{"id":"https://openalex.org/W4408352573","doi":"https://doi.org/10.1109/icassp49660.2025.10890750","title":"Scaling Bioacoustic Signal Pre-training with Million Samples Via Mask-Modeling","display_name":"Scaling Bioacoustic Signal Pre-training with Million Samples Via Mask-Modeling","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352573","doi":"https://doi.org/10.1109/icassp49660.2025.10890750"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"display_name":"Xuyao Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuyao Deng","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061252955","display_name":"Tianjiao Wan","orcid":"https://orcid.org/0000-0002-2423-4982"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianjiao Wan","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013340793","display_name":"Kele Xu","orcid":"https://orcid.org/0000-0001-5997-5169"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kele Xu","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080657827","display_name":"Tian Gao","orcid":"https://orcid.org/0000-0003-0466-1001"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian Gao","raw_affiliation_strings":["iFLYTEK Research Institute,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research Institute,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018873974","display_name":"Peng Qiao","orcid":"https://orcid.org/0000-0002-7882-6449"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Qiao","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039795290","display_name":"Dawei Feng","orcid":"https://orcid.org/0000-0002-7587-8905"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Feng","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051680867","display_name":"Yong Dou","orcid":"https://orcid.org/0000-0002-1256-8934"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Dou","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11698","display_name":"Underwater Acoustics Research","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11698","display_name":"Underwater Acoustics Research","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9904000163078308,"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":0.9514999985694885,"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/bioacoustics","display_name":"Bioacoustics","score":0.8627755045890808},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6202698945999146},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5585893988609314},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5449787378311157},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5294356346130371},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.5015075206756592},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4344245195388794},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.380767285823822},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.34069937467575073},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.21030044555664062},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12893030047416687},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10334351658821106}],"concepts":[{"id":"https://openalex.org/C34951282","wikidata":"https://www.wikidata.org/wiki/Q864191","display_name":"Bioacoustics","level":2,"score":0.8627755045890808},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6202698945999146},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5585893988609314},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5449787378311157},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5294356346130371},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.5015075206756592},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4344245195388794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.380767285823822},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.34069937467575073},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.21030044555664062},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12893030047416687},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10334351658821106},{"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324150","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2052666245","https://openalex.org/W2161944985","https://openalex.org/W2194775991","https://openalex.org/W2295598076","https://openalex.org/W2526050071","https://openalex.org/W2590924240","https://openalex.org/W2593116425","https://openalex.org/W2757431469","https://openalex.org/W2936774411","https://openalex.org/W3015371781","https://openalex.org/W3033723397","https://openalex.org/W3135648777","https://openalex.org/W3156947595","https://openalex.org/W3206996142","https://openalex.org/W4205689591","https://openalex.org/W4210883322","https://openalex.org/W4307823382","https://openalex.org/W4372262734","https://openalex.org/W4372266830","https://openalex.org/W4385245566","https://openalex.org/W4390060493","https://openalex.org/W4396982399","https://openalex.org/W4404609584","https://openalex.org/W6697193729","https://openalex.org/W6750665317","https://openalex.org/W6799586247","https://openalex.org/W6889743928"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2124374855","https://openalex.org/W2997094352","https://openalex.org/W4233748472","https://openalex.org/W3105563334","https://openalex.org/W2915791176","https://openalex.org/W286580249"],"abstract_inverted_index":{"Deep":[0],"learning-based":[1],"bioacoustic":[2,38,53,82,114],"audio":[3,54,83],"analysis":[4],"holds":[5],"immense":[6],"potential":[7],"across":[8,30,98],"various":[9],"applications.":[10],"However,":[11],"existing":[12],"studies":[13],"in":[14,138,157],"bioacoustics":[15],"often":[16],"focus":[17],"on":[18,51,77,112,130],"a":[19,57,72,99],"limited":[20],"number":[21],"of":[22,28,37,91,102],"species,":[23],"potentially":[24],"hindering":[25],"the":[26,34,87,131,139,146],"transferability":[27],"models":[29,163],"different":[31],"species.":[32],"Furthermore,":[33],"manual":[35],"annotation":[36],"data":[39,55,115],"is":[40],"both":[41,121],"costly":[42],"and":[43,89,104,123,134,164],"labor-intensive.":[44],"To":[45,153],"address":[46],"these":[47],"challenges,":[48],"self-supervised":[49],"learning":[50],"large-scale":[52,113],"presents":[56],"promising":[58],"solution.":[59],"In":[60],"this":[61,92],"paper,":[62],"we":[63,159],"introduce":[64],"GPM-BT":[65,126],"(General":[66],"Pre-training":[67],"Model":[68],"for":[69],"Bioacoustic":[70,141],"Tasks),":[71],"self-supervised,":[73],"Transformer-based":[74],"model":[75,118],"pre-trained":[76],"approximately":[78],"1.2":[79],"million":[80],"unannotated":[81],"samples.":[84],"We":[85],"evaluate":[86],"scalability":[88],"effectiveness":[90],"pre-training":[93,111],"approach":[94],"through":[95],"comprehensive":[96],"experiments":[97],"broad":[100],"range":[101],"classification":[103],"detection":[105],"tasks.":[106],"Our":[107],"results":[108],"demonstrate":[109],"that":[110],"significantly":[116],"enhances":[117],"performance,":[119],"improving":[120],"generalization":[122],"robustness.":[124],"Notably,":[125],"achieves":[127],"state-of-the-art":[128],"performance":[129],"BEANS":[132],"benchmark":[133],"secures":[135],"first":[136],"place":[137],"Few-shot":[140],"Event":[142],"Detection":[143],"task":[144],"at":[145],"IEEE":[147],"DCASE":[148],"2024":[149],"Challenge<sup":[150],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[151,166],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[152],"further":[154],"advance":[155],"research":[156],"bioacoustics,":[158],"have":[160],"open-sourced":[161],"our":[162],"code<sup":[165],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
