{"id":"https://openalex.org/W2889513020","doi":"https://doi.org/10.21437/interspeech.2018-1143","title":"Deep Learning Techniques for Koala Activity Detection","display_name":"Deep Learning Techniques for Koala Activity Detection","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889513020","doi":"https://doi.org/10.21437/interspeech.2018-1143","mag":"2889513020"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1143","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.isca-speech.org/archive/Interspeech_2018/pdfs/1143.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039529498","display_name":"Ivan Himawan","orcid":"https://orcid.org/0000-0003-3848-244X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ivan Himawan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068327003","display_name":"Michael Towsey","orcid":"https://orcid.org/0000-0002-8246-7151"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Towsey","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064708052","display_name":"Bradley Law","orcid":"https://orcid.org/0000-0002-3991-3865"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bradley Law","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5107595310","display_name":"Paul Roe","orcid":"https://orcid.org/0000-0002-4892-1509"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paul Roe","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5039529498"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4039,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.88275434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2107","last_page":"2111"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9779999852180481,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.9476785659790039},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.788577139377594},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6940218210220337},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6852916479110718},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6339143514633179},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6185729503631592},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5241004228591919},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39114588499069214},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3769281506538391},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36103206872940063},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.20712104439735413},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06522667407989502}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9476785659790039},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.788577139377594},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6940218210220337},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6852916479110718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6339143514633179},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6185729503631592},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5241004228591919},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39114588499069214},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3769281506538391},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36103206872940063},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.20712104439735413},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06522667407989502},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-1143","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.qut.edu.au:124100","is_oa":true,"landing_page_url":null,"pdf_url":"https://www.isca-speech.org/archive/Interspeech_2018/pdfs/1143.pdf","source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 19th Annual Conference of the International Speech Communication Association (INTERSPEECH 2018)","raw_type":"Chapter in Book, Report or Conference volume"}],"best_oa_location":{"id":"pmh:oai:eprints.qut.edu.au:124100","is_oa":true,"landing_page_url":null,"pdf_url":"https://www.isca-speech.org/archive/Interspeech_2018/pdfs/1143.pdf","source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 19th Annual Conference of the International Speech Communication Association (INTERSPEECH 2018)","raw_type":"Chapter in Book, Report or Conference volume"},"sustainable_development_goals":[{"display_name":"Life in Land","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2889513020.pdf","grobid_xml":"https://content.openalex.org/works/W2889513020.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W2076608692","https://openalex.org/W2119525517","https://openalex.org/W2437181147","https://openalex.org/W2518102674","https://openalex.org/W2765532459"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3133861977","https://openalex.org/W3008584592","https://openalex.org/W2951211570","https://openalex.org/W3103566983","https://openalex.org/W3167935049","https://openalex.org/W3029198973"],"abstract_inverted_index":{"Free":[0],"to":[1],"read":[2],"on":[3,160],"publisher's":[4],"website":[5],"Automatically":[6],"detecting":[7,144],"koalas":[8],"in":[9,26,43,48,128,134],"the":[10,30,37,51,82,94,100,161],"real-life":[11],"environment":[12],"from":[13,81],"audio":[14,45,83,163],"recordings":[15],"will":[16],"immensely":[17],"help":[18],"ecologists,":[19],"conservation":[20],"groups,":[21],"and":[22,29,85,106],"government":[23],"departments":[24],"interested":[25],"their":[27,33],"preservation":[28],"protection":[31],"of":[32,39,53,69,93,102],"habitat.":[34],"Inspired":[35],"by":[36,131],"success":[38],"deep":[40],"learning":[41,125],"approaches":[42],"various":[44],"classification":[46],"tasks,":[47],"this":[49,70],"paper,":[50],"feasibility":[52],"recognizing":[54],"koalas\u2019":[55,132],"calls":[56,133,147],"using":[57],"a":[58],"convolutional":[59,75,110],"recurrent":[60,87],"neural":[61,111],"network":[62],"architecture":[63,71,121],"(CNN+RNN)":[64],"is":[65,72,104,122,140],"studied.":[66],"The":[67,114,137],"benefit":[68],"twofold:":[73],"firstly,":[74],"layers":[76,88],"learn":[77],"local":[78],"time-frequency":[79],"patterns":[80,127],"spectrogram":[84,129],"secondly,":[86],"model":[89],"longer":[90],"temporal":[91],"dependencies":[92],"extracted":[95],"features.":[96],"In":[97],"our":[98],"datasets,":[99],"performance":[101],"CNN+RNN":[103,120],"evaluated":[105],"compared":[107],"with":[108],"standard":[109],"networks":[112],"(CNNs).":[113],"experimental":[115],"results":[116],"show":[117],"that":[118],"hybrid":[119],"beneficial":[123],"for":[124,143],"long-term":[126],"exhibited":[130],"unseen":[135],"conditions.":[136],"proposed":[138],"method":[139],"also":[141],"applicable":[142],"other":[145],"animal":[146],"such":[148],"as":[149],"bird":[150,162],"sound":[151],"where":[152],"it":[153],"achieves":[154],"87.46%":[155],"area":[156],"under":[157],"curve":[158],"score":[159],"detection":[164],"challenge":[165],"evaluation":[166],"data.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}