Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386044529> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4386044529 abstract "For learning-based sound event localization and detection (SELD) methods, different acoustic environments in the training and test sets may result in large performance differences in the validation and evaluation stages. Different environments, such as different sizes of rooms, different reverberation times, and different background noise, may be reasons for a learning-based system to fail. On the other hand, acquiring annotated spatial sound event samples, which include onset and offset time stamps, class types of sound events, and direction-of-arrival (DOA) of sound sources is very expensive. In addition, deploying a SELD system in a new environment often poses challenges due to time-consuming training and fine-tuning processes. To address these issues, we propose Meta-SELD, which applies meta-learning methods to achieve fast adaptation to new environments. More specifically, based on Model Agnostic Meta-Learning (MAML), the proposed Meta-SELD aims to find good meta-initialized parameters to adapt to new environments with only a small number of samples and parameter updating iterations. We can then quickly adapt the meta-trained SELD model to unseen environments. Our experiments compare fine-tuning methods from pre-trained SELD models with our Meta-SELD on the Sony-TAU Realistic Spatial Soundscapes 2023 (STARSSS23) dataset. The evaluation results demonstrate the effectiveness of Meta-SELD when adapting to new environments." @default.
- W4386044529 created "2023-08-22" @default.
- W4386044529 creator A5028105492 @default.
- W4386044529 creator A5028989611 @default.
- W4386044529 creator A5034422993 @default.
- W4386044529 creator A5037691180 @default.
- W4386044529 creator A5047649448 @default.
- W4386044529 creator A5066967599 @default.
- W4386044529 creator A5088185643 @default.
- W4386044529 creator A5088852046 @default.
- W4386044529 date "2023-08-17" @default.
- W4386044529 modified "2023-10-18" @default.
- W4386044529 title "META-SELD: Meta-Learning for Fast Adaptation to the new environment in Sound Event Localization and Detection" @default.
- W4386044529 doi "https://doi.org/10.48550/arxiv.2308.08847" @default.
- W4386044529 hasPublicationYear "2023" @default.
- W4386044529 type Work @default.
- W4386044529 citedByCount "0" @default.
- W4386044529 crossrefType "posted-content" @default.
- W4386044529 hasAuthorship W4386044529A5028105492 @default.
- W4386044529 hasAuthorship W4386044529A5028989611 @default.
- W4386044529 hasAuthorship W4386044529A5034422993 @default.
- W4386044529 hasAuthorship W4386044529A5037691180 @default.
- W4386044529 hasAuthorship W4386044529A5047649448 @default.
- W4386044529 hasAuthorship W4386044529A5066967599 @default.
- W4386044529 hasAuthorship W4386044529A5088185643 @default.
- W4386044529 hasAuthorship W4386044529A5088852046 @default.
- W4386044529 hasBestOaLocation W43860445291 @default.
- W4386044529 hasConcept C119857082 @default.
- W4386044529 hasConcept C121332964 @default.
- W4386044529 hasConcept C139807058 @default.
- W4386044529 hasConcept C154945302 @default.
- W4386044529 hasConcept C169760540 @default.
- W4386044529 hasConcept C24890656 @default.
- W4386044529 hasConcept C2779662365 @default.
- W4386044529 hasConcept C41008148 @default.
- W4386044529 hasConcept C62520636 @default.
- W4386044529 hasConcept C86803240 @default.
- W4386044529 hasConcept C95851461 @default.
- W4386044529 hasConceptScore W4386044529C119857082 @default.
- W4386044529 hasConceptScore W4386044529C121332964 @default.
- W4386044529 hasConceptScore W4386044529C139807058 @default.
- W4386044529 hasConceptScore W4386044529C154945302 @default.
- W4386044529 hasConceptScore W4386044529C169760540 @default.
- W4386044529 hasConceptScore W4386044529C24890656 @default.
- W4386044529 hasConceptScore W4386044529C2779662365 @default.
- W4386044529 hasConceptScore W4386044529C41008148 @default.
- W4386044529 hasConceptScore W4386044529C62520636 @default.
- W4386044529 hasConceptScore W4386044529C86803240 @default.
- W4386044529 hasConceptScore W4386044529C95851461 @default.
- W4386044529 hasLocation W43860445291 @default.
- W4386044529 hasOpenAccess W4386044529 @default.
- W4386044529 hasPrimaryLocation W43860445291 @default.
- W4386044529 hasRelatedWork W1571518467 @default.
- W4386044529 hasRelatedWork W2961085424 @default.
- W4386044529 hasRelatedWork W3046775127 @default.
- W4386044529 hasRelatedWork W3170094116 @default.
- W4386044529 hasRelatedWork W4285260836 @default.
- W4386044529 hasRelatedWork W4286629047 @default.
- W4386044529 hasRelatedWork W4306321456 @default.
- W4386044529 hasRelatedWork W4306674287 @default.
- W4386044529 hasRelatedWork W87991986 @default.
- W4386044529 hasRelatedWork W4224009465 @default.
- W4386044529 isParatext "false" @default.
- W4386044529 isRetracted "false" @default.
- W4386044529 workType "article" @default.