{"id":"https://openalex.org/W4392903475","doi":"https://doi.org/10.1109/icassp48485.2024.10447250","title":"Transferable Models for Bioacoustics with Human Language Supervision","display_name":"Transferable Models for Bioacoustics with Human Language Supervision","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903475","doi":"https://doi.org/10.1109/icassp48485.2024.10447250"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5052435548","display_name":"David J. Robinson","orcid":"https://orcid.org/0000-0002-2044-0754"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"David Robinson","raw_affiliation_strings":["Independent"],"affiliations":[{"raw_affiliation_string":"Independent","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108428025","display_name":"A.J. Robinson","orcid":null},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adelaide Robinson","raw_affiliation_strings":["University of California,Santa Barbara","University of California, Santa Barbara"],"affiliations":[{"raw_affiliation_string":"University of California,Santa Barbara","institution_ids":["https://openalex.org/I154570441"]},{"raw_affiliation_string":"University of California, Santa Barbara","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022278374","display_name":"Lily Akrapongpisak","orcid":"https://orcid.org/0009-0006-5866-9999"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lily Akrapongpisak","raw_affiliation_strings":["University of Queensland"],"affiliations":[{"raw_affiliation_string":"University of Queensland","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052435548"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5811,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.87420237,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1316","last_page":"1320"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9782000184059143,"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/bioacoustics","display_name":"Bioacoustics","score":0.8884565830230713},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7553353309631348},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5170400738716125},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.46381422877311707},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.46344828605651855},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.41751497983932495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41350075602531433},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36556750535964966},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3303823471069336},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.18948125839233398},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09048795700073242}],"concepts":[{"id":"https://openalex.org/C34951282","wikidata":"https://www.wikidata.org/wiki/Q864191","display_name":"Bioacoustics","level":2,"score":0.8884565830230713},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7553353309631348},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5170400738716125},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.46381422877311707},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.46344828605651855},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.41751497983932495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41350075602531433},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36556750535964966},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3303823471069336},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.18948125839233398},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09048795700073242},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1665214252","https://openalex.org/W2000252739","https://openalex.org/W2002011878","https://openalex.org/W2052666245","https://openalex.org/W2112796928","https://openalex.org/W2161944985","https://openalex.org/W2194775991","https://openalex.org/W2526050071","https://openalex.org/W2567936177","https://openalex.org/W2590924240","https://openalex.org/W2593116425","https://openalex.org/W2757431469","https://openalex.org/W2896457183","https://openalex.org/W2952087486","https://openalex.org/W2953164412","https://openalex.org/W2965373594","https://openalex.org/W3033723397","https://openalex.org/W3033775310","https://openalex.org/W3121931845","https://openalex.org/W3135648777","https://openalex.org/W3156947595","https://openalex.org/W3166396011","https://openalex.org/W4226051760","https://openalex.org/W4226442948","https://openalex.org/W4286903465","https://openalex.org/W4286987939","https://openalex.org/W4292779060","https://openalex.org/W4306353462","https://openalex.org/W4317617284","https://openalex.org/W4372260310","https://openalex.org/W4372262734","https://openalex.org/W4372266552","https://openalex.org/W4372266830","https://openalex.org/W4385245566","https://openalex.org/W4400033239","https://openalex.org/W6637242042","https://openalex.org/W6755207826","https://openalex.org/W6778883912","https://openalex.org/W6791353385","https://openalex.org/W6799586247","https://openalex.org/W6800875267"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"Passive":[0],"acoustic":[1,169],"monitoring":[2,162,170],"offers":[3],"a":[4,22,36,52,68,75,104,127],"scalable,":[5],"non-invasive":[6],"method":[7],"for":[8,25,55],"tracking":[9],"global":[10],"biodiversity":[11],"and":[12,40,85,96,114,144,163,177],"anthropogenic":[13],"impacts":[14],"on":[15,58,81,90,130,168],"species.":[16],"Although":[17],"deep":[18],"learning":[19],"has":[20],"become":[21],"vital":[23],"tool":[24],"processing":[26],"this":[27,47,91,155],"data,":[28],"current":[29],"models":[30],"are":[31,41],"inflexible,":[32],"typically":[33],"cover":[34],"only":[35],"handful":[37],"of":[38,136],"species,":[39,82],"limited":[42],"by":[43],"data":[44],"scarcity.":[45],"In":[46],"work,":[48],"we":[49,153],"propose":[50],"BioLingual,":[51],"new":[53,128,158],"model":[54,100,156],"bioacoustics":[56],"based":[57],"contrastive":[59],"language-audio":[60,69],"pretraining.":[61],"We":[62,172],"first":[63],"aggregate":[64],"bioacoustic":[65,111],"archives":[66],"into":[67],"dataset,":[70,176],"called":[71],"AnimalSpeak,":[72],"with":[73],"over":[74,103],"million":[76],"audio-caption":[77],"pairs":[78],"holding":[79],"information":[80],"vocalization":[83,117],"context,":[84],"animal":[86,116],"behavior.":[87],"After":[88],"training":[89],"dataset":[92],"to":[93,146],"connect":[94],"language":[95],"audio":[97],"representations,":[98],"our":[99,174],"can":[101],"identify":[102],"thousand":[105],"species\u2019":[106],"calls":[107],"across":[108],"taxa,":[109],"complete":[110],"tasks":[112,132],"zero-shot,":[113],"retrieve":[115],"recordings":[118],"from":[119],"natural":[120],"text":[121],"queries.":[122],"When":[123],"fine-tuned,":[124],"BioLingual":[125],"sets":[126],"state-of-the-art":[129],"nine":[131],"in":[133,150,160],"the":[134],"Benchmark":[135],"Animal":[137],"Sounds.":[138],"Given":[139],"its":[140],"broad":[141],"taxa":[142],"coverage":[143],"ability":[145],"be":[147],"flexibly":[148],"queried":[149],"human":[151],"language,":[152],"believe":[154],"opens":[157],"paradigms":[159],"ecological":[161],"research,":[164],"including":[165],"free-text":[166],"search":[167],"archives.":[171],"release":[173],"models,":[175],"code.":[178],"<sup":[179],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[180],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-24T08:02:53.985720","created_date":"2025-10-10T00:00:00"}
