{"id":"https://openalex.org/W2987974664","doi":"https://doi.org/10.1109/icassp40776.2020.9054137","title":"Coincidence, Categorization, and Consolidation: Learning to Recognize Sounds with Minimal Supervision","display_name":"Coincidence, Categorization, and Consolidation: Learning to Recognize Sounds with Minimal Supervision","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2987974664","doi":"https://doi.org/10.1109/icassp40776.2020.9054137","mag":"2987974664"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054137","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1911.05894","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103622427","display_name":"Aren Jansen","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":"Aren Jansen","raw_affiliation_strings":["Google Research, Mountain View, New York, CA, NY, USA","[Google Research, Mountain View, New York, CA, NY, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, New York, CA, NY, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google Research, Mountain View, New York, CA, NY, USA]","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055458377","display_name":"Daniel P. W. Ellis","orcid":"https://orcid.org/0000-0002-5076-4311"},"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":"Daniel P. W. Ellis","raw_affiliation_strings":["Google Research, Mountain View, New York, CA, NY, USA","[Google Research, Mountain View, New York, CA, NY, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, New York, CA, NY, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google Research, Mountain View, New York, CA, NY, USA]","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014428891","display_name":"Shawn 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":"Shawn Hershey","raw_affiliation_strings":["Google Research, Mountain View, New York, CA, NY, USA","[Google Research, Mountain View, New York, CA, NY, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, New York, CA, NY, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google Research, Mountain View, New York, CA, NY, USA]","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110435728","display_name":"Robert C. Moore","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":"R. Channing Moore","raw_affiliation_strings":["Google Research, Mountain View, New York, CA, NY, USA","[Google Research, Mountain View, New York, CA, NY, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, New York, CA, NY, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google Research, Mountain View, New York, CA, NY, USA]","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059222327","display_name":"Manoj Plakal","orcid":"https://orcid.org/0000-0001-6759-3873"},"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":"Manoj Plakal","raw_affiliation_strings":["Google Research, Mountain View, New York, CA, NY, USA","[Google Research, Mountain View, New York, CA, NY, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, New York, CA, NY, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google Research, Mountain View, New York, CA, NY, USA]","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078560039","display_name":"Ashok C. Popat","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":"Ashok C. Popat","raw_affiliation_strings":["Google Research, Mountain View, New York, CA, NY, USA","[Google Research, Mountain View, New York, CA, NY, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, New York, CA, NY, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google Research, Mountain View, New York, CA, NY, USA]","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026650852","display_name":"Rif A. Saurous","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":"Rif A. Saurous","raw_affiliation_strings":["Google Research, Mountain View, New York, CA, NY, USA","[Google Research, Mountain View, New York, CA, NY, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, New York, CA, NY, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google Research, Mountain View, New York, CA, NY, USA]","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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"121","last_page":"125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.998199999332428,"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":0.998199999332428,"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":0.9890000224113464,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9747999906539917,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/categorization","display_name":"Categorization","score":0.7554011344909668},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6355512142181396},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.6184125542640686},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5938250422477722},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5868077278137207},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5653266310691833},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5630394220352173},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5412927865982056},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.5173208713531494},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5060169100761414},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45396432280540466},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37015825510025024},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13675141334533691}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7554011344909668},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6355512142181396},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.6184125542640686},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5938250422477722},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5868077278137207},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5653266310691833},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5630394220352173},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5412927865982056},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.5173208713531494},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5060169100761414},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45396432280540466},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37015825510025024},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13675141334533691},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054137","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1911.05894","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.05894","pdf_url":"https://arxiv.org/pdf/1911.05894","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2987974664","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1911.05894","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1911.05894","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1911.05894","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/27ct-ya09","is_oa":true,"landing_page_url":"https://doi.org/10.17023/27ct-ya09","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1911.05894","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.05894","pdf_url":"https://arxiv.org/pdf/1911.05894","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2987974664.pdf","grobid_xml":"https://content.openalex.org/works/W2987974664.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W219040644","https://openalex.org/W343636949","https://openalex.org/W1520997877","https://openalex.org/W1982182713","https://openalex.org/W1991051444","https://openalex.org/W2033015347","https://openalex.org/W2074488330","https://openalex.org/W2108392811","https://openalex.org/W2142714010","https://openalex.org/W2145038566","https://openalex.org/W2162207320","https://openalex.org/W2294167968","https://openalex.org/W2326925005","https://openalex.org/W2483390977","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2595120084","https://openalex.org/W2619697695","https://openalex.org/W2767754137","https://openalex.org/W2785294821","https://openalex.org/W2842511635","https://openalex.org/W2883725317","https://openalex.org/W2938798071","https://openalex.org/W2939574508","https://openalex.org/W2962865004","https://openalex.org/W2963420272","https://openalex.org/W2963680395","https://openalex.org/W2963902314","https://openalex.org/W3155584997","https://openalex.org/W6601741498","https://openalex.org/W6631216910","https://openalex.org/W6674787384","https://openalex.org/W6680970901","https://openalex.org/W6685380521","https://openalex.org/W6735927292","https://openalex.org/W6747899497","https://openalex.org/W6840487619"],"related_works":["https://openalex.org/W3015817524","https://openalex.org/W2053354347","https://openalex.org/W1494485407","https://openalex.org/W3200580571","https://openalex.org/W2949114386","https://openalex.org/W2963154787","https://openalex.org/W3090425949","https://openalex.org/W2796429358","https://openalex.org/W3044803312","https://openalex.org/W3093563057","https://openalex.org/W2962845320","https://openalex.org/W3173094203","https://openalex.org/W3093471646","https://openalex.org/W2887108625","https://openalex.org/W2218417636","https://openalex.org/W3129814727","https://openalex.org/W3206649123","https://openalex.org/W1876424772","https://openalex.org/W3149607248","https://openalex.org/W3110370715"],"abstract_inverted_index":{"Humans":[0],"do":[1],"not":[2],"acquire":[3],"perceptual":[4],"abilities":[5],"in":[6,130],"the":[7,131],"way":[8],"we":[9,44,115],"train":[10],"machines.":[11],"While":[12],"machine":[13],"learning":[14,33,38,47,90],"algorithms":[15],"typically":[16],"operate":[17],"on":[18,30,61,82],"large":[19],"collections":[20],"of":[21,65,133],"randomly-chosen,":[22],"explicitly-labeled":[23],"examples,":[24],"human":[25],"acquisition":[26],"relies":[27],"more":[28],"heavily":[29],"multimodal":[31],"unsupervised":[32,120],"(as":[34,39],"infants)":[35],"and":[36,52,67,85,123],"active":[37,89],"children).":[40],"With":[41],"this":[42],"motivation,":[43],"present":[45],"a":[46,57,62,71,87,106,117,127,138],"framework":[48],"for":[49],"sound":[50,108],"representation":[51,122],"recognition":[53],"that":[54,74,92],"combines":[55],"(i)":[56],"self-supervised":[58],"objective":[59,73],"based":[60],"general":[63],"notion":[64],"unimodal":[66],"cross-modal":[68],"coincidence,":[69],"(ii)":[70],"clustering":[72],"reflects":[75],"our":[76,83],"need":[77],"to":[78,97,112,126,136],"impose":[79],"categorical":[80],"structure":[81],"experiences,":[84],"(iii)":[86],"cluster-based":[88],"procedure":[91],"solicits":[93],"targeted":[94],"weak":[95],"supervision":[96],"consolidate":[98],"categories":[99],"into":[100],"relevant":[101],"semantic":[102],"classes.":[103],"By":[104],"training":[105],"combined":[107],"embedding/clustering/classification":[109],"network":[110],"according":[111],"these":[113],"criteria,":[114],"achieve":[116],"new":[118],"state-of-the-art":[119],"audio":[121],"demonstrate":[124],"up":[125],"20-fold":[128],"reduction":[129],"number":[132],"labels":[134],"required":[135],"reach":[137],"desired":[139],"classification":[140],"performance.":[141]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}