{"id":"https://openalex.org/W3090699804","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207440","title":"pcIRM: Complex Ideal Ratio Masking for Speaker-Independent Monaural Source Separation with Utterance Permutation Invariant Training","display_name":"pcIRM: Complex Ideal Ratio Masking for Speaker-Independent Monaural Source Separation with Utterance Permutation Invariant Training","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3090699804","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207440","mag":"3090699804"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207440","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207440","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","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/A5100444401","display_name":"Wen Zhang","orcid":"https://orcid.org/0000-0002-7945-9580"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wen Zhang","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, China","College of Meteorology and Oceanology, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Meteorology and Oceanology, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100673955","display_name":"Xiaoyong Li","orcid":"https://orcid.org/0000-0002-0497-5978"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyong Li","raw_affiliation_strings":["College of Meteorology and Oceanology, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"College of Meteorology and Oceanology, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049270622","display_name":"Aolong Zhou","orcid":"https://orcid.org/0000-0002-3732-0847"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aolong Zhou","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, China","College of Meteorology and Oceanology, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Meteorology and Oceanology, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102374259","display_name":"Kaijun Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaijun Ren","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, China","College of Meteorology and Oceanology, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Meteorology and Oceanology, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101788380","display_name":"Junqiang Song","orcid":"https://orcid.org/0009-0003-2686-566X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junqiang Song","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology, China","College of Meteorology and Oceanology, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Meteorology and Oceanology, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100444401"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.1515,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44173799,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"83","issue":null,"first_page":"1","last_page":"8"},"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":0.9990000128746033,"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":0.9962999820709229,"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/monaural","display_name":"Monaural","score":0.7589536905288696},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7355620861053467},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5706954002380371},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5050111413002014},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4808974266052246},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47791963815689087},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.44155967235565186},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.42801207304000854},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.41255974769592285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3949960768222809},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3845500648021698},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3738548755645752},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19095909595489502},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.12395584583282471}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.7589536905288696},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7355620861053467},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5706954002380371},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5050111413002014},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4808974266052246},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47791963815689087},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.44155967235565186},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.42801207304000854},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.41255974769592285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3949960768222809},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3845500648021698},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3738548755645752},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19095909595489502},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.12395584583282471},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207440","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207440","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W285277413","https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W2031647436","https://openalex.org/W2046869671","https://openalex.org/W2048142341","https://openalex.org/W2069681747","https://openalex.org/W2122982914","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2291877678","https://openalex.org/W2460742184","https://openalex.org/W2594251744","https://openalex.org/W2604917595","https://openalex.org/W2678916739","https://openalex.org/W2734774145","https://openalex.org/W2929481141","https://openalex.org/W2937090489","https://openalex.org/W2962715207","https://openalex.org/W2962866211","https://openalex.org/W2964121744","https://openalex.org/W2973062255","https://openalex.org/W2990014691","https://openalex.org/W6631190155","https://openalex.org/W6755462816","https://openalex.org/W6770505166"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2045506488","https://openalex.org/W1983045063","https://openalex.org/W2103031592","https://openalex.org/W1967226023","https://openalex.org/W2538939196","https://openalex.org/W2955471771"],"abstract_inverted_index":{"Typical":[0],"speech":[1,70],"separation":[2,150],"systems":[3],"usually":[4],"operate":[5],"in":[6,177],"the":[7,13,18,46,73,103,120,124,135,145,153,162,170,180],"time-frequency":[8],"(T-F)":[9],"domain":[10],"by":[11],"enhancing":[12],"magnitude":[14,38],"response":[15,20],"and":[16,39,53,142,156],"leaving":[17],"phase":[19,27,40],"unaltered.":[21],"Recent":[22],"studies,":[23],"however,":[24],"suggest":[25],"that":[26,160],"is":[28,132],"important":[29],"for":[30,84,152],"perceptual":[31],"quality,":[32],"leading":[33],"some":[34],"researchers":[35],"to":[36,63,68,92,101,159],"consider":[37],"spectrum":[41],"enhancements.":[42],"The":[43],"merging":[44],"of":[45,105,161,172,179],"complex":[47],"ideal":[48],"ratio":[49,182],"masking":[50],"(cIRM)":[51],"estimation":[52,122],"training":[54,128],"with":[55,95,123,134,144],"deep":[56,136],"neural":[57],"network":[58],"(DNN)":[59],"has":[60,79],"been":[61],"proved":[62],"be":[64],"an":[65],"effective":[66],"way":[67],"improve":[69],"separation.":[71],"Furthermore,":[72],"label":[74],"ambiguity":[75],"(or":[76],"permutation)":[77],"problem":[78,104],"become":[80],"a":[81,112],"major":[82],"barrier":[83],"speaker-independent":[85,106],"multi-talker":[86],"source":[87,108],"separation,":[88,109],"which":[89,117],"prompts":[90],"us":[91],"come":[93],"up":[94],"new":[96],"solutions.":[97],"In":[98],"this":[99],"paper,":[100],"solve":[102],"monaural":[107],"we":[110],"propose":[111],"novel":[113],"method":[114,155,176],"called":[115],"pcIRM,":[116],"creatively":[118],"achieves":[119],"cIRM":[121],"utterance-level":[125],"permutation":[126],"invariant":[127],"(uPIT).":[129],"Specifically,":[130],"pcIRM":[131,175],"implemented":[133],"bidirectional":[137],"LSTM":[138],"(Bi-LSTM)":[139],"RNN":[140],"network,":[141],"evaluated":[143],"WSJ0-2mix":[146],"datasets.":[147],"We":[148],"report":[149],"results":[151,168],"proposed":[154,174],"compare":[157],"them":[158],"existing":[163],"state-of-the-art":[164],"methods.":[165],"Extensive":[166],"experimental":[167],"demonstrate":[169],"advantages":[171],"our":[173],"terms":[178],"signal-to-distortion":[181],"(SDR)":[183],"metric.":[184]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}