{"id":"https://openalex.org/W3016048045","doi":"https://doi.org/10.1109/icassp40776.2020.9053068","title":"An Online Speaker-aware Speech Separation Approach Based on Time-domain Representation","display_name":"An Online Speaker-aware Speech Separation Approach Based on Time-domain Representation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016048045","doi":"https://doi.org/10.1109/icassp40776.2020.9053068","mag":"3016048045"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053068","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/An_Online_Speaker-aware_Speech_Separation_Approach_Based_on_Time-domain_Representation/24217434","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100460841","display_name":"Hui Wang","orcid":"https://orcid.org/0000-0002-8476-888X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hui Wang","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381758","display_name":"Yan Song","orcid":"https://orcid.org/0000-0002-5668-9068"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Song","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101587843","display_name":"Zeng-Xi Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeng-Xi Li","raw_affiliation_strings":["Microsoft China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft China, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000620878","display_name":"Ian McLoughlin","orcid":"https://orcid.org/0000-0001-7111-2008"},"institutions":[{"id":"https://openalex.org/I167056439","display_name":"Medway School of Pharmacy","ror":"https://ror.org/00fa9v295","country_code":"GB","type":"education","lineage":["https://openalex.org/I167056439"]},{"id":"https://openalex.org/I20581793","display_name":"University of Kent","ror":"https://ror.org/00xkeyj56","country_code":"GB","type":"education","lineage":["https://openalex.org/I20581793"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ian McLoughlin","raw_affiliation_strings":["School of Computing, University of Kent, Medway, UK"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Kent, Medway, UK","institution_ids":["https://openalex.org/I167056439","https://openalex.org/I20581793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100460841"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.4571,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.5973958,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"6379","last_page":"6383"},"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8376225233078003},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7380031943321228},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.711044430732727},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5872597098350525},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5751506686210632},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5385332107543945},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5335099697113037},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4637637138366699},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4607115685939789},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44693008065223694},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.445425420999527},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4248260259628296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8376225233078003},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7380031943321228},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.711044430732727},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5872597098350525},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5751506686210632},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5385332107543945},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5335099697113037},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4637637138366699},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4607115685939789},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44693008065223694},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.445425420999527},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4248260259628296},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053068","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:figshare.com:article/24217434","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/An_Online_Speaker-aware_Speech_Separation_Approach_Based_on_Time-domain_Representation/24217434","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/24217434","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/An_Online_Speaker-aware_Speech_Separation_Approach_Based_on_Time-domain_Representation/24217434","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"score":0.699999988079071,"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":26,"referenced_works":["https://openalex.org/W185399533","https://openalex.org/W1677182931","https://openalex.org/W2044222806","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2561557072","https://openalex.org/W2567070169","https://openalex.org/W2734774145","https://openalex.org/W2799930831","https://openalex.org/W2801839390","https://openalex.org/W2889540509","https://openalex.org/W2910254446","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962935966","https://openalex.org/W2963970792","https://openalex.org/W2972460025","https://openalex.org/W2972853597","https://openalex.org/W2973062255","https://openalex.org/W3099330747","https://openalex.org/W6607486085","https://openalex.org/W6678799340","https://openalex.org/W6731370813","https://openalex.org/W6751646133","https://openalex.org/W7065181925"],"related_works":["https://openalex.org/W4384929466","https://openalex.org/W2206035908","https://openalex.org/W3148366653","https://openalex.org/W2149220986","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021"],"abstract_inverted_index":{"Despite":[0],"the":[1,18,31,40,62,69,97,116,121],"significant":[2],"progress":[3],"of":[4,99],"deep":[5],"learning":[6],"based":[7,60],"speech":[8,19,50,82],"separation":[9,83],"methods,":[10],"it":[11],"remains":[12],"challenging":[13],"to":[14,38,109],"extract":[15],"and":[16,45,84],"track":[17],"from":[20],"target":[21],"speakers,":[22],"especially":[23],"in":[24,43,67],"a":[25,34,57,104],"single-channel":[26],"multiple":[27],"speaker":[28,70,78,85],"situation.":[29],"Previously,":[30],"authors":[32],"proposed":[33,122],"source-aware":[35,63],"context":[36,42,64],"network":[37,65],"exploit":[39],"temporal":[41],"mixtures":[44],"estimated":[46],"sources":[47],"for":[48],"online":[49],"separation.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55,95],"propose":[56],"speaker-aware":[58],"approach":[59],"on":[61,115],"structure,":[66],"which":[68],"information":[71],"is":[72],"explicitly":[73],"modeled":[74],"by":[75,91,102],"an":[76],"auxiliary":[77],"identification":[79],"branch.":[80],"Then":[81],"tracking":[86],"can":[87],"be":[88],"jointly":[89],"optimized":[90],"multi-task":[92],"learning.":[93],"Furthermore,":[94],"study":[96],"effectiveness":[98],"time-domain":[100],"representation":[101],"proposing":[103],"raw":[105],"sparse":[106],"waveform":[107],"encoder":[108],"preserve":[110],"discriminative":[111],"information.":[112],"Experimental":[113],"results":[114],"WSJ0-2mix":[117],"benchmark":[118],"show":[119],"that":[120],"system":[123],"significantly":[124],"improves":[125],"Signal-to-Distortion":[126],"Ratio":[127],"(SDR)":[128],"performance.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}