Matches in SemOpenAlex for { <https://semopenalex.org/work/W4213209776> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4213209776 endingPage "366" @default.
- W4213209776 startingPage "366" @default.
- W4213209776 abstract "Polyphonic sound event detection (SED) is the task of detecting the time stamps and the class of sound event that occurred during a recording. Real life sound events overlap in recordings, and their durations vary dramatically, making them even harder to recognize. In this paper, we propose Convolutional Recurrent Neural Networks (CRNNs) to extract hidden state feature representations; then, a self-attention mechanism using a symmetric score function is introduced to memorize long-range dependencies of features that the CRNNs extract. Furthermore, we propose to use memory-controlled self-attention to explicitly compute the relations between time steps in audio representation embedding. Then, we propose a strategy for adaptive memory-controlled self-attention mechanisms. Moreover, we applied semi-supervised learning, namely, mean teacher–student methods, to exploit unlabeled audio data. The proposed methods all performed well in the Detection and Classification of Acoustic Scenes and Events (DCASE) 2017 Sound Event Detection in Real Life Audio (task3) test and the DCASE 2021 Sound Event Detection and Separation in Domestic Environments (task4) test. In DCASE 2017 task3, our model surpassed the challenge’s winning system’s F1-score by 6.8%. We show that the proposed adaptive memory-controlled model reached the same performance level as a fixed attention width model. Experimental results indicate that the proposed attention mechanism is able to improve sound event detection. In DCASE 2021 task4, we investigated various pooling strategies in two scenarios. In addition, we found that in weakly labeled semi-supervised sound event detection, building an attention layer on top of the CRNN is needless repetition. This conclusion could be applied to other multi-instance learning problems." @default.
- W4213209776 created "2022-02-24" @default.
- W4213209776 creator A5027790457 @default.
- W4213209776 creator A5033082988 @default.
- W4213209776 creator A5035322817 @default.
- W4213209776 creator A5041873456 @default.
- W4213209776 date "2022-02-12" @default.
- W4213209776 modified "2023-09-26" @default.
- W4213209776 title "Adaptive Memory-Controlled Self-Attention for Polyphonic Sound Event Detection" @default.
- W4213209776 cites W1844944916 @default.
- W4213209776 cites W2408239454 @default.
- W4213209776 cites W2529483679 @default.
- W4213209776 cites W2799258971 @default.
- W4213209776 cites W2809183397 @default.
- W4213209776 cites W2938440247 @default.
- W4213209776 cites W2963128891 @default.
- W4213209776 cites W2963610932 @default.
- W4213209776 cites W2964891022 @default.
- W4213209776 cites W2973152780 @default.
- W4213209776 cites W2987999870 @default.
- W4213209776 cites W3015190346 @default.
- W4213209776 cites W3017521796 @default.
- W4213209776 cites W3124216180 @default.
- W4213209776 cites W3162400960 @default.
- W4213209776 cites W821549425 @default.
- W4213209776 doi "https://doi.org/10.3390/sym14020366" @default.
- W4213209776 hasPublicationYear "2022" @default.
- W4213209776 type Work @default.
- W4213209776 citedByCount "2" @default.
- W4213209776 countsByYear W42132097762022 @default.
- W4213209776 crossrefType "journal-article" @default.
- W4213209776 hasAuthorship W4213209776A5027790457 @default.
- W4213209776 hasAuthorship W4213209776A5033082988 @default.
- W4213209776 hasAuthorship W4213209776A5035322817 @default.
- W4213209776 hasAuthorship W4213209776A5041873456 @default.
- W4213209776 hasBestOaLocation W42132097761 @default.
- W4213209776 hasConcept C121332964 @default.
- W4213209776 hasConcept C138885662 @default.
- W4213209776 hasConcept C145420912 @default.
- W4213209776 hasConcept C153180895 @default.
- W4213209776 hasConcept C154945302 @default.
- W4213209776 hasConcept C162324750 @default.
- W4213209776 hasConcept C187736073 @default.
- W4213209776 hasConcept C2776401178 @default.
- W4213209776 hasConcept C2779662365 @default.
- W4213209776 hasConcept C2780451532 @default.
- W4213209776 hasConcept C28490314 @default.
- W4213209776 hasConcept C30038468 @default.
- W4213209776 hasConcept C33923547 @default.
- W4213209776 hasConcept C41008148 @default.
- W4213209776 hasConcept C41608201 @default.
- W4213209776 hasConcept C41895202 @default.
- W4213209776 hasConcept C62520636 @default.
- W4213209776 hasConceptScore W4213209776C121332964 @default.
- W4213209776 hasConceptScore W4213209776C138885662 @default.
- W4213209776 hasConceptScore W4213209776C145420912 @default.
- W4213209776 hasConceptScore W4213209776C153180895 @default.
- W4213209776 hasConceptScore W4213209776C154945302 @default.
- W4213209776 hasConceptScore W4213209776C162324750 @default.
- W4213209776 hasConceptScore W4213209776C187736073 @default.
- W4213209776 hasConceptScore W4213209776C2776401178 @default.
- W4213209776 hasConceptScore W4213209776C2779662365 @default.
- W4213209776 hasConceptScore W4213209776C2780451532 @default.
- W4213209776 hasConceptScore W4213209776C28490314 @default.
- W4213209776 hasConceptScore W4213209776C30038468 @default.
- W4213209776 hasConceptScore W4213209776C33923547 @default.
- W4213209776 hasConceptScore W4213209776C41008148 @default.
- W4213209776 hasConceptScore W4213209776C41608201 @default.
- W4213209776 hasConceptScore W4213209776C41895202 @default.
- W4213209776 hasConceptScore W4213209776C62520636 @default.
- W4213209776 hasFunder F4320321001 @default.
- W4213209776 hasIssue "2" @default.
- W4213209776 hasLocation W42132097761 @default.
- W4213209776 hasLocation W42132097762 @default.
- W4213209776 hasOpenAccess W4213209776 @default.
- W4213209776 hasPrimaryLocation W42132097761 @default.
- W4213209776 hasRelatedWork W2050745433 @default.
- W4213209776 hasRelatedWork W2053849704 @default.
- W4213209776 hasRelatedWork W2081647779 @default.
- W4213209776 hasRelatedWork W2315316873 @default.
- W4213209776 hasRelatedWork W2380865367 @default.
- W4213209776 hasRelatedWork W2382607599 @default.
- W4213209776 hasRelatedWork W2546942002 @default.
- W4213209776 hasRelatedWork W2938470310 @default.
- W4213209776 hasRelatedWork W2970216048 @default.
- W4213209776 hasRelatedWork W4308629216 @default.
- W4213209776 hasVolume "14" @default.
- W4213209776 isParatext "false" @default.
- W4213209776 isRetracted "false" @default.
- W4213209776 workType "article" @default.