{"id":"https://openalex.org/W2395569966","doi":"https://doi.org/10.1109/icassp.2016.7471737","title":"Bird species recognition using HMM-based unsupervised modelling of individual syllables with incorporated duration modelling","display_name":"Bird species recognition using HMM-based unsupervised modelling of individual syllables with incorporated duration modelling","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2395569966","doi":"https://doi.org/10.1109/icassp.2016.7471737","mag":"2395569966"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7471737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031388449","display_name":"Peter Jan\u010dovi\u010d","orcid":"https://orcid.org/0000-0002-8897-1762"},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Jancovic","raw_affiliation_strings":["School of Electronic, University of Birmingham, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic, University of Birmingham, UK","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012447353","display_name":"M\u00fcnevver K\u00f6k\u00fcer","orcid":"https://orcid.org/0000-0002-5164-7125"},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Munevver Kokuer","raw_affiliation_strings":["School of Electronic, University of Birmingham, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic, University of Birmingham, UK","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111430106","display_name":"Masoud Zakeri","orcid":null},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Masoud Zakeri","raw_affiliation_strings":["School of Electronic, University of Birmingham, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic, University of Birmingham, UK","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079477816","display_name":"Martin Russell","orcid":"https://orcid.org/0000-0002-8324-4961"},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Martin Russell","raw_affiliation_strings":["School of Electronic, University of Birmingham, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic, University of Birmingham, UK","institution_ids":["https://openalex.org/I79619799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0382,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.85741373,"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":"559","last_page":"563"},"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":0.9959999918937683,"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":0.9599000215530396,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.9232978820800781},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6573483347892761},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6354312300682068},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.6131734251976013},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5712177753448486},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5550393462181091},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5508247017860413},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.5454533696174622},{"id":"https://openalex.org/keywords/bioacoustics","display_name":"Bioacoustics","score":0.4969466030597687},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4546617865562439},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.43859991431236267}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9232978820800781},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6573483347892761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6354312300682068},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.6131734251976013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5712177753448486},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5550393462181091},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5508247017860413},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.5454533696174622},{"id":"https://openalex.org/C34951282","wikidata":"https://www.wikidata.org/wiki/Q864191","display_name":"Bioacoustics","level":2,"score":0.4969466030597687},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4546617865562439},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.43859991431236267},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2016.7471737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/41b9a919-49bd-4363-88bc-6195d9888ff3","is_oa":false,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/41b9a919-49bd-4363-88bc-6195d9888ff3","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Jancovic, P, Kokuer, M, Zakeri, M & Russell, M 2016, 'Bird species recognition using HMM-based unsupervised modelling of individual syllables with incorporated duration modelling', Paper presented at IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP) 2016, Shanghai, China, 20/03/16 - 25/03/16. https://doi.org/10.1109/ICASSP.2016.7471737","raw_type":"conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","score":0.6600000262260437,"display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1493349636","https://openalex.org/W1505009870","https://openalex.org/W1525028393","https://openalex.org/W1965147617","https://openalex.org/W1972934497","https://openalex.org/W1992317776","https://openalex.org/W1997356920","https://openalex.org/W2001975519","https://openalex.org/W2011972438","https://openalex.org/W2019432531","https://openalex.org/W2036610824","https://openalex.org/W2046237430","https://openalex.org/W2048747935","https://openalex.org/W2089900668","https://openalex.org/W2115891142","https://openalex.org/W2128312716","https://openalex.org/W2144165558","https://openalex.org/W2149241068","https://openalex.org/W2152867001","https://openalex.org/W2164764235","https://openalex.org/W2395266509","https://openalex.org/W2406356403","https://openalex.org/W6712147338","https://openalex.org/W6713744849"],"related_works":["https://openalex.org/W2341338763","https://openalex.org/W2950183183","https://openalex.org/W2030799363","https://openalex.org/W2419138286","https://openalex.org/W2507549656","https://openalex.org/W2050318184","https://openalex.org/W2182848507","https://openalex.org/W2387825067","https://openalex.org/W2506414444","https://openalex.org/W3117879940"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3,18,69],"HMM-based":[4],"automatic":[5],"system":[6,159],"for":[7,93],"recognition":[8],"of":[9,22,43,49,61,63,95,99,113,126,138,165,170],"bird":[10,24,50,64,131,161],"species":[11,162],"from":[12],"audio":[13],"field":[14,127],"recordings.":[15],"It":[16],"includes":[17],"improved":[19],"unsupervised":[20,70],"modelling":[21,149],"individual":[23,91],"syllables":[25,51,62,94],"and":[26,77,116,146],"duration":[27,102,117,148],"modelling.":[28,118],"The":[29,157],"acoustic":[30,115],"signal":[31],"is":[32,52,66,87,103],"decomposed":[33],"into":[34],"isolated":[35],"segments,":[36],"each":[37,96],"segment":[38],"containing":[39,129],"a":[40,44,106],"temporal":[41],"evolution":[42],"detected":[45,172],"sinusodal":[46],"component.":[47],"Modelling":[48,98],"performed":[53,121],"using":[54,167],"Hidden":[55],"Markov":[56],"models":[57],"(HMMs).":[58],"A":[59,81],"set":[60],"vocalisations":[65],"discovered":[67],"in":[68,105,151],"manner":[71],"by":[72,109],"employing":[73],"dynamic":[74],"time":[75],"warping":[76],"agglomerative":[78],"hierarchical":[79],"clustering.":[80],"novel":[82],"iterative":[83,142],"maximum":[84],"likelihood":[85,112],"procedure":[86,145],"used":[88],"to":[89],"train":[90],"HMMs":[92],"species.":[97,132],"the":[100,111,114,136,139,147,171],"state":[101],"employed":[104],"post-recognition":[107],"stage":[108],"combining":[110],"Experiments":[119],"are":[120],"on":[122],"over":[123],"33":[124],"hours":[125],"recordings,":[128],"30":[130],"Evaluations":[133],"demonstrate":[134],"that":[135],"use":[137],"proposed":[140],"un-supervised":[141],"HMM":[143],"training":[144],"provides":[150],"average":[152],"45%":[153],"error":[154],"rate":[155],"reduction.":[156],"presented":[158],"recognises":[160],"with":[163],"accuracy":[164],"97.8%":[166],"3":[168],"seconds":[169],"signal.":[173]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}