{"id":"https://openalex.org/W3206645997","doi":"https://doi.org/10.21437/interspeech.2022-864","title":"MusicNet: Compact Convolutional Neural Network for Real-time Background Music Detection","display_name":"MusicNet: Compact Convolutional Neural Network for Real-time Background Music Detection","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W3206645997","doi":"https://doi.org/10.21437/interspeech.2022-864","mag":"3206645997"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-864","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-864","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5001022750","display_name":"Chandan K. Reddy","orcid":"https://orcid.org/0000-0003-2839-3662"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chandan Reddy","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024067566","display_name":"Vishak Gopal","orcid":"https://orcid.org/0009-0005-3887-1439"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vishak Gopal","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033701513","display_name":"Harishchandra Dubey","orcid":"https://orcid.org/0000-0003-0476-3884"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harishchandra Dubey","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068040769","display_name":"Ross Cutler","orcid":"https://orcid.org/0000-0002-2004-3003"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ross Cutler","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033592362","display_name":"Sergiy Matusevych","orcid":"https://orcid.org/0009-0002-4774-0965"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergiy Matusevych","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086512263","display_name":"Robert Aichner","orcid":"https://orcid.org/0009-0000-6754-107X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Aichner","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3631,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.45829399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4162","last_page":"4166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9980000257492065,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7812412977218628},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7711511850357056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47170066833496094},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40760648250579834},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3803907036781311}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7812412977218628},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7711511850357056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47170066833496094},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40760648250579834},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3803907036781311}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-864","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-864","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1980993072","https://openalex.org/W2086384421","https://openalex.org/W2105068979","https://openalex.org/W2106339924","https://openalex.org/W2129120544","https://openalex.org/W2166481862","https://openalex.org/W2167665852","https://openalex.org/W2197404611","https://openalex.org/W2593116425","https://openalex.org/W2770119437","https://openalex.org/W2952003418","https://openalex.org/W2953763392","https://openalex.org/W2963022469","https://openalex.org/W2964891022","https://openalex.org/W3049406809","https://openalex.org/W3090169026","https://openalex.org/W3094550259","https://openalex.org/W3112098675","https://openalex.org/W3120907516","https://openalex.org/W3160076412","https://openalex.org/W3197042120"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"With":[0],"the":[1,30,47,62,96,103,107,165],"recent":[2],"growth":[3],"of":[4,23,83,106,135],"remote":[5],"work,":[6],"online":[7],"meetings":[8],"often":[9],"encounter":[10],"challenging":[11],"audio":[12,85],"contexts":[13],"such":[14],"as":[15,86],"background":[16,44,59],"noise,":[17],"music,":[18],"and":[19,58,88,112,159],"echo.Accurate":[20],"real-time":[21,48],"detection":[22],"music":[24,45,53],"events":[25],"can":[26],"help":[27],"to":[28],"improve":[29],"user":[31],"experience.In":[32],"this":[33],"paper,":[34],"we":[35,121,169],"present":[36],"MusicNet,":[37],"a":[38,68,130,138],"compact":[39,69],"neural":[40,71],"model":[41,101],"for":[42],"detecting":[43],"in":[46,95,152],"communications":[49],"pipeline.In":[50],"video":[51],"meetings,":[52],"frequently":[54],"co-occurs":[55],"with":[56,125],"speech":[57],"noises,":[60],"making":[61],"accurate":[63],"classification":[64],"quite":[65],"challenging.We":[66],"propose":[67],"convolutional":[70],"network":[72],"core":[73],"preceded":[74],"by":[75],"an":[76],"in-model":[77],"featurization":[78,94],"layer.MusicNet":[79],"takes":[80],"9":[81],"seconds":[82],"raw":[84],"input":[87],"does":[89],"not":[90],"require":[91],"any":[92],"model-specific":[93],"product":[97],"stack.We":[98],"train":[99],"our":[100,153],"on":[102,115],"balanced":[104],"subset":[105],"Audio":[108],"Set":[109],"[1]":[110],"data":[111],"validate":[113],"it":[114],"1000":[116],"crowd-sourced":[117],"real":[118],"test":[119],"clips.Finally,":[120],"compare":[122],"MusicNet":[123],"performance":[124],"20":[126],"state-of-the-art":[127,149],"models.MusicNet":[128],"has":[129,160],"true":[131],"positive":[132,141],"rate":[133,142],"(TPR)":[134],"81.3%":[136],"at":[137],"0.1%":[139],"false":[140],"(FPR),":[143],"which":[144],"is":[145,155],"significantly":[146],"better":[147],"than":[148,164],"models":[150,168],"included":[151],"study.MusicNet":[154],"also":[156],"10x":[157],"smaller":[158],"4x":[161],"faster":[162],"inference":[163],"best":[166],"performing":[167],"benchmarked.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}