{"id":"https://openalex.org/W3133834828","doi":"https://doi.org/10.1109/slt48900.2021.9383514","title":"Dual-Path RNN for Long Recording Speech Separation","display_name":"Dual-Path RNN for Long Recording Speech Separation","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3133834828","doi":"https://doi.org/10.1109/slt48900.2021.9383514","mag":"3133834828"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383514","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383514","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/A5090224430","display_name":"Chenda Li","orcid":"https://orcid.org/0000-0003-0299-9914"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenda Li","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048439332","display_name":"Yi Luo","orcid":"https://orcid.org/0000-0002-7447-3885"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Luo","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070114472","display_name":"Cong Han","orcid":"https://orcid.org/0000-0003-2121-000X"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cong Han","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103218426","display_name":"Tianyan Zhou","orcid":"https://orcid.org/0000-0003-3238-2982"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tianyan Zhou","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Corporation"],"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Corporation"],"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064522438","display_name":"Christoph Boeddeker","orcid":"https://orcid.org/0000-0002-8701-1567"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Boeddeker","raw_affiliation_strings":["Paderborn University"],"affiliations":[{"raw_affiliation_string":"Paderborn University","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"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":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100345092","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0002-9011-7928"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Microsoft Corporation"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5090224430"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":3.0472,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.91974307,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"865","last_page":"872"},"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":0.9995999932289124,"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":0.9994000196456909,"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":0.7628371715545654},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.755267858505249},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6955257058143616},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6453805565834045},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5689568519592285},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.557400643825531},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5428594946861267},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.49606308341026306},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.495084673166275},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4490894377231598},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43837472796440125},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4217781126499176},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.41408392786979675},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35367342829704285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3521726429462433},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14612579345703125},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.13614854216575623},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10546362400054932},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09105446934700012}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7628371715545654},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.755267858505249},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6955257058143616},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6453805565834045},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5689568519592285},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.557400643825531},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5428594946861267},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.49606308341026306},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.495084673166275},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4490894377231598},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43837472796440125},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4217781126499176},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.41408392786979675},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35367342829704285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3521726429462433},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14612579345703125},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.13614854216575623},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10546362400054932},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09105446934700012},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383514","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383514","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.550000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307764","display_name":"Microsoft","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"},{"id":"https://openalex.org/F4320310145","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W262275730","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2069681747","https://openalex.org/W2221409856","https://openalex.org/W2407685581","https://openalex.org/W2460742184","https://openalex.org/W2552071709","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2803322398","https://openalex.org/W2891054259","https://openalex.org/W2891405874","https://openalex.org/W2891833136","https://openalex.org/W2939397531","https://openalex.org/W2944972166","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2952752702","https://openalex.org/W2962715207","https://openalex.org/W2962935966","https://openalex.org/W2964058413","https://openalex.org/W2964121744","https://openalex.org/W2972460025","https://openalex.org/W2972767900","https://openalex.org/W3000358149","https://openalex.org/W3004309045","https://openalex.org/W3008003372","https://openalex.org/W3008283340","https://openalex.org/W3015199127","https://openalex.org/W3015372568","https://openalex.org/W3015788098","https://openalex.org/W3016232124","https://openalex.org/W3016257794","https://openalex.org/W3028458564","https://openalex.org/W3035268204","https://openalex.org/W3097445713","https://openalex.org/W3099330747","https://openalex.org/W3105169251","https://openalex.org/W3105928222","https://openalex.org/W3124972797","https://openalex.org/W3151596526","https://openalex.org/W3185109982","https://openalex.org/W6631190155","https://openalex.org/W6714030504","https://openalex.org/W6752148239","https://openalex.org/W6762182681","https://openalex.org/W6768815455","https://openalex.org/W6774687970","https://openalex.org/W6774995033","https://openalex.org/W6778035800","https://openalex.org/W6779752190"],"related_works":["https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W1847088711","https://openalex.org/W4225394202","https://openalex.org/W3036642985","https://openalex.org/W3032952384","https://openalex.org/W3017902212","https://openalex.org/W2964335273","https://openalex.org/W2982145560","https://openalex.org/W2077498359"],"abstract_inverted_index":{"Continuous":[0],"speech":[1,9],"separation":[2,10,28,44,61,76,106],"(CSS)":[3],"is":[4,33,119],"an":[5],"arising":[6],"task":[7,32],"in":[8,128],"aiming":[11],"at":[12],"separating":[13],"overlap-free":[14],"targets":[15],"from":[16],"a":[17],"long,":[18],"partially-overlapped":[19],"recording.":[20],"A":[21],"straightforward":[22],"extension":[23,51],"of":[24],"previously":[25],"proposed":[26,93],"sentence-level":[27],"models":[29],"to":[30,34,84,121],"this":[31,68],"segment":[35],"the":[36,56,60,74,86,91,104,108,124],"long":[37],"recording":[38],"into":[39],"fixed-length":[40],"blocks":[41],"and":[42,59,111,131],"perform":[43],"on":[45,72,90],"them":[46],"independently.":[47],"However,":[48],"such":[49],"simple":[50],"does":[52],"not":[53,64],"fully":[54],"address":[55],"cross-block":[57,87],"dependencies":[58],"performance":[62,77],"may":[63],"be":[65,79],"satisfactory.":[66],"In":[67],"paper,":[69],"we":[70,98],"focus":[71],"how":[73,100],"block-level":[75,105,126],"can":[78,102],"improved":[80],"by":[81,107],"exploring":[82],"methods":[83],"utilize":[85],"information.":[88],"Based":[89],"recently":[92],"dual-path":[94],"RNN":[95],"(DPRNN)":[96],"architecture,":[97],"investigate":[99],"DPRNN":[101,118],"help":[103],"interleaved":[109],"intra-":[110],"inter-block":[112],"modules.":[113],"Experiment":[114],"results":[115],"show":[116],"that":[117],"able":[120],"significantly":[122],"outperform":[123],"baseline":[125],"model":[127],"both":[129],"offline":[130],"block-online":[132],"configurations":[133],"under":[134],"certain":[135],"settings.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}