Matches in SemOpenAlex for { <https://semopenalex.org/work/W2889513020> ?p ?o ?g. }
Showing items 1 to 52 of
52
with 100 items per page.
- W2889513020 abstract "Free to read on publisher's website Automatically detecting koalas in the real-life environment from audio recordings will immensely help ecologists, conservation groups, and government departments interested in their preservation and the protection of their habitat. Inspired by the success of deep learning approaches in various audio classification tasks, in this paper, the feasibility of recognizing koalas’ calls using a convolutional recurrent neural network architecture (CNN+RNN) is studied. The benefit of this architecture is twofold: firstly, convolutional layers learn local time-frequency patterns from the audio spectrogram and secondly, recurrent layers model longer temporal dependencies of the extracted features. In our datasets, the performance of CNN+RNN is evaluated and compared with standard convolutional neural networks (CNNs). The experimental results show that hybrid CNN+RNN architecture is beneficial for learning long-term patterns in spectrogram exhibited by koalas’ calls in unseen conditions. The proposed method is also applicable for detecting other animal calls such as bird sound where it achieves 87.46% area under curve score on the bird audio detection challenge evaluation data." @default.
- W2889513020 created "2018-09-07" @default.
- W2889513020 creator A5039529498 @default.
- W2889513020 creator A5061954034 @default.
- W2889513020 creator A5064708052 @default.
- W2889513020 creator A5068327003 @default.
- W2889513020 date "2018-09-02" @default.
- W2889513020 modified "2023-09-25" @default.
- W2889513020 title "Deep Learning Techniques for Koala Activity Detection" @default.
- W2889513020 cites W2076608692 @default.
- W2889513020 cites W2119525517 @default.
- W2889513020 cites W2437181147 @default.
- W2889513020 cites W2518102674 @default.
- W2889513020 cites W2765532459 @default.
- W2889513020 doi "https://doi.org/10.21437/interspeech.2018-1143" @default.
- W2889513020 hasPublicationYear "2018" @default.
- W2889513020 type Work @default.
- W2889513020 sameAs 2889513020 @default.
- W2889513020 citedByCount "15" @default.
- W2889513020 countsByYear W28895130202019 @default.
- W2889513020 countsByYear W28895130202020 @default.
- W2889513020 countsByYear W28895130202021 @default.
- W2889513020 countsByYear W28895130202022 @default.
- W2889513020 countsByYear W28895130202023 @default.
- W2889513020 crossrefType "proceedings-article" @default.
- W2889513020 hasAuthorship W2889513020A5039529498 @default.
- W2889513020 hasAuthorship W2889513020A5061954034 @default.
- W2889513020 hasAuthorship W2889513020A5064708052 @default.
- W2889513020 hasAuthorship W2889513020A5068327003 @default.
- W2889513020 hasConcept C108583219 @default.
- W2889513020 hasConcept C154945302 @default.
- W2889513020 hasConcept C41008148 @default.
- W2889513020 hasConceptScore W2889513020C108583219 @default.
- W2889513020 hasConceptScore W2889513020C154945302 @default.
- W2889513020 hasConceptScore W2889513020C41008148 @default.
- W2889513020 hasLocation W28895130201 @default.
- W2889513020 hasOpenAccess W2889513020 @default.
- W2889513020 hasPrimaryLocation W28895130201 @default.
- W2889513020 hasRelatedWork W2126887587 @default.
- W2889513020 hasRelatedWork W2731899572 @default.
- W2889513020 hasRelatedWork W2939353110 @default.
- W2889513020 hasRelatedWork W3009238340 @default.
- W2889513020 hasRelatedWork W3215138031 @default.
- W2889513020 hasRelatedWork W4230611425 @default.
- W2889513020 hasRelatedWork W4312962853 @default.
- W2889513020 hasRelatedWork W4321369474 @default.
- W2889513020 hasRelatedWork W4327774331 @default.
- W2889513020 hasRelatedWork W4360585206 @default.
- W2889513020 isParatext "false" @default.
- W2889513020 isRetracted "false" @default.
- W2889513020 magId "2889513020" @default.
- W2889513020 workType "article" @default.