{"id":"https://openalex.org/W3096787185","doi":"https://doi.org/10.21437/interspeech.2020-1806","title":"Transfer Learning for Improving Singing-Voice Detection in Polyphonic Instrumental Music","display_name":"Transfer Learning for Improving Singing-Voice Detection in Polyphonic Instrumental Music","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096787185","doi":"https://doi.org/10.21437/interspeech.2020-1806","mag":"3096787185"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1806","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1806","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5063248625","display_name":"Yuanbo Hou","orcid":"https://orcid.org/0000-0001-8469-5740"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuanbo Hou","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Frank K. Soong","raw_affiliation_strings":["Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054843960","display_name":"Jian Luan","orcid":"https://orcid.org/0000-0002-2383-226X"},"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":"Jian Luan","raw_affiliation_strings":["Microsoft Search Technology Center Asia, XiaoIce"],"affiliations":[{"raw_affiliation_string":"Microsoft Search Technology Center Asia, XiaoIce","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024084275","display_name":"Shengchen Li","orcid":"https://orcid.org/0000-0002-2488-298X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengchen Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063248625"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":1.6669,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.84805793,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1236","last_page":"1240"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9940999746322632,"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":0.9901000261306763,"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/singing","display_name":"Singing","score":0.873591423034668},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.8232007622718811},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6943042874336243},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6265475749969482},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5858665704727173},{"id":"https://openalex.org/keywords/phonation","display_name":"Phonation","score":0.531827986240387},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.5138362050056458},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4165727198123932},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34350085258483887},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.24555963277816772},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.14105179905891418},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.06042322516441345}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.873591423034668},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.8232007622718811},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6943042874336243},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6265475749969482},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5858665704727173},{"id":"https://openalex.org/C173988693","wikidata":"https://www.wikidata.org/wiki/Q678132","display_name":"Phonation","level":2,"score":0.531827986240387},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.5138362050056458},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4165727198123932},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34350085258483887},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.24555963277816772},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.14105179905891418},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.06042322516441345},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1806","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1806","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.550000011920929,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1589182518","https://openalex.org/W1849277567","https://openalex.org/W2038678505","https://openalex.org/W2048127514","https://openalex.org/W2099760476","https://openalex.org/W2104298926","https://openalex.org/W2124867748","https://openalex.org/W2127177652","https://openalex.org/W2153331925","https://openalex.org/W2154591323","https://openalex.org/W2165698076","https://openalex.org/W2187089797","https://openalex.org/W2293255527","https://openalex.org/W2296751288","https://openalex.org/W2394955069","https://openalex.org/W2405258286","https://openalex.org/W2408239454","https://openalex.org/W2566935005","https://openalex.org/W2567070169","https://openalex.org/W2575145750","https://openalex.org/W2604509013","https://openalex.org/W2604959036","https://openalex.org/W2900819428","https://openalex.org/W2964070952","https://openalex.org/W2964235767","https://openalex.org/W3098357269","https://openalex.org/W4234674466"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W1987047733","https://openalex.org/W2360603947","https://openalex.org/W2378998464","https://openalex.org/W2619297421","https://openalex.org/W2410507441"],"abstract_inverted_index":{"Detecting":[0],"singing-voice":[1,45],"in":[2,166],"polyphonic":[3,79,111,145],"instrumental":[4,70,120],"music":[5,9,71,112],"is":[6,28,32,39,114,127],"critical":[7],"to":[8,77,81,87,129,140,156,186],"information":[10],"retrieval.To":[11],"train":[12,82],"a":[13,17,50,83,141],"robust":[14],"vocal":[15,22,84,98],"detector,":[16],"large":[18],"dataset":[19,42,104],"marked":[20],"with":[21,64,101,109,118,150,180],"or":[23],"non-vocal":[24],"label":[25],"at":[26],"frame-level":[27,30],"essential.However,":[29],"labeling":[31],"time-consuming":[33],"and":[34,68,91,95],"labor":[35],"expensive,":[36],"resulting":[37],"there":[38],"little":[40],"well-labeled":[41,163],"available":[43],"for":[44,54,159],"detection":[46],"(S-VD).Hence,":[47],"we":[48],"propose":[49],"data":[51,165,170],"augmentation":[52,171],"method":[53,172],"S-VD":[55,178],"by":[56,173],"transfer":[57,125,130,174],"learning.In":[58],"this":[59,123],"study,":[60],"clean":[61],"speech":[62],"clips":[63,72],"voice":[65],"activity":[66],"endpoints":[67],"separate":[69],"are":[73],"artificially":[74],"added":[75],"together":[76,117],"simulate":[78],"vocals":[80,116,149],"/non-vocal":[85],"detector.Due":[86],"the":[88,97,102,110,119,131,135,153,160,168],"different":[89],"articulation":[90],"phonation":[92],"between":[93],"speaking":[94],"singing,":[96],"detector":[99],"trained":[100],"artificial":[103,136],"does":[105],"not":[106],"match":[107],"well":[108],"which":[113],"singing":[115,148],"accompaniments.To":[121],"reduce":[122],"mismatch,":[124],"learning":[126,175],"used":[128],"knowledge":[132,155],"learned":[133],"from":[134,184],"speech-plus-music":[137],"training":[138,164],"set":[139],"small":[142],"but":[143],"matched":[144],"dataset,":[146],"i.e.,":[147],"accompaniments.By":[151],"transferring":[152],"related":[154],"make":[157],"up":[158],"lack":[161],"of":[162],"S-VD,":[167],"proposed":[169],"can":[176],"improve":[177],"performance":[179],"an":[181],"F-score":[182],"improvement":[183],"89.5%":[185],"93.2%.":[187]},"counts_by_year":[{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
