FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4224303702> ?p ?o ?g. }

• W4224303702 endingPage "1567" @default.
• W4224303702 startingPage "1552" @default.
• W4224303702 abstract "Abstract When recorders are used to survey acoustically conspicuous species, identification calls of the target species in recordings is essential for estimating density and abundance. We investigate how well deep neural networks identify vocalisations consisting of phrases of varying lengths, each containing a variable number of syllables . We use recordings of Hainan gibbon Nomascus hainanus vocalisations to develop and test the methods. We propose two methods for exploiting the two‐level structure of such data. The first combines convolutional neural network (CNN) models with a hidden Markov model (HMM) and the second uses a convolutional recurrent neural network (CRNN). Both models learn acoustic features of syllables via a CNN and temporal correlations of syllables into phrases either via an HMM or recurrent network. We compare their performance to commonly used CNNs LeNet and VGGNet, and support vector machine (SVM). We also propose a dynamic programming method to evaluate how well phrases are predicted. This is useful for evaluating performance when vocalisations are labelled by phrases, not syllables. Our methods perform substantially better than the commonly used methods when applied to the gibbon acoustic recordings. The CRNN has an F ‐score of 90% on phrase prediction, which is 18% higher than the best of the SVM or LeNet and VGGNet methods. HMM post‐processing raised the F ‐score of these last three methods to as much as 87%. The number of phrases is overestimated by CNNs and SVM, leading to error rates between 49% and 54%. With HMM, these error rates can be reduced to 0.4% at the lowest. Similarly, the error rate of CRNN's prediction is no more than 0.5%. CRNNs are better at identifying phrases of varying lengths composed of a varying number of syllables than simpler CNN or SVM models. We find a CRNN model to be best at this task, with a CNN combined with an HMM performing almost as well. We recommend that these kinds of models are used for species whose vocalisations are structured into phrases of varying lengths." @default.
• W4224303702 created "2022-04-26" @default.
• W4224303702 creator A5000533321 @default.
• W4224303702 creator A5059122071 @default.
• W4224303702 creator A5070918563 @default.
• W4224303702 date "2022-05-05" @default.
• W4224303702 modified "2023-09-27" @default.
• W4224303702 title "Automated call detection for acoustic surveys with structured calls of varying length" @default.
• W4224303702 cites W1600744878 @default.
• W4224303702 cites W1965147617 @default.
• W4224303702 cites W1977618577 @default.
• W4224303702 cites W2000700559 @default.
• W4224303702 cites W2034813712 @default.
• W4224303702 cites W2038484192 @default.
• W4224303702 cites W2054282473 @default.
• W4224303702 cites W2064675550 @default.
• W4224303702 cites W2112796928 @default.
• W4224303702 cites W2149241068 @default.
• W4224303702 cites W2191779130 @default.
• W4224303702 cites W2194187530 @default.
• W4224303702 cites W2395984164 @default.
• W4224303702 cites W2408239454 @default.
• W4224303702 cites W2561443310 @default.
• W4224303702 cites W2581706890 @default.
• W4224303702 cites W2591013610 @default.
• W4224303702 cites W2593610980 @default.
• W4224303702 cites W2680737492 @default.
• W4224303702 cites W2731031236 @default.
• W4224303702 cites W2754508014 @default.
• W4224303702 cites W2784076614 @default.
• W4224303702 cites W2889513020 @default.
• W4224303702 cites W2890012819 @default.
• W4224303702 cites W2896082894 @default.
• W4224303702 cites W2901877043 @default.
• W4224303702 cites W2916994621 @default.
• W4224303702 cites W2919115771 @default.
• W4224303702 cites W2922355292 @default.
• W4224303702 cites W2938440247 @default.
• W4224303702 cites W2962677373 @default.
• W4224303702 cites W2965503177 @default.
• W4224303702 cites W2971670291 @default.
• W4224303702 cites W2981733351 @default.
• W4224303702 cites W2987685943 @default.
• W4224303702 cites W2997741622 @default.
• W4224303702 cites W3008768000 @default.
• W4224303702 cites W3011702533 @default.
• W4224303702 cites W3014988774 @default.
• W4224303702 cites W3017875707 @default.
• W4224303702 cites W3035400806 @default.
• W4224303702 cites W3083888421 @default.
• W4224303702 cites W3086539361 @default.
• W4224303702 cites W3183398559 @default.
• W4224303702 cites W403203070 @default.
• W4224303702 cites W4224303702 @default.
• W4224303702 cites W4245906119 @default.
• W4224303702 doi "https://doi.org/10.1111/2041-210x.13873" @default.
• W4224303702 hasPublicationYear "2022" @default.
• W4224303702 type Work @default.
• W4224303702 citedByCount "4" @default.
• W4224303702 countsByYear W42243037022022 @default.
• W4224303702 countsByYear W42243037022023 @default.
• W4224303702 crossrefType "journal-article" @default.
• W4224303702 hasAuthorship W4224303702A5000533321 @default.
• W4224303702 hasAuthorship W4224303702A5059122071 @default.
• W4224303702 hasAuthorship W4224303702A5070918563 @default.
• W4224303702 hasBestOaLocation W42243037021 @default.
• W4224303702 hasConcept C12267149 @default.
• W4224303702 hasConcept C147168706 @default.
• W4224303702 hasConcept C153180895 @default.
• W4224303702 hasConcept C154945302 @default.
• W4224303702 hasConcept C23224414 @default.
• W4224303702 hasConcept C2776224158 @default.
• W4224303702 hasConcept C28490314 @default.
• W4224303702 hasConcept C40969351 @default.
• W4224303702 hasConcept C41008148 @default.
• W4224303702 hasConcept C50644808 @default.
• W4224303702 hasConcept C81363708 @default.
• W4224303702 hasConceptScore W4224303702C12267149 @default.
• W4224303702 hasConceptScore W4224303702C147168706 @default.
• W4224303702 hasConceptScore W4224303702C153180895 @default.
• W4224303702 hasConceptScore W4224303702C154945302 @default.
• W4224303702 hasConceptScore W4224303702C23224414 @default.
• W4224303702 hasConceptScore W4224303702C2776224158 @default.
• W4224303702 hasConceptScore W4224303702C28490314 @default.
• W4224303702 hasConceptScore W4224303702C40969351 @default.
• W4224303702 hasConceptScore W4224303702C41008148 @default.
• W4224303702 hasConceptScore W4224303702C50644808 @default.
• W4224303702 hasConceptScore W4224303702C81363708 @default.
• W4224303702 hasFunder F4320322725 @default.
• W4224303702 hasIssue "7" @default.
• W4224303702 hasLocation W42243037021 @default.
• W4224303702 hasLocation W42243037022 @default.
• W4224303702 hasOpenAccess W4224303702 @default.
• W4224303702 hasPrimaryLocation W42243037021 @default.
• W4224303702 hasRelatedWork W1574295218 @default.
• W4224303702 hasRelatedWork W2021413527 @default.
• W4224303702 hasRelatedWork W2117295508 @default.
• W4224303702 hasRelatedWork W2120476639 @default.

• next