{"id":"https://openalex.org/W3093979239","doi":"https://doi.org/10.1109/icassp39728.2021.9413975","title":"Training Noisy Single-Channel Speech Separation with Noisy Oracle Sources: A Large Gap and a Small Step","display_name":"Training Noisy Single-Channel Speech Separation with Noisy Oracle Sources: A Large Gap and a Small Step","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3093979239","doi":"https://doi.org/10.1109/icassp39728.2021.9413975","mag":"3093979239"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.12430","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054649622","display_name":"Matthew Maciejewski","orcid":"https://orcid.org/0000-0002-6336-2135"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Matthew Maciejewski","raw_affiliation_strings":["The Johns Hopkins University,Center for Language and Speech Processing,USA"],"affiliations":[{"raw_affiliation_string":"The Johns Hopkins University,Center for Language and Speech Processing,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112122495","display_name":"Jing Shi","orcid":"https://orcid.org/0000-0003-3225-7145"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Shi","raw_affiliation_strings":["The Johns Hopkins University,Center for Language and Speech Processing,USA"],"affiliations":[{"raw_affiliation_string":"The Johns Hopkins University,Center for Language and Speech Processing,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["The Johns Hopkins University,Center for Language and Speech Processing,USA"],"affiliations":[{"raw_affiliation_string":"The Johns Hopkins University,Center for Language and Speech Processing,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["The Johns Hopkins University,Center for Language and Speech Processing,USA"],"affiliations":[{"raw_affiliation_string":"The Johns Hopkins University,Center for Language and Speech Processing,USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5054649622"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.1539,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39165157,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"5774","last_page":"5778"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9970999956130981,"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/oracle","display_name":"Oracle","score":0.7871413230895996},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7373637557029724},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6613715887069702},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6546463966369629},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6218104958534241},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5524277091026306},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5017173290252686},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5015957355499268},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.42889177799224854},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4250548779964447},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38245245814323425},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2041633427143097},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13605892658233643},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12458279728889465}],"concepts":[{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.7871413230895996},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7373637557029724},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6613715887069702},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6546463966369629},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6218104958534241},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5524277091026306},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5017173290252686},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5015957355499268},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.42889177799224854},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4250548779964447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38245245814323425},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2041633427143097},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13605892658233643},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12458279728889465},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.12430","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.12430","pdf_url":"https://arxiv.org/pdf/2010.12430","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":"doi:10.48550/arxiv.2010.12430","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.12430","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":"article"},{"id":"doi:10.17023/pk4j-x321","is_oa":true,"landing_page_url":"https://doi.org/10.17023/pk4j-x321","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"article"},{"id":"mag:3093979239","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.12430","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.12430","pdf_url":"https://arxiv.org/pdf/2010.12430","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":[{"id":"https://metadata.un.org/sdg/16","score":0.75,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3093979239.pdf","grobid_xml":"https://content.openalex.org/works/W3093979239.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W262275730","https://openalex.org/W1552314771","https://openalex.org/W1608304634","https://openalex.org/W2067295501","https://openalex.org/W2101045344","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2734774145","https://openalex.org/W2884797218","https://openalex.org/W2918296821","https://openalex.org/W2962935966","https://openalex.org/W2964058413","https://openalex.org/W2964121744","https://openalex.org/W2972541922","https://openalex.org/W2982471419","https://openalex.org/W2996322586","https://openalex.org/W2997696598","https://openalex.org/W2998657200","https://openalex.org/W3008283340","https://openalex.org/W3008880747","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3015390914","https://openalex.org/W3016400019","https://openalex.org/W3020336359","https://openalex.org/W3027008958","https://openalex.org/W3036069164","https://openalex.org/W3095082129","https://openalex.org/W4300098418","https://openalex.org/W6631190155","https://openalex.org/W6688843265","https://openalex.org/W6774687970","https://openalex.org/W6777776875","https://openalex.org/W6779963951"],"related_works":["https://openalex.org/W3162577490","https://openalex.org/W3011500442","https://openalex.org/W3031135612","https://openalex.org/W3091830790","https://openalex.org/W1497972261","https://openalex.org/W3209376089","https://openalex.org/W3164223074","https://openalex.org/W3116834994","https://openalex.org/W2153250483","https://openalex.org/W3207551191","https://openalex.org/W1591308582","https://openalex.org/W3198130028","https://openalex.org/W2134749286","https://openalex.org/W3199713199","https://openalex.org/W347019003","https://openalex.org/W2797972631","https://openalex.org/W2106603795","https://openalex.org/W2765164841","https://openalex.org/W3015231328","https://openalex.org/W1557725510"],"abstract_inverted_index":{"As":[0,49],"the":[1,22,65,82,87,91,120,127,135],"performance":[2],"of":[3,67,78,94,106,122,137],"single-channel":[4],"speech":[5,25,100],"separation":[6,36,132,139],"systems":[7,28,140],"has":[8,11],"improved,":[9],"there":[10],"been":[12],"a":[13,38,71],"desire":[14],"to":[15,17,44,61,84,103,118,124],"move":[16],"more":[18],"challenging":[19],"conditions":[20,54],"than":[21],"clean,":[23],"near-field":[24],"that":[26,97,116],"initial":[27],"were":[29],"developed":[30],"on.":[31],"When":[32],"training":[33,45,51,75,114,136],"deep":[34],"learning":[35],"models,":[37],"need":[39],"for":[40,70],"ground":[41],"truth":[42],"leads":[43,102],"on":[46],"synthetic":[47],"mixtures.":[48],"such,":[50],"in":[52],"noisy":[53,79,99,142],"requires":[55],"either":[56],"using":[57,76],"noise":[58,95,123,131],"synthetically":[59],"added":[60],"clean":[62],"speech,":[63,80],"preventing":[64],"use":[66],"in-domain":[68],"data":[69],"noisy-condition":[72],"task,":[73],"or":[74],"mixtures":[77],"requiring":[81],"network":[83],"additionally":[85],"separate":[86],"noise.":[88],"We":[89,109],"demonstrate":[90],"relative":[92],"inseparability":[93,121],"and":[96,129],"this":[98],"paradigm":[101],"significant":[104],"degradation":[105],"system":[107],"performance.":[108],"also":[110],"propose":[111],"an":[112],"SI-SDR\u2013inspired":[113],"objective":[115],"tries":[117],"exploit":[119],"implicitly":[125],"partition":[126],"signal":[128],"discount":[130],"errors,":[133],"enabling":[134],"better":[138],"with":[141],"oracle":[143],"sources.":[144]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}