Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297686742> ?p ?o ?g. }
Showing items 1 to 59 of
59
with 100 items per page.
- W4297686742 abstract "The development of audio event recognition systems require labeled training data, which are generally hard to obtain. One promising source of recordings of audio events is the large amount of multimedia data on the web. In particular, if the audio content analysis must itself be performed on web audio, it is important to train the recognizers themselves from such data. Training from these web data, however, poses several challenges, the most important being the availability of labels: labels, if any, that may be obtained for the data are generally weak, and not of the kind conventionally required for training detectors or classifiers. We propose that learning algorithms that can exploit weak labels offer an effective method to learn from web data. We then propose a robust and efficient deep convolutional neural network (CNN) based framework to learn audio event recognizers from weakly labeled data. The proposed method can train from and analyze recordings of variable length in an efficient manner and outperforms a network trained with strongly labeled web data by a considerable margin. Moreover, even though we learn from weakly labeled data, where event time stamps within the recording are not available during training, our proposed framework is able to localize events during the inference stage." @default.
- W4297686742 created "2022-09-30" @default.
- W4297686742 creator A5016771874 @default.
- W4297686742 creator A5066528816 @default.
- W4297686742 date "2017-07-09" @default.
- W4297686742 modified "2023-09-28" @default.
- W4297686742 title "Deep CNN Framework for Audio Event Recognition using Weakly Labeled Web Data" @default.
- W4297686742 doi "https://doi.org/10.48550/arxiv.1707.02530" @default.
- W4297686742 hasPublicationYear "2017" @default.
- W4297686742 type Work @default.
- W4297686742 citedByCount "0" @default.
- W4297686742 crossrefType "posted-content" @default.
- W4297686742 hasAuthorship W4297686742A5016771874 @default.
- W4297686742 hasAuthorship W4297686742A5066528816 @default.
- W4297686742 hasBestOaLocation W42976867421 @default.
- W4297686742 hasConcept C108583219 @default.
- W4297686742 hasConcept C119857082 @default.
- W4297686742 hasConcept C121332964 @default.
- W4297686742 hasConcept C154945302 @default.
- W4297686742 hasConcept C165696696 @default.
- W4297686742 hasConcept C2776145971 @default.
- W4297686742 hasConcept C2776214188 @default.
- W4297686742 hasConcept C2779662365 @default.
- W4297686742 hasConcept C28490314 @default.
- W4297686742 hasConcept C38652104 @default.
- W4297686742 hasConcept C41008148 @default.
- W4297686742 hasConcept C62520636 @default.
- W4297686742 hasConcept C774472 @default.
- W4297686742 hasConcept C81363708 @default.
- W4297686742 hasConceptScore W4297686742C108583219 @default.
- W4297686742 hasConceptScore W4297686742C119857082 @default.
- W4297686742 hasConceptScore W4297686742C121332964 @default.
- W4297686742 hasConceptScore W4297686742C154945302 @default.
- W4297686742 hasConceptScore W4297686742C165696696 @default.
- W4297686742 hasConceptScore W4297686742C2776145971 @default.
- W4297686742 hasConceptScore W4297686742C2776214188 @default.
- W4297686742 hasConceptScore W4297686742C2779662365 @default.
- W4297686742 hasConceptScore W4297686742C28490314 @default.
- W4297686742 hasConceptScore W4297686742C38652104 @default.
- W4297686742 hasConceptScore W4297686742C41008148 @default.
- W4297686742 hasConceptScore W4297686742C62520636 @default.
- W4297686742 hasConceptScore W4297686742C774472 @default.
- W4297686742 hasConceptScore W4297686742C81363708 @default.
- W4297686742 hasLocation W42976867421 @default.
- W4297686742 hasOpenAccess W4297686742 @default.
- W4297686742 hasPrimaryLocation W42976867421 @default.
- W4297686742 hasRelatedWork W2337926734 @default.
- W4297686742 hasRelatedWork W2731899572 @default.
- W4297686742 hasRelatedWork W2953238046 @default.
- W4297686742 hasRelatedWork W2963058055 @default.
- W4297686742 hasRelatedWork W4300631627 @default.
- W4297686742 hasRelatedWork W4311257506 @default.
- W4297686742 hasRelatedWork W4312417841 @default.
- W4297686742 hasRelatedWork W4320802194 @default.
- W4297686742 hasRelatedWork W4321369474 @default.
- W4297686742 hasRelatedWork W4366224123 @default.
- W4297686742 isParatext "false" @default.
- W4297686742 isRetracted "false" @default.
- W4297686742 workType "article" @default.