{"id":"https://openalex.org/W2982269310","doi":"https://doi.org/10.1109/icassp40776.2020.9053697","title":"Interrupted and Cascaded Permutation Invariant Training for Speech Separation","display_name":"Interrupted and Cascaded Permutation Invariant Training for Speech Separation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2982269310","doi":"https://doi.org/10.1109/icassp40776.2020.9053697","mag":"2982269310"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053697","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","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.12706","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085238281","display_name":"Gene-Ping Yang","orcid":"https://orcid.org/0000-0002-3786-3251"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gene-Ping Yang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, Nation Taiwan University","Nation Taiwan University,Department of Computer Science and Information Engineering"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, Nation Taiwan University","institution_ids":[]},{"raw_affiliation_string":"Nation Taiwan University,Department of Computer Science and Information Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082670614","display_name":"Szu-Lin Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Szu-Lin Wu","raw_affiliation_strings":["Department of Computer Science and Information Engineering, Nation Taiwan University","Nation Taiwan University,Department of Computer Science and Information Engineering"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, Nation Taiwan University","institution_ids":[]},{"raw_affiliation_string":"Nation Taiwan University,Department of Computer Science and Information Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067593181","display_name":"Yao-Wen Mao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao-Wen Mao","raw_affiliation_strings":["Department of Computer Science and Information Engineering, Nation Taiwan University","Nation Taiwan University,Department of Computer Science and Information Engineering"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, Nation Taiwan University","institution_ids":[]},{"raw_affiliation_string":"Nation Taiwan University,Department of Computer Science and Information Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hung-yi Lee","raw_affiliation_strings":["Department of Computer Science and Information Engineering, Nation Taiwan University","Nation Taiwan University,Department of Computer Science and Information Engineering"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, Nation Taiwan University","institution_ids":[]},{"raw_affiliation_string":"Nation Taiwan University,Department of Computer Science and Information Engineering","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044010123","display_name":"Lin-shan Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin-shan Lee","raw_affiliation_strings":["Department of Computer Science and Information Engineering, Nation Taiwan University","Nation Taiwan University,Department of Computer Science and Information Engineering"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, Nation Taiwan University","institution_ids":[]},{"raw_affiliation_string":"Nation Taiwan University,Department of Computer Science and Information Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5085238281"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00713211,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":null,"first_page":"6369","last_page":"6373"},"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6806516647338867},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.6774437427520752},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.6532751321792603},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.6458935141563416},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5143536329269409},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5047184228897095},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41384217143058777},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3802070915699005},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3356119394302368},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3307141363620758},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2147330939769745},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.05607825517654419}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6806516647338867},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6774437427520752},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.6532751321792603},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.6458935141563416},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5143536329269409},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5047184228897095},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41384217143058777},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3802070915699005},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3356119394302368},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3307141363620758},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2147330939769745},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.05607825517654419},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053697","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:1910.12706","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.12706","pdf_url":"https://arxiv.org/pdf/1910.12706","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":"mag:2982269310","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.12706.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1910.12706","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.12706","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:10.17023/9amt-5628","is_oa":true,"landing_page_url":"https://doi.org/10.17023/9amt-5628","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.12706","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.12706","pdf_url":"https://arxiv.org/pdf/1910.12706","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2982269310.pdf","grobid_xml":"https://content.openalex.org/works/W2982269310.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2069681747","https://openalex.org/W2127851351","https://openalex.org/W2150769028","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2465050681","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2799119527","https://openalex.org/W2890964092","https://openalex.org/W2891405874","https://openalex.org/W2892365986","https://openalex.org/W2900834497","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962788625","https://openalex.org/W2962866211","https://openalex.org/W2962905190","https://openalex.org/W2962935966","https://openalex.org/W2972864514","https://openalex.org/W2973143779","https://openalex.org/W6745415975","https://openalex.org/W6754743415","https://openalex.org/W6756102682"],"related_works":["https://openalex.org/W3156681329","https://openalex.org/W2942135187","https://openalex.org/W2952173962","https://openalex.org/W3038884714","https://openalex.org/W3106218560","https://openalex.org/W3046295538","https://openalex.org/W3142540411","https://openalex.org/W3112820730","https://openalex.org/W2440580753","https://openalex.org/W1821290842","https://openalex.org/W3096412097","https://openalex.org/W3020903536","https://openalex.org/W2126903356","https://openalex.org/W2478006492","https://openalex.org/W2971267209","https://openalex.org/W2807202877","https://openalex.org/W2063587930","https://openalex.org/W2029441559","https://openalex.org/W2171183582","https://openalex.org/W2096748209"],"abstract_inverted_index":{"Permutation":[0],"Invariant":[1],"Training":[2],"(PIT)":[3],"has":[4],"long":[5],"been":[6],"a":[7,66,88,107],"stepping":[8],"stone":[9],"method":[10],"for":[11,53,65,76],"training":[12,77,117],"speech":[13],"separation":[14,36],"model":[15,43,55,68,99,134],"in":[16],"handling":[17],"the":[18,25,35,42,46,70,78,98,126,133],"label":[19,28,47,73,104,116],"ambiguity":[20],"problem.":[21],"With":[22,114],"PIT":[23,94],"selecting":[24],"minimum":[26],"cost":[27],"assignments":[29,105],"dynamically,":[30],"very":[31],"few":[32],"studies":[33],"considered":[34],"problem":[37],"to":[38,93],"be":[39],"optimizing":[40],"both":[41],"parameters":[44],"and":[45,57,106],"assignments,":[48],"but":[49],"focused":[50],"on":[51,129],"searching":[52],"good":[54,108],"architecture":[56,69,135],"parameters.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62,86,124],"investigate":[63],"instead":[64],"given":[67],"various":[71],"flexible":[72],"assignment":[74],"strategies":[75],"model,":[79],"rather":[80],"than":[81],"directly":[82],"using":[83],"PIT.":[84],"Surprisingly,":[85],"discover":[87],"significant":[89],"performance":[90,128],"boost":[91],"compared":[92],"is":[95,100,112],"possible":[96],"if":[97],"trained":[101],"with":[102],"fixed":[103,115],"set":[109],"of":[110,122],"labels":[111],"chosen.":[113],"cascaded":[118],"between":[119],"two":[120],"sections":[121],"PIT,":[123],"achieved":[125],"state-of-the-art":[127],"WSJ0-2mix":[130],"without":[131],"changing":[132],"at":[136],"all.":[137]},"counts_by_year":[],"updated_date":"2026-03-21T08:13:44.787528","created_date":"2022-07-28T00:00:00"}
