{"id":"https://openalex.org/W3202820684","doi":"https://doi.org/10.1109/icassp43922.2022.9747202","title":"Improving Bird Classification with Unsupervised Sound Separation","display_name":"Improving Bird Classification with Unsupervised Sound Separation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3202820684","doi":"https://doi.org/10.1109/icassp43922.2022.9747202","mag":"3202820684"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747202","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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":"https://openalex.org/A5060666547","display_name":"Tom Denton","orcid":"https://orcid.org/0000-0003-3866-0031"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tom Denton","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053447215","display_name":"Scott Wisdom","orcid":"https://orcid.org/0000-0001-6671-1428"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Wisdom","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Hershey","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"636","last_page":"640"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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":0.9977999925613403,"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/computer-science","display_name":"Computer science","score":0.7356173396110535},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7235043048858643},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5828998684883118},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5378726124763489},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5197665095329285},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5035852789878845},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4741199314594269},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44672760367393494},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43032899498939514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7356173396110535},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7235043048858643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5828998684883118},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5378726124763489},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5197665095329285},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5035852789878845},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4741199314594269},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44672760367393494},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43032899498939514},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747202","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2150766729","https://openalex.org/W2168130065","https://openalex.org/W2593116425","https://openalex.org/W2738038934","https://openalex.org/W2799258971","https://openalex.org/W2899201823","https://openalex.org/W2952218014","https://openalex.org/W2955425717","https://openalex.org/W2963189033","https://openalex.org/W2963881567","https://openalex.org/W2964058413","https://openalex.org/W2965335183","https://openalex.org/W2982343573","https://openalex.org/W2998657200","https://openalex.org/W3030437843","https://openalex.org/W3093839391","https://openalex.org/W3099330747","https://openalex.org/W3100954996","https://openalex.org/W3151596526","https://openalex.org/W3198408613","https://openalex.org/W4225641627","https://openalex.org/W4388619812","https://openalex.org/W6762718338","https://openalex.org/W6766864773","https://openalex.org/W6771467084","https://openalex.org/W6784499681","https://openalex.org/W6800400543"],"related_works":["https://openalex.org/W2591697403","https://openalex.org/W2953716828","https://openalex.org/W2904857019","https://openalex.org/W2944728705","https://openalex.org/W3011538607","https://openalex.org/W2904022177","https://openalex.org/W4321441197","https://openalex.org/W2359348847","https://openalex.org/W4294432981","https://openalex.org/W2077498359"],"abstract_inverted_index":{"This":[0,68],"paper":[1],"addresses":[2],"the":[3,162,167],"problem":[4],"of":[5,15,19,96,136],"species":[6,60,66],"classification":[7],"in":[8,82,133],"bird":[9,31,97,148],"song":[10],"recordings.":[11,105],"The":[12,54,154],"massive":[13],"amount":[14],"available":[16,56],"field":[17,40],"recordings":[18,41],"birds":[20],"presents":[21],"an":[22],"opportunity":[23],"to":[24,28,71,99],"use":[25],"machine":[26],"learning":[27],"automatically":[29],"track":[30],"populations.":[32],"However,":[33,79],"it":[34],"also":[35,62,140],"poses":[36],"a":[37,75,116,124,145],"problem:":[38],"such":[39,86,103],"typically":[42,63],"contain":[43],"significant":[44],"environmental":[45],"noise":[46],"and":[47,170,187],"overlapping":[48],"vocalizations":[49,73],"that":[50],"interfere":[51],"with":[52,74,144],"classification.":[53],"widely":[55],"training":[57,90,115],"datasets":[58],"for":[59,120],"identification":[61],"leave":[64],"background":[65],"unlabeled.":[67],"leads":[69],"classifiers":[70],"ignore":[72],"low":[76],"signal-to-noise":[77],"ratio.":[78],"recent":[80],"advances":[81],"unsupervised":[83],"sound":[84],"separation,":[85],"as":[87],"mixture":[88],"invariant":[89],"(MixIT),":[91],"enable":[92],"high":[93],"quality":[94,113],"separation":[95,112,127],"songs":[98],"be":[100],"learned":[101],"from":[102],"noisy":[104],"In":[106],"this":[107],"paper,":[108],"we":[109,174],"demonstrate":[110,141],"improved":[111],"when":[114],"MixIT":[117],"model":[118,128,164],"specifically":[119],"birdsong":[121],"data,":[122],"outperforming":[123],"general":[125],"audio":[126],"by":[129,160,183],"over":[130,166],"5":[131],"dB":[132],"SI-SNR":[134],"improvement":[135],"reconstructed":[137],"mixtures.":[138],"We":[139],"precision":[142],"improvements":[143],"downstream":[146],"multi-species":[147],"classifier":[149,156,177],"across":[150],"three":[151],"independent":[152],"datasets.":[153],"best":[155],"performance":[157],"is":[158],"achieved":[159],"taking":[161],"maximum":[163],"activations":[165],"separated":[168],"channels":[169],"original":[171],"audio.":[172],"Finally,":[173],"document":[175],"additional":[176,188],"improvements,":[178],"including":[179],"taxonomic":[180],"classification,":[181],"augmentation":[182],"random":[184],"low-pass":[185],"filters,":[186],"channel":[189],"normalization.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
