{"id":"https://openalex.org/W2943839958","doi":"https://doi.org/10.1109/iscslp.2018.8706611","title":"Utterance-level Permutation Invariant Training with Discriminative Learning for Single Channel Speech Separation","display_name":"Utterance-level Permutation Invariant Training with Discriminative Learning for Single Channel Speech Separation","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2943839958","doi":"https://doi.org/10.1109/iscslp.2018.8706611","mag":"2943839958"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2018.8706611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5037493212","display_name":"Cunhang Fan","orcid":"https://orcid.org/0000-0001-6318-8803"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cunhang Fan","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395443","display_name":"Bin Liu","orcid":"https://orcid.org/0000-0001-8800-7239"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Liu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111856667","display_name":"Zhengqi Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqi Wen","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078525423","display_name":"Jiangyan Yi","orcid":"https://orcid.org/0000-0003-2422-4618"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangyan Yi","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624455","display_name":"Ye Bai","orcid":"https://orcid.org/0000-0001-5533-6909"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Bai","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3302,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.82669621,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"4","issue":null,"first_page":"26","last_page":"30"},"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":0.9994999766349792,"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":0.9991000294685364,"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/discriminative-model","display_name":"Discriminative model","score":0.7871854305267334},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.6857624650001526},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6179274320602417},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5543748140335083},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5357178449630737},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.4878878593444824},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4776783585548401},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4727764129638672},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.45578545331954956},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4332464933395386},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4321766495704651},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.41727009415626526},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.331967294216156},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.31524065136909485},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1019456684589386}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7871854305267334},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.6857624650001526},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6179274320602417},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5543748140335083},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5357178449630737},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.4878878593444824},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4776783585548401},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4727764129638672},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.45578545331954956},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4332464933395386},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4321766495704651},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.41727009415626526},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.331967294216156},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31524065136909485},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1019456684589386},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2018.8706611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W185399533","https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W1550027367","https://openalex.org/W1748744376","https://openalex.org/W1977812963","https://openalex.org/W2031647436","https://openalex.org/W2060822897","https://openalex.org/W2069681747","https://openalex.org/W2108384452","https://openalex.org/W2127851351","https://openalex.org/W2147174722","https://openalex.org/W2158904676","https://openalex.org/W2221409856","https://openalex.org/W2271840356","https://openalex.org/W2405258286","https://openalex.org/W2460742184","https://openalex.org/W2508884455","https://openalex.org/W2558649592","https://openalex.org/W2561557072","https://openalex.org/W2734774145","https://openalex.org/W2745634895","https://openalex.org/W2800022361","https://openalex.org/W2800664709","https://openalex.org/W2804644188","https://openalex.org/W2883127466","https://openalex.org/W2962866211","https://openalex.org/W2964121744","https://openalex.org/W6607486085","https://openalex.org/W6629014544","https://openalex.org/W6631190155","https://openalex.org/W6637891802","https://openalex.org/W6658463413","https://openalex.org/W6688843265","https://openalex.org/W6713676406"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2353179089","https://openalex.org/W2153315159","https://openalex.org/W3177678247","https://openalex.org/W3103844505","https://openalex.org/W2372338004"],"abstract_inverted_index":{"The":[0],"challenge":[1],"in":[2],"deep":[3,45],"learning":[4,46,86],"for":[5],"speaker":[6],"independent":[7],"speech":[8],"separation":[9],"comes":[10],"from":[11],"the":[12,29,52,56,70,74,98,106,109,119,122,125,134,156],"label":[13],"ambiguity":[14],"or":[15],"permutation":[16,19,54],"problem.":[17],"Utterance-level":[18],"invariant":[20],"training":[21],"(uPIT)":[22],"technique":[23],"solves":[24],"this":[25,78,91],"problem":[26,92],"by":[27,93],"minimizing":[28],"mean":[30],"square":[31],"error":[32],"(MSE)":[33],"over":[34],"all":[35],"permutations":[36],"between":[37,108,121],"outputs":[38,110],"and":[39,113,124,144,151],"targets.":[40],"It":[41],"is":[42,130],"a":[43,82],"state-of-the-art":[44],"architecture.":[47],"However,":[48],"uPIT":[49,83,157],"only":[50],"minimizes":[51],"chosen":[53],"with":[55,62,84,155],"lowest":[57],"MSE,":[58],"not":[59],"discriminates":[60],"it":[61],"other":[63,102,128],"permutations.":[64],"This":[65],"may":[66],"lead":[67],"to":[68,89],"increase":[69],"possibility":[71],"of":[72,111,127],"remixing":[73],"separated":[75],"sources.":[76],"In":[77,101],"paper,":[79],"we":[80,104],"propose":[81],"discriminative":[85],"(uPITDL)":[87],"method":[88],"solve":[90],"adding":[94],"one":[95],"regularization":[96],"at":[97],"cost":[99],"function.":[100],"words,":[103],"minimize":[105],"difference":[107],"model":[112,136],"their":[114],"corresponding":[115],"reference":[116],"signals.":[117],"Moreover,":[118],"dissimilarity":[120],"prediction":[123],"targets":[126],"sources":[129],"maximized.":[131],"We":[132],"evaluate":[133],"proposed":[135],"on":[137],"WSJ0-2mix":[138],"dataset.":[139],"Experimental":[140],"results":[141],"show":[142],"22.0%":[143],"24.8%":[145],"relative":[146],"improvements":[147],"under":[148],"both":[149],"closed":[150],"open":[152],"conditions":[153],"compared":[154],"baseline.":[158]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}