Matches in SemOpenAlex for { <https://semopenalex.org/work/W3199385162> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3199385162 endingPage "240" @default.
- W3199385162 startingPage "229" @default.
- W3199385162 abstract "Modern streaming services are increasingly labeling videos based on their visual or audio content. This typically augments the use of technologies such as AI and ML by allowing to use natural speech for searching by keywords and video descriptions. Prior research has successfully provided a number of solutions for speech to text, in the case of a human speech, but this article aims to investigate possible solutions to retrieve sound events based on a natural language query, and estimate how effective and accurate they are. In this study, we specifically focus on the YamNet, AlexNet, and ResNet-50 pre-trained models to automatically classify audio samples using their respective melspectrograms into a number of predefined classes. The predefined classes can represent sounds associated with actions within a video fragment. Two tests are conducted to evaluate the performance of the models on two separate problems: audio classification and intervals retrieval based on a natural language query. Results show that the benchmarked models are comparable in terms of performance, with YamNet slightly outperforming the other two models. YamNet was able to classify single fixed-size audio samples with 92.7% accuracy and 68.75% precision while its average accuracy on intervals retrieval was 71.62% and precision was 41.95%. The investigated method may be embedded into an automated event marking architecture for streaming services." @default.
- W3199385162 created "2021-09-27" @default.
- W3199385162 creator A5004375212 @default.
- W3199385162 creator A5010458580 @default.
- W3199385162 creator A5044709278 @default.
- W3199385162 creator A5045970461 @default.
- W3199385162 date "2020-01-01" @default.
- W3199385162 modified "2023-10-04" @default.
- W3199385162 title "Audio Interval Retrieval Using Convolutional Neural Networks" @default.
- W3199385162 cites W1568422127 @default.
- W3199385162 cites W1607419436 @default.
- W3199385162 cites W1970578576 @default.
- W3199385162 cites W2003026766 @default.
- W3199385162 cites W2011046539 @default.
- W3199385162 cites W2015433306 @default.
- W3199385162 cites W2046134527 @default.
- W3199385162 cites W2078306367 @default.
- W3199385162 cites W2081008303 @default.
- W3199385162 cites W2139762313 @default.
- W3199385162 cites W2151044017 @default.
- W3199385162 cites W2159277110 @default.
- W3199385162 cites W2165525622 @default.
- W3199385162 cites W2194775991 @default.
- W3199385162 cites W2526050071 @default.
- W3199385162 cites W2583662698 @default.
- W3199385162 cites W2588534625 @default.
- W3199385162 cites W2593116425 @default.
- W3199385162 cites W2618530766 @default.
- W3199385162 cites W2620760558 @default.
- W3199385162 cites W2791602430 @default.
- W3199385162 cites W2894145431 @default.
- W3199385162 cites W2962910007 @default.
- W3199385162 cites W3104862079 @default.
- W3199385162 cites W4255842403 @default.
- W3199385162 doi "https://doi.org/10.1007/978-3-030-65726-0_21" @default.
- W3199385162 hasPublicationYear "2020" @default.
- W3199385162 type Work @default.
- W3199385162 sameAs 3199385162 @default.
- W3199385162 citedByCount "5" @default.
- W3199385162 countsByYear W31993851622021 @default.
- W3199385162 countsByYear W31993851622022 @default.
- W3199385162 countsByYear W31993851622023 @default.
- W3199385162 crossrefType "book-chapter" @default.
- W3199385162 hasAuthorship W3199385162A5004375212 @default.
- W3199385162 hasAuthorship W3199385162A5010458580 @default.
- W3199385162 hasAuthorship W3199385162A5044709278 @default.
- W3199385162 hasAuthorship W3199385162A5045970461 @default.
- W3199385162 hasBestOaLocation W31993851622 @default.
- W3199385162 hasConcept C114614502 @default.
- W3199385162 hasConcept C120665830 @default.
- W3199385162 hasConcept C121332964 @default.
- W3199385162 hasConcept C154945302 @default.
- W3199385162 hasConcept C192209626 @default.
- W3199385162 hasConcept C195324797 @default.
- W3199385162 hasConcept C204321447 @default.
- W3199385162 hasConcept C2778067643 @default.
- W3199385162 hasConcept C2779662365 @default.
- W3199385162 hasConcept C28490314 @default.
- W3199385162 hasConcept C33923547 @default.
- W3199385162 hasConcept C41008148 @default.
- W3199385162 hasConcept C62520636 @default.
- W3199385162 hasConcept C81363708 @default.
- W3199385162 hasConceptScore W3199385162C114614502 @default.
- W3199385162 hasConceptScore W3199385162C120665830 @default.
- W3199385162 hasConceptScore W3199385162C121332964 @default.
- W3199385162 hasConceptScore W3199385162C154945302 @default.
- W3199385162 hasConceptScore W3199385162C192209626 @default.
- W3199385162 hasConceptScore W3199385162C195324797 @default.
- W3199385162 hasConceptScore W3199385162C204321447 @default.
- W3199385162 hasConceptScore W3199385162C2778067643 @default.
- W3199385162 hasConceptScore W3199385162C2779662365 @default.
- W3199385162 hasConceptScore W3199385162C28490314 @default.
- W3199385162 hasConceptScore W3199385162C33923547 @default.
- W3199385162 hasConceptScore W3199385162C41008148 @default.
- W3199385162 hasConceptScore W3199385162C62520636 @default.
- W3199385162 hasConceptScore W3199385162C81363708 @default.
- W3199385162 hasLocation W31993851621 @default.
- W3199385162 hasLocation W31993851622 @default.
- W3199385162 hasLocation W31993851623 @default.
- W3199385162 hasLocation W31993851624 @default.
- W3199385162 hasOpenAccess W3199385162 @default.
- W3199385162 hasPrimaryLocation W31993851621 @default.
- W3199385162 hasRelatedWork W159132833 @default.
- W3199385162 hasRelatedWork W180507639 @default.
- W3199385162 hasRelatedWork W1806995473 @default.
- W3199385162 hasRelatedWork W2293457016 @default.
- W3199385162 hasRelatedWork W2916492174 @default.
- W3199385162 hasRelatedWork W2977842567 @default.
- W3199385162 hasRelatedWork W3107474891 @default.
- W3199385162 hasRelatedWork W3185852197 @default.
- W3199385162 hasRelatedWork W87581401 @default.
- W3199385162 hasRelatedWork W1872130062 @default.
- W3199385162 isParatext "false" @default.
- W3199385162 isRetracted "false" @default.
- W3199385162 magId "3199385162" @default.
- W3199385162 workType "book-chapter" @default.