proposed for the activity-coupled Cartesian direction of arrival output representation (ACCDOA) described SELD task. It consists of three waveform and spectrogram augmentation techniques, which are exquisitely assembled from the feature map augmentation to audio channel swapping, and finally sample mixup. Second, we propose to augment the training samples by generating more simulated audio samples and making the selected sound events list publicly available to the community. Experiments on the STARSS22 dataset showed that our HAAC audio augmentation chain greatly improved the SELD performance, which increased the sound event detection score by 24% and decreased the localization error by 12.1°. We demonstrate it’s one simple yet effective approach, compared to other data augmentation methods. Moreover, with more simulated audio samples, generated by convolving selected sound events with SRIRs, used for training, the SELD performance was improved greatly." @default.
• W4385164055 created "2023-07-24" @default.
• W4385164055 creator A5000114367 @default.
• W4385164055 creator A5023173312 @default.
• W4385164055 creator A5026827945 @default.
• W4385164055 creator A5030233306 @default.
• W4385164055 date "2023-08-01" @default.
• W4385164055 modified "2023-10-06" @default.
• W4385164055 title "HAAC: Hierarchical audio augmentation chain for ACCDOA described sound event localization and detection" @default.
• W4385164055 cites W2052666245 @default.
• W4385164055 cites W2535477605 @default.
• W4385164055 cites W2769428625 @default.
• W4385164055 cites W2770832746 @default.
• W4385164055 cites W2775794021 @default.
• W4385164055 cites W2792333172 @default.
• W4385164055 cites W2807015669 @default.
• W4385164055 cites W2810934215 @default.
• W4385164055 cites W2888793942 @default.
• W4385164055 cites W2936774411 @default.
• W4385164055 cites W2982680886 @default.
• W4385164055 cites W3102937397 @default.
• W4385164055 cites W3197097128 @default.
• W4385164055 cites W4205434973 @default.
• W4385164055 cites W4205689591 @default.
• W4385164055 cites W4220779383 @default.
• W4385164055 cites W4229045152 @default.
• W4385164055 cites W4309763950 @default.
• W4385164055 cites W4313594820 @default.
• W4385164055 cites W4321793287 @default.
• W4385164055 doi "https://doi.org/10.1016/j.apacoust.2023.109541" @default.
• W4385164055 hasPublicationYear "2023" @default.
• W4385164055 type Work @default.
• W4385164055 citedByCount "0" @default.
• W4385164055 crossrefType "journal-article" @default.
• W4385164055 hasAuthorship W4385164055A5000114367 @default.
• W4385164055 hasAuthorship W4385164055A5023173312 @default.
• W4385164055 hasAuthorship W4385164055A5026827945 @default.
• W4385164055 hasAuthorship W4385164055A5030233306 @default.
• W4385164055 hasConcept C121332964 @default.
• W4385164055 hasConcept C127220857 @default.
• W4385164055 hasConcept C128422554 @default.
• W4385164055 hasConcept C13895895 @default.
• W4385164055 hasConcept C153180895 @default.
• W4385164055 hasConcept C154945302 @default.
• W4385164055 hasConcept C162324750 @default.
• W4385164055 hasConcept C177264268 @default.
• W4385164055 hasConcept C17744445 @default.
• W4385164055 hasConcept C185592680 @default.
• W4385164055 hasConcept C187736073 @default.
• W4385164055 hasConcept C197424946 @default.
• W4385164055 hasConcept C198531522 @default.
• W4385164055 hasConcept C199360897 @default.
• W4385164055 hasConcept C199539241 @default.
• W4385164055 hasConcept C24890656 @default.
• W4385164055 hasConcept C2776359362 @default.
• W4385164055 hasConcept C2779662365 @default.
• W4385164055 hasConcept C2780451532 @default.
• W4385164055 hasConcept C28490314 @default.
• W4385164055 hasConcept C41008148 @default.
• W4385164055 hasConcept C43617362 @default.
• W4385164055 hasConcept C45273575 @default.
• W4385164055 hasConcept C554190296 @default.
• W4385164055 hasConcept C62520636 @default.
• W4385164055 hasConcept C64922751 @default.
• W4385164055 hasConcept C76155785 @default.
• W4385164055 hasConcept C94625758 @default.
• W4385164055 hasConceptScore W4385164055C121332964 @default.
• W4385164055 hasConceptScore W4385164055C127220857 @default.
• W4385164055 hasConceptScore W4385164055C128422554 @default.
• W4385164055 hasConceptScore W4385164055C13895895 @default.
• W4385164055 hasConceptScore W4385164055C153180895 @default.
• W4385164055 hasConceptScore W4385164055C154945302 @default.
• W4385164055 hasConceptScore W4385164055C162324750 @default.
• W4385164055 hasConceptScore W4385164055C177264268 @default.
• W4385164055 hasConceptScore W4385164055C17744445 @default.
• W4385164055 hasConceptScore W4385164055C185592680 @default.
• W4385164055 hasConceptScore W4385164055C187736073 @default.
• W4385164055 hasConceptScore W4385164055C197424946 @default.
• W4385164055 hasConceptScore W4385164055C198531522 @default.
• W4385164055 hasConceptScore W4385164055C199360897 @default.
• W4385164055 hasConceptScore W4385164055C199539241 @default.
• W4385164055 hasConceptScore W4385164055C24890656 @default.
• W4385164055 hasConceptScore W4385164055C2776359362 @default.
• W4385164055 hasConceptScore W4385164055C2779662365 @default.
• W4385164055 hasConceptScore W4385164055C2780451532 @default.
• W4385164055 hasConceptScore W4385164055C28490314 @default.
• W4385164055 hasConceptScore W4385164055C41008148 @default.
• W4385164055 hasConceptScore W4385164055C43617362 @default.
• W4385164055 hasConceptScore W4385164055C45273575 @default.
• W4385164055 hasConceptScore W4385164055C554190296 @default.
• W4385164055 hasConceptScore W4385164055C62520636 @default.
• W4385164055 hasConceptScore W4385164055C64922751 @default.
• W4385164055 hasConceptScore W4385164055C76155785 @default.
• W4385164055 hasConceptScore W4385164055C94625758 @default.
• W4385164055 hasFunder F4320321001 @default.
• W4385164055 hasLocation W43851640551 @default.
• W4385164055 hasOpenAccess W4385164055 @default.
• W4385164055 hasPrimaryLocation W43851640551 @default.

• next