Matches in SemOpenAlex for { <https://semopenalex.org/work/W2943067474> ?p ?o ?g. }
- W2943067474 abstract "The majority of sound scene analysis work focuses on one of two clearly defined tasks: acoustic scene classification or sound event detection. Whilst this separation of tasks is useful for problem definition, they inherently ignore some subtleties of the real-world, in particular how humans vary in how they describe a scene. Some will describe the weather and features within it, others will use a holistic descriptor like `park', and others still will use unique identifiers such as cities or names. In this paper, we undertake the task of automatic city classification to ask whether we can recognize a city from a set of sound scenes? In this problem each city has recordings from multiple scenes. We test a series of methods for this novel task and show that a simple convolutional neural network (CNN) can achieve accuracy of 50%. This is less than the acoustic scene classification task baseline in the DCASE 2018 ASC challenge on the same data. A simple adaptation to the class labels of pairing city labels with grouped scenes, accuracy increases to 52%, closer to the simpler scene classification task. Finally we also formulate the problem in a multi-task learning framework and achieve an accuracy of 56%, outperforming the aforementioned approaches." @default.
- W2943067474 created "2019-05-09" @default.
- W2943067474 creator A5031962033 @default.
- W2943067474 creator A5049691461 @default.
- W2943067474 creator A5059929826 @default.
- W2943067474 creator A5079981416 @default.
- W2943067474 creator A5084672392 @default.
- W2943067474 date "2019-05-02" @default.
- W2943067474 modified "2023-09-27" @default.
- W2943067474 title "City classification from multiple real-world sound scenes" @default.
- W2943067474 cites W1650531274 @default.
- W2943067474 cites W2137561966 @default.
- W2943067474 cites W2165409492 @default.
- W2943067474 cites W2341412280 @default.
- W2943067474 cites W2619623002 @default.
- W2943067474 cites W2758074877 @default.
- W2943067474 cites W2759976799 @default.
- W2943067474 cites W2883935097 @default.
- W2943067474 cites W2888678380 @default.
- W2943067474 cites W2893908923 @default.
- W2943067474 cites W2942146535 @default.
- W2943067474 cites W2963475812 @default.
- W2943067474 hasPublicationYear "2019" @default.
- W2943067474 type Work @default.
- W2943067474 sameAs 2943067474 @default.
- W2943067474 citedByCount "0" @default.
- W2943067474 crossrefType "posted-content" @default.
- W2943067474 hasAuthorship W2943067474A5031962033 @default.
- W2943067474 hasAuthorship W2943067474A5049691461 @default.
- W2943067474 hasAuthorship W2943067474A5059929826 @default.
- W2943067474 hasAuthorship W2943067474A5079981416 @default.
- W2943067474 hasAuthorship W2943067474A5084672392 @default.
- W2943067474 hasConcept C111368507 @default.
- W2943067474 hasConcept C111472728 @default.
- W2943067474 hasConcept C119857082 @default.
- W2943067474 hasConcept C120665830 @default.
- W2943067474 hasConcept C121332964 @default.
- W2943067474 hasConcept C12725497 @default.
- W2943067474 hasConcept C127313418 @default.
- W2943067474 hasConcept C138885662 @default.
- W2943067474 hasConcept C139807058 @default.
- W2943067474 hasConcept C154504017 @default.
- W2943067474 hasConcept C154945302 @default.
- W2943067474 hasConcept C162324750 @default.
- W2943067474 hasConcept C177264268 @default.
- W2943067474 hasConcept C187736073 @default.
- W2943067474 hasConcept C199360897 @default.
- W2943067474 hasConcept C2777212361 @default.
- W2943067474 hasConcept C2779662365 @default.
- W2943067474 hasConcept C2780451532 @default.
- W2943067474 hasConcept C2780586882 @default.
- W2943067474 hasConcept C41008148 @default.
- W2943067474 hasConcept C62520636 @default.
- W2943067474 hasConcept C81363708 @default.
- W2943067474 hasConceptScore W2943067474C111368507 @default.
- W2943067474 hasConceptScore W2943067474C111472728 @default.
- W2943067474 hasConceptScore W2943067474C119857082 @default.
- W2943067474 hasConceptScore W2943067474C120665830 @default.
- W2943067474 hasConceptScore W2943067474C121332964 @default.
- W2943067474 hasConceptScore W2943067474C12725497 @default.
- W2943067474 hasConceptScore W2943067474C127313418 @default.
- W2943067474 hasConceptScore W2943067474C138885662 @default.
- W2943067474 hasConceptScore W2943067474C139807058 @default.
- W2943067474 hasConceptScore W2943067474C154504017 @default.
- W2943067474 hasConceptScore W2943067474C154945302 @default.
- W2943067474 hasConceptScore W2943067474C162324750 @default.
- W2943067474 hasConceptScore W2943067474C177264268 @default.
- W2943067474 hasConceptScore W2943067474C187736073 @default.
- W2943067474 hasConceptScore W2943067474C199360897 @default.
- W2943067474 hasConceptScore W2943067474C2777212361 @default.
- W2943067474 hasConceptScore W2943067474C2779662365 @default.
- W2943067474 hasConceptScore W2943067474C2780451532 @default.
- W2943067474 hasConceptScore W2943067474C2780586882 @default.
- W2943067474 hasConceptScore W2943067474C41008148 @default.
- W2943067474 hasConceptScore W2943067474C62520636 @default.
- W2943067474 hasConceptScore W2943067474C81363708 @default.
- W2943067474 hasLocation W29430674741 @default.
- W2943067474 hasOpenAccess W2943067474 @default.
- W2943067474 hasPrimaryLocation W29430674741 @default.
- W2943067474 hasRelatedWork W1558349653 @default.
- W2943067474 hasRelatedWork W1837649128 @default.
- W2943067474 hasRelatedWork W1959000896 @default.
- W2943067474 hasRelatedWork W2156935079 @default.
- W2943067474 hasRelatedWork W2403009109 @default.
- W2943067474 hasRelatedWork W2403062601 @default.
- W2943067474 hasRelatedWork W2561741492 @default.
- W2943067474 hasRelatedWork W2572644365 @default.
- W2943067474 hasRelatedWork W2605147985 @default.
- W2943067474 hasRelatedWork W2767868154 @default.
- W2943067474 hasRelatedWork W2889626218 @default.
- W2943067474 hasRelatedWork W2913521523 @default.
- W2943067474 hasRelatedWork W2952809312 @default.
- W2943067474 hasRelatedWork W2953349900 @default.
- W2943067474 hasRelatedWork W2967870022 @default.
- W2943067474 hasRelatedWork W2973570544 @default.
- W2943067474 hasRelatedWork W2987008042 @default.
- W2943067474 hasRelatedWork W3021321555 @default.
- W2943067474 hasRelatedWork W3200294180 @default.
- W2943067474 hasRelatedWork W2269548449 @default.
- W2943067474 isParatext "false" @default.