{"id":"https://openalex.org/W7204283463","doi":null,"title":"Scalable Bird Diversity: Mastering High-Chorus Soundscape and Species Richness with Time-frequency YOLOv5","display_name":"Scalable Bird Diversity: Mastering High-Chorus Soundscape and Species Richness with Time-frequency YOLOv5","publication_year":2026,"publication_date":"2026-08-21","ids":{"openalex":"https://openalex.org/W7204283463"},"language":"en","primary_location":{"id":"pmh:oai:HAL:hal-05723151v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05723151v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2026","raw_type":"info:eu-repo/semantics/preprint"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-05723151v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116111922","display_name":"St\u00e9phane Chavin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I143002897","display_name":"Universit\u00e9 de Toulon","ror":"https://ror.org/02m9kbe37","country_code":"FR","type":"education","lineage":["https://openalex.org/I143002897"]},{"id":"https://openalex.org/I21491767","display_name":"Aix-Marseille Universit\u00e9","ror":"https://ror.org/035xkbk20","country_code":"FR","type":"education","lineage":["https://openalex.org/I21491767"]},{"id":"https://openalex.org/I4210114274","display_name":"Laboratoire d\u2019Informatique et Syst\u00e8mes","ror":"https://ror.org/0257sgk90","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I143002897","https://openalex.org/I21491767","https://openalex.org/I4210114274"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Chavin, St\u00e9phane","raw_affiliation_strings":["CIAN - Centre d'Intelligence Artificielle en Acoustique Naturelle (Universit\u00e9 de ToulonCS 60584 83041 TOULON CEDEX 9 - France)","LIS - Laboratoire d'Informatique et des Syst\u00e8mes (LIS) (Marseille, Toulon) (Aix Marseille Universit\u00e9 \u2013 Campus de Saint J\u00e9r\u00f4me \u2013 Bat. Polytech, 52 Av. Escadrille Normandie Niemen, 13397 Marseille Cedex 20 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIAN - Centre d'Intelligence Artificielle en Acoustique Naturelle (Universit\u00e9 de ToulonCS 60584 83041 TOULON CEDEX 9 - France)","institution_ids":["https://openalex.org/I143002897"]},{"raw_affiliation_string":"LIS - Laboratoire d'Informatique et des Syst\u00e8mes (LIS) (Marseille, Toulon) (Aix Marseille Universit\u00e9 \u2013 Campus de Saint J\u00e9r\u00f4me \u2013 Bat. Polytech, 52 Av. Escadrille Normandie Niemen, 13397 Marseille Cedex 20 - France)","institution_ids":["https://openalex.org/I21491767","https://openalex.org/I4210114274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091353420","display_name":"Anouk Simard","orcid":"https://orcid.org/0000-0002-5139-9336","observed_orcids":["https://orcid.org/0000-0002-5139-9336"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simard, Anouk","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052214896","display_name":"Jean-Fran\u00e7ois Jett\u00e9","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jett\u00e9, Jean-Fran\u00e7ois","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040217264","display_name":"Marc\u2010Andr\u00e9 Villard","orcid":"https://orcid.org/0000-0002-8485-1800","observed_orcids":["https://orcid.org/0000-0002-8485-1800"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Villard, Marc-Andr\u00e9","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066999333","display_name":"Yann Ourmi\u00e8res","orcid":"https://orcid.org/0000-0003-3745-245X","observed_orcids":["https://orcid.org/0000-0003-3745-245X"]},"institutions":[{"id":"https://openalex.org/I4210155331","display_name":"Institut M\u00e9diterran\u00e9en d\u2019Oc\u00e9anologie","ror":"https://ror.org/05258q350","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I143002897","https://openalex.org/I21491767","https://openalex.org/I2802818602","https://openalex.org/I4210088668","https://openalex.org/I4210090127","https://openalex.org/I4210093025","https://openalex.org/I4210131494","https://openalex.org/I4210148025","https://openalex.org/I4210155331","https://openalex.org/I4210166444"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ourmi\u00e8res, Yann","raw_affiliation_strings":["MIO - Institut m\u00e9diterran\u00e9en d'oc\u00e9anologie (M.I.O. Institut M\u00e9diterran\u00e9en d'Oc\u00e9anologie B\u00e2timent M\u00e9diterran\u00e9e163 Avenue de Luminy13288 Marseille - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIO - Institut m\u00e9diterran\u00e9en d'oc\u00e9anologie (M.I.O. Institut M\u00e9diterran\u00e9en d'Oc\u00e9anologie B\u00e2timent M\u00e9diterran\u00e9e163 Avenue de Luminy13288 Marseille - France)","institution_ids":["https://openalex.org/I4210155331"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105836701","display_name":"Herv\u00e9 Glotin","orcid":"https://orcid.org/0000-0001-7338-8518","observed_orcids":["https://orcid.org/0000-0001-7338-8518"]},"institutions":[{"id":"https://openalex.org/I143002897","display_name":"Universit\u00e9 de Toulon","ror":"https://ror.org/02m9kbe37","country_code":"FR","type":"education","lineage":["https://openalex.org/I143002897"]},{"id":"https://openalex.org/I21491767","display_name":"Aix-Marseille Universit\u00e9","ror":"https://ror.org/035xkbk20","country_code":"FR","type":"education","lineage":["https://openalex.org/I21491767"]},{"id":"https://openalex.org/I4210114274","display_name":"Laboratoire d\u2019Informatique et Syst\u00e8mes","ror":"https://ror.org/0257sgk90","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I143002897","https://openalex.org/I21491767","https://openalex.org/I4210114274"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Glotin, Herv\u00e9","raw_affiliation_strings":["AMU - Aix Marseille Universit\u00e9 (Aix-Marseille Universit\u00e9Jardins du Pharo58 Boulevard Charles Livon13284 Marseille cedex 7 - France)","CIAN - Centre d'Intelligence Artificielle en Acoustique Naturelle (Universit\u00e9 de ToulonCS 60584 83041 TOULON CEDEX 9 - France)","DYNI - DYNamiques de l\u2019Information (France)","LIS - Laboratoire d'Informatique et des Syst\u00e8mes (LIS) (Marseille, Toulon) (Aix Marseille Universit\u00e9 \u2013 Campus de Saint J\u00e9r\u00f4me \u2013 Bat. Polytech, 52 Av. Escadrille Normandie Niemen, 13397 Marseille Cedex 20 - France)","UTLN - Universit\u00e9 de Toulon (Avenue de l'Universit\u00e9 - BP 20132 - 83957 La Garde Cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMU - Aix Marseille Universit\u00e9 (Aix-Marseille Universit\u00e9Jardins du Pharo58 Boulevard Charles Livon13284 Marseille cedex 7 - France)","institution_ids":["https://openalex.org/I21491767"]},{"raw_affiliation_string":"CIAN - Centre d'Intelligence Artificielle en Acoustique Naturelle (Universit\u00e9 de ToulonCS 60584 83041 TOULON CEDEX 9 - France)","institution_ids":["https://openalex.org/I143002897"]},{"raw_affiliation_string":"DYNI - DYNamiques de l\u2019Information (France)","institution_ids":[]},{"raw_affiliation_string":"LIS - Laboratoire d'Informatique et des Syst\u00e8mes (LIS) (Marseille, Toulon) (Aix Marseille Universit\u00e9 \u2013 Campus de Saint J\u00e9r\u00f4me \u2013 Bat. Polytech, 52 Av. Escadrille Normandie Niemen, 13397 Marseille Cedex 20 - France)","institution_ids":["https://openalex.org/I21491767","https://openalex.org/I4210114274"]},{"raw_affiliation_string":"UTLN - Universit\u00e9 de Toulon (Avenue de l'Universit\u00e9 - BP 20132 - 83957 La Garde Cedex - France)","institution_ids":["https://openalex.org/I143002897"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9179999828338623,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9179999828338623,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.07429999858140945,"subfield":{"id":"https://openalex.org/subfields/1105","display_name":"Ecology, Evolution, Behavior and Systematics"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.0010000000474974513,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/bioacoustic-monitoring","display_name":"bioacoustic monitoring","score":0.8579999804496765},{"id":"https://openalex.org/keywords/species-richness-estimation","display_name":"species richness estimation","score":0.6449999809265137},{"id":"https://openalex.org/keywords/yolov5","display_name":"YOLOv5","score":0.9440000057220459},{"id":"https://openalex.org/keywords/species-distribution-monitoring","display_name":"species distribution monitoring","score":0.5210000276565552}],"concepts":[{"id":"https://openalex.org/C53565203","wikidata":"https://www.wikidata.org/wiki/Q17146659","display_name":"Species richness","level":2,"score":0.8159000277519226},{"id":"https://openalex.org/C34951282","wikidata":"https://www.wikidata.org/wiki/Q864191","display_name":"Bioacoustics","level":2,"score":0.5659000277519226},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5612000226974487},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5067999958992004},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.5022000074386597},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4966000020503998},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.47429999709129333},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.46320000290870667},{"id":"https://openalex.org/C142795923","wikidata":"https://www.wikidata.org/wiki/Q1358257","display_name":"Soundscape","level":3,"score":0.4431999921798706},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.42669999599456787},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4140999913215637},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.38839998841285706},{"id":"https://openalex.org/C2987826769","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Species identification","level":2,"score":0.3804999887943268},{"id":"https://openalex.org/C2780832652","wikidata":"https://www.wikidata.org/wiki/Q5105266","display_name":"Chorus","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C130217890","wikidata":"https://www.wikidata.org/wiki/Q47041","display_name":"Biodiversity","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31929999589920044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.305400013923645},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C62648534","wikidata":"https://www.wikidata.org/wiki/Q706937","display_name":"Species diversity","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C2992428333","wikidata":"https://www.wikidata.org/wiki/Q11461","display_name":"Sound production","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C160331591","wikidata":"https://www.wikidata.org/wiki/Q7075743","display_name":"Occupancy","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26080000400543213}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:HAL:hal-05723151v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05723151v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2026","raw_type":"info:eu-repo/semantics/preprint"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-05723151v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05723151v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2026","raw_type":"info:eu-repo/semantics/preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life on land","score":0.7605999708175659}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4386811749","https://openalex.org/W4401358421","https://openalex.org/W3121931845","https://openalex.org/W4309293828","https://openalex.org/W3036940419","https://openalex.org/W4403022406","https://openalex.org/W2768827738","https://openalex.org/W4412901359","https://openalex.org/W3176373068","https://openalex.org/W7038277816"],"abstract_inverted_index":{"Bioacoustic":[0],"monitoring":[1,10],"of":[2,42,53,64,87,102,106,117,133,139,165],"birds":[3],"plays":[4],"an":[5,24],"important":[6],"role":[7],"in":[8,15,38,47,56,60,90,104,119],"avian":[9,146],"and":[11,114,136],"can":[12],"be":[13,159],"valuable":[14],"developing":[16],"conservation":[17],"strategies.":[18],"In":[19],"this":[20],"study,":[21],"we":[22],"developed":[23],"automatic":[25],"detection":[26,82],"model":[27,83,98,144,156],"for":[28,73,112,126],"27":[29,167],"bird":[30],"species":[31,68,89,147,168],"recorded":[32],"along":[33],"a":[34,70,100,115],"1300-km":[35],"north-south":[36],"gradient":[37],"Qu\u00e9bec,":[39],"Canada.":[40],"One":[41],"the":[43,51,62,79,131,137,143],"main":[44],"challenges":[45],"addressed":[46],"our":[48,134],"research":[49],"is":[50],"problem":[52],"chorus":[54,121],"inherent":[55],"neural":[57,154],"network":[58,155],"detection,":[59],"which":[61],"overlap":[63],"vocalisations":[65],"from":[66],"multiple":[67],"constitutes":[69],"significant":[71],"obstacle":[72],"accurate":[74,85],"detection.":[75],"We":[76],"demonstrate":[77],"that":[78],"YOLOv5":[80],"visual":[81],"provides":[84],"identification":[86],"individual":[88],"complex":[91],"acoustic":[92],"environments":[93],"using":[94],"bounding":[95],"boxes.":[96],"The":[97],"achieved":[99],"cmAP":[101,116],"63%":[103],"cases":[105],"intense":[107],"chorusing,":[108],"compared":[109,123],"to":[110,124,161],"54%":[111],"BirdNET,":[113],"60%":[118],"all":[120],"cases,":[122],"55%":[125],"BirdNET.":[127],"These":[128],"results":[129],"confirm":[130],"e!ciency":[132],"approach":[135],"relevance":[138],"class-specific":[140],"thresholds.":[141],"Furthermore,":[142],"predicted":[145],"richness":[148],"fairly":[149],"accurately":[150],"(Spearmans":[151],"rho=62%).":[152],"This":[153],"will":[157],"therefore":[158],"used":[160],"monitor":[162],"distributional":[163],"changes":[164],"these":[166],"across":[169],"Qu\u00e9bec.":[170]},"counts_by_year":[],"updated_date":"2026-10-25T09:29:13.331239","created_date":"2026-08-27T00:00:00"}
