{"id":"https://openalex.org/W2981436548","doi":"https://doi.org/10.1109/icassp40776.2020.9054172","title":"Two-Step Sound Source Separation: Training On Learned Latent Targets","display_name":"Two-Step Sound Source Separation: Training On Learned Latent Targets","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2981436548","doi":"https://doi.org/10.1109/icassp40776.2020.9054172","mag":"2981436548"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054172","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/1910.09804","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/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Efthymios Tzinis","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001842601","display_name":"Shrikant Venkataramani","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikant Venkataramani","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102709539","display_name":"Zhepei Wang","orcid":"https://orcid.org/0000-0001-7845-5273"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhepei Wang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023830739","display_name":"Cem Subakan","orcid":"https://orcid.org/0000-0002-7593-6589"},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Cem Subakan","raw_affiliation_strings":["Mila\u2013Quebec Artificial Intelligence Institute"],"affiliations":[{"raw_affiliation_string":"Mila\u2013Quebec Artificial Intelligence Institute","institution_ids":["https://openalex.org/I4210164802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038903729","display_name":"Paris Smaragdis","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paris Smaragdis","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5016864112"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":7.9238,"has_fulltext":false,"cited_by_count":67,"citation_normalized_percentile":{"value":0.98351109,"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":"31","last_page":"35"},"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":0.9997000098228455,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7059133052825928},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6145246028900146},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5778992772102356},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5728070139884949},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4397466480731964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41448843479156494},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3871808648109436},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21251437067985535}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7059133052825928},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6145246028900146},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5778992772102356},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5728070139884949},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4397466480731964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41448843479156494},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3871808648109436},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21251437067985535},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054172","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:1910.09804","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.09804","pdf_url":"https://arxiv.org/pdf/1910.09804","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:1910.09804","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.09804","pdf_url":"https://arxiv.org/pdf/1910.09804","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":37,"referenced_works":["https://openalex.org/W1485161427","https://openalex.org/W1522301498","https://openalex.org/W1555814299","https://openalex.org/W1790748249","https://openalex.org/W2024490156","https://openalex.org/W2031647436","https://openalex.org/W2052666245","https://openalex.org/W2158456262","https://openalex.org/W2221409856","https://openalex.org/W2398042854","https://openalex.org/W2460742184","https://openalex.org/W2625041691","https://openalex.org/W2774707525","https://openalex.org/W2894785362","https://openalex.org/W2896457183","https://openalex.org/W2899515918","https://openalex.org/W2900132857","https://openalex.org/W2933708090","https://openalex.org/W2935846637","https://openalex.org/W2940948712","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962935966","https://openalex.org/W2963317762","https://openalex.org/W2963341956","https://openalex.org/W2963443859","https://openalex.org/W2964058413","https://openalex.org/W2964237233","https://openalex.org/W2972460025","https://openalex.org/W2998657200","https://openalex.org/W3099330747","https://openalex.org/W3124794156","https://openalex.org/W4398958419","https://openalex.org/W6631190155","https://openalex.org/W6688843265","https://openalex.org/W6746914816","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2071676784","https://openalex.org/W4292513318","https://openalex.org/W4308092240","https://openalex.org/W2287611352","https://openalex.org/W320684304","https://openalex.org/W1509352139","https://openalex.org/W2053286651","https://openalex.org/W2077498359"],"abstract_inverted_index":{"In":[0,17,56],"this":[1,102],"paper,":[2],"we":[3,21,44,61,82],"propose":[4],"a":[5,13,23,29,46,66,131],"two-step":[6],"training":[7],"procedure":[8],"for":[9],"source":[10],"separation":[11,34,47,97,118,138],"via":[12],"deep":[14],"neural":[15,135],"network.":[16],"the":[18,41,52,78,87,90,114,117],"first":[19],"step":[20],"learn":[22,113],"transform":[24,115],"(and":[25],"it's":[26],"inverse)":[27],"to":[28,58,69,110,127,130],"latent":[30,79],"space":[31],"where":[32],"masking-based":[33],"performance":[35,107],"using":[36],"oracles":[37],"is":[38,124],"optimal.":[39],"For":[40],"second":[42],"step,":[43],"train":[45],"module":[48,119],"that":[49,75,84,99,112],"operates":[50],"on":[51],"previously":[53],"learned":[54],"space.":[55],"order":[57],"do":[59],"so,":[60],"also":[62],"make":[63],"use":[64],"of":[65,134],"scale-invariant":[67],"signal":[68],"distortion":[70],"ratio":[71],"(SI-SDR)":[72],"loss":[73],"function":[74],"works":[76],"in":[77,89],"space,":[80],"and":[81,116],"prove":[83],"it":[85],"lower-bounds":[86],"SI-SDR":[88],"time":[91],"domain.":[92],"We":[93],"run":[94],"various":[95],"sound":[96],"experiments":[98],"show":[100],"how":[101],"approach":[103],"can":[104],"obtain":[105],"better":[106],"as":[108],"compared":[109],"systems":[111],"jointly.":[120],"The":[121],"proposed":[122],"methodology":[123],"general":[125],"enough":[126],"be":[128],"applicable":[129],"large":[132],"class":[133],"network":[136],"end-to-end":[137],"systems.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":10}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}