{"id":"https://openalex.org/W2990666817","doi":"https://doi.org/10.1109/icassp40776.2020.9053921","title":"Improving Universal Sound Separation Using Sound Classification","display_name":"Improving Universal Sound Separation Using Sound Classification","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2990666817","doi":"https://doi.org/10.1109/icassp40776.2020.9053921","mag":"2990666817"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053921","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":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1911.07951","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016864112","display_name":"Efthymios Tzinis","orcid":"https://orcid.org/0000-0002-1047-1338"},"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":true,"raw_author_name":"Efthymios Tzinis","raw_affiliation_strings":["Google Research"],"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"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","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"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","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"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","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"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5016864112"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":8.3809,"has_fulltext":false,"cited_by_count":71,"citation_normalized_percentile":{"value":0.98573578,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"96","last_page":"100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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/sound","display_name":"Sound (geography)","score":0.7568302154541016},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6021013259887695},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5450199246406555},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.5012092590332031},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36858680844306946},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11723312735557556},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.07007518410682678}],"concepts":[{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.7568302154541016},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6021013259887695},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5450199246406555},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.5012092590332031},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36858680844306946},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11723312735557556},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07007518410682678}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053921","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:1911.07951","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.07951","pdf_url":"https://arxiv.org/pdf/1911.07951","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1911.07951","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.07951","pdf_url":"https://arxiv.org/pdf/1911.07951","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2031647436","https://openalex.org/W2125389028","https://openalex.org/W2221409856","https://openalex.org/W2328009109","https://openalex.org/W2423557781","https://openalex.org/W2460742184","https://openalex.org/W2475611006","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2612445135","https://openalex.org/W2735663686","https://openalex.org/W2743167696","https://openalex.org/W2767754137","https://openalex.org/W2889404825","https://openalex.org/W2945544731","https://openalex.org/W2949447796","https://openalex.org/W2952218014","https://openalex.org/W2952269766","https://openalex.org/W2962715207","https://openalex.org/W2962753171","https://openalex.org/W2962756039","https://openalex.org/W2963189033","https://openalex.org/W2963783181","https://openalex.org/W2964058413","https://openalex.org/W2964121744","https://openalex.org/W2969034647","https://openalex.org/W2973062255","https://openalex.org/W2991226820","https://openalex.org/W2998657200","https://openalex.org/W3099330747","https://openalex.org/W3124972797","https://openalex.org/W4293665662","https://openalex.org/W4297775537","https://openalex.org/W6631190155","https://openalex.org/W6678815747","https://openalex.org/W6720957491","https://openalex.org/W6729831399","https://openalex.org/W6734260513","https://openalex.org/W6737664043","https://openalex.org/W6742972455","https://openalex.org/W6755462816","https://openalex.org/W6762643587","https://openalex.org/W6766938422"],"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/W2071676784","https://openalex.org/W2376932109","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"approaches":[2,20],"have":[3],"recently":[4],"achieved":[5],"impressive":[6],"performance":[7],"on":[8,23,78],"both":[9],"audio":[10,17],"source":[11,18,32,126],"separation":[12,19,108,131,143],"and":[13,37,133,173],"sound":[14,48,74,88,100,192],"classification.":[15],"Most":[16],"focus":[21],"only":[22],"separating":[24],"sources":[25,55,165],"belonging":[26],"to":[27,52,85,105,140],"a":[28,79,99,107,141,147,154,179,187],"restricted":[29],"domain":[30],"of":[31,46,61,82,152,170,182],"classes,":[33],"such":[34],"as":[35],"speech":[36],"music.":[38],"However,":[39],"recent":[40],"work":[41],"has":[42],"demonstrated":[43],"the":[44,69],"possibility":[45],"\"universal":[47],"separation\",":[49],"which":[50],"aims":[51],"separate":[53],"acoustic":[54],"from":[56,98,128,162],"an":[57,122,129],"open":[58],"domain,":[59],"regardless":[60],"their":[62,134],"class.":[63],"In":[64,90],"this":[65,183],"paper,":[66],"we":[67,92,157],"utilize":[68],"semantic":[70,95],"information":[71],"learned":[72],"by":[73],"classifier":[75,101,160],"networks":[76],"trained":[77],"vast":[80],"amount":[81],"diverse":[83],"sounds":[84],"improve":[86],"universal":[87,191],"separation.":[89,193],"particular,":[91],"show":[93],"that":[94,159],"embeddings":[96,137,161],"extracted":[97],"can":[102],"be":[103],"used":[104],"condition":[106],"network,":[109],"providing":[110],"it":[111],"with":[112],"useful":[113,120],"additional":[114],"information.":[115],"This":[116],"approach":[117],"is":[118],"especially":[119],"in":[121],"iterative":[123,176],"setup,":[124],"where":[125],"estimates":[127],"initial":[130],"stage":[132],"corresponding":[135],"classifier-derived":[136],"are":[138],"fed":[139],"second":[142],"network.":[144],"By":[145],"performing":[146],"thorough":[148],"hyperparameter":[149],"search":[150],"consisting":[151],"over":[153],"thousand":[155],"experiments,":[156],"find":[158],"oracle":[163,184],"clean":[164],"provide":[166],"nearly":[167],"one":[168],"dB":[169],"SNR":[171],"gain,":[172],"our":[174],"best":[175],"models":[177],"achieve":[178],"significant":[180],"fraction":[181],"performance,":[185],"establishing":[186],"new":[188],"state-of-the-art":[189],"for":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":13}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}