{"id":"https://openalex.org/W4404037684","doi":"https://doi.org/10.1109/mlsp58920.2024.10734816","title":"Detection of Manatee Vocalisations Using the Audio Spectrogram Transformer","display_name":"Detection of Manatee Vocalisations Using the Audio Spectrogram Transformer","publication_year":2024,"publication_date":"2024-09-22","ids":{"openalex":"https://openalex.org/W4404037684","doi":"https://doi.org/10.1109/mlsp58920.2024.10734816"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp58920.2024.10734816","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mlsp58920.2024.10734816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5107604947","display_name":"Stefano Schiappacasse","orcid":null},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":true,"raw_author_name":"Stefano Schiappacasse","raw_affiliation_strings":["Universidad de Chile,Initiative for Data &#x0026; Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"Universidad de Chile,Initiative for Data &#x0026; Artificial Intelligence","institution_ids":["https://openalex.org/I69737025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021259139","display_name":"Taco de Wolff","orcid":"https://orcid.org/0000-0002-2962-5309"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taco de Wolff","raw_affiliation_strings":["DeWolff AI"],"affiliations":[{"raw_affiliation_string":"DeWolff AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062689344","display_name":"Yann H\u00e9naut","orcid":"https://orcid.org/0000-0002-8805-1739"},"institutions":[{"id":"https://openalex.org/I4210165284","display_name":"El Colegio de la Frontera Sur","ror":"https://ror.org/05bpb0y22","country_code":"MX","type":"facility","lineage":["https://openalex.org/I4210163111","https://openalex.org/I4210165284"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Yann Henaut","raw_affiliation_strings":["El Colegio de la Frontera,Departamento de Conservaci&#x00F3;n de la Biodiversidad"],"affiliations":[{"raw_affiliation_string":"El Colegio de la Frontera,Departamento de Conservaci&#x00F3;n de la Biodiversidad","institution_ids":["https://openalex.org/I4210165284"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107487905","display_name":"Regina Cervera","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Regina Cervera","raw_affiliation_strings":["C Minds"],"affiliations":[{"raw_affiliation_string":"C Minds","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062136183","display_name":"Aviva Charles","orcid":"https://orcid.org/0000-0001-5850-6053"},"institutions":[{"id":"https://openalex.org/I4210096121","display_name":"Centre d'\u00c9cologie et des Sciences de la Conservation","ror":"https://ror.org/00sad8321","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210096121","https://openalex.org/I4210107625","https://openalex.org/I4210123595"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Aviva Charles","raw_affiliation_strings":["Centre d&#x0027;Ecologie et des Sciences de la Conservation"],"affiliations":[{"raw_affiliation_string":"Centre d&#x0027;Ecologie et des Sciences de la Conservation","institution_ids":["https://openalex.org/I4210096121"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020822083","display_name":"Felipe Tobar","orcid":"https://orcid.org/0000-0003-2486-3583"},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Felipe Tobar","raw_affiliation_strings":["Universidad de Chile,Initiative for Data &#x0026; Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"Universidad de Chile,Initiative for Data &#x0026; Artificial Intelligence","institution_ids":["https://openalex.org/I69737025"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5107604947"],"corresponding_institution_ids":["https://openalex.org/I69737025"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22182363,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.46299999952316284,"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/T10860","display_name":"Speech and Audio Processing","score":0.46299999952316284,"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/T13289","display_name":"Infant Health and Development","score":0.45879998803138733,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.4350999891757965,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8798688054084778},{"id":"https://openalex.org/keywords/manatee","display_name":"Manatee","score":0.7456241846084595},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5726588368415833},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5076736211776733},{"id":"https://openalex.org/keywords/harp","display_name":"HARP","score":0.4867975413799286},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3204095959663391},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.10149449110031128},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.08652782440185547},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06124964356422424}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8798688054084778},{"id":"https://openalex.org/C2781037846","wikidata":"https://www.wikidata.org/wiki/Q42797","display_name":"Manatee","level":2,"score":0.7456241846084595},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5726588368415833},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5076736211776733},{"id":"https://openalex.org/C2776030095","wikidata":"https://www.wikidata.org/wiki/Q5628954","display_name":"HARP","level":2,"score":0.4867975413799286},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3204095959663391},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.10149449110031128},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.08652782440185547},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06124964356422424},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C52119013","wikidata":"https://www.wikidata.org/wiki/Q50637","display_name":"Art history","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp58920.2024.10734816","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mlsp58920.2024.10734816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W138628383","https://openalex.org/W1521485304","https://openalex.org/W1993652809","https://openalex.org/W2022971332","https://openalex.org/W2108598243","https://openalex.org/W2128653836","https://openalex.org/W2131320681","https://openalex.org/W2139481049","https://openalex.org/W2266735401","https://openalex.org/W2593116425","https://openalex.org/W2890619389","https://openalex.org/W2950845555","https://openalex.org/W2975482270","https://openalex.org/W3005143001","https://openalex.org/W3023645882","https://openalex.org/W3172981086","https://openalex.org/W3196974791","https://openalex.org/W4232027948","https://openalex.org/W4293104232","https://openalex.org/W4311404970","https://openalex.org/W4313650419","https://openalex.org/W4383559417","https://openalex.org/W4385245566","https://openalex.org/W4387673412","https://openalex.org/W6631329720"],"related_works":["https://openalex.org/W4241804228","https://openalex.org/W2091083843","https://openalex.org/W424580262","https://openalex.org/W2597835809","https://openalex.org/W4300904561","https://openalex.org/W619121476","https://openalex.org/W2807944126","https://openalex.org/W4248186805","https://openalex.org/W2897924318","https://openalex.org/W2138997758"],"abstract_inverted_index":{"The":[0],"Antillean":[1],"manatee":[2,31,53,73],"(Trichechus":[3],"manatus)":[4],"is":[5,33,142],"an":[6,14],"endangered":[7],"herbivorous":[8],"aquatic":[9],"mammal":[10],"whose":[11],"role":[12],"as":[13],"ecological":[15],"balancer":[16],"and":[17,120],"umbrella":[18],"species":[19,158],"underscores":[20],"the":[21,57,94,99,108,111,129,134,153,156],"importance":[22],"of":[23,98,110,136,155,159],"its":[24,77],"conservation.":[25],"An":[26],"innovative":[27],"approach":[28,50],"to":[29,51,71,147],"monitor":[30],"populations":[32],"passive":[34],"acoustic":[35],"monitoring":[36],"(PAM),":[37],"where":[38],"vocalisations":[39,54,127],"are":[40],"extracted":[41],"from":[42],"submarine":[43],"audio.":[44],"We":[45],"propose":[46],"a":[47,63,79,81,83,143],"novel":[48],"end-to-end":[49],"detect":[52,72],"building":[55],"on":[56,105],"Audio":[58],"Spectrogram":[59],"Transformer":[60],"(AST).":[61],"In":[62],"transfer":[64],"learning":[65],"spirit,":[66],"we":[67],"fine-tune":[68],"A":[69],"ST":[70],"calls":[74],"by":[75],"redesigning":[76],"filterbanks":[78],"nd":[80],"dapting":[82],"real-world":[84],"dataset":[85],"containing":[86],"partial":[87],"positive":[88],"labels.":[89],"Our":[90],"experimental":[91],"evaluation":[92],"reveals":[93],"two":[95],"key":[96],"features":[97],"proposed":[100],"model:":[101],"i)":[102],"it":[103,122],"performs":[104],"par":[106],"with":[107],"state":[109],"art":[112],"without":[113],"requiring":[114],"hand-tuned":[115],"denoising":[116],"or":[117],"detection":[118],"stages,":[119],"ii)":[121],"can":[123],"successfully":[124],"identify":[125],"missed":[126],"in":[128],"training":[130],"dataset,":[131],"thus":[132],"reducing":[133],"workload":[135],"expert":[137],"bioacoustic":[138],"labellers.":[139],"This":[140],"work":[141],"preliminary":[144],"relevant":[145],"step":[146],"develop":[148],"novel,":[149],"user-friendly":[150],"tools":[151],"for":[152],"conservation":[154],"different":[157],"manatees.":[160]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
