{"id":"https://openalex.org/W4224938485","doi":"https://doi.org/10.1109/icassp43922.2022.9746372","title":"Skim: Skipping Memory Lstm for Low-Latency Real-Time Continuous Speech Separation","display_name":"Skim: Skipping Memory Lstm for Low-Latency Real-Time Continuous Speech Separation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224938485","doi":"https://doi.org/10.1109/icassp43922.2022.9746372"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746372","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5013809674","display_name":"Chenda Li","orcid":null},"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,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037587077","display_name":"Lei Yang","orcid":"https://orcid.org/0000-0001-8393-7189"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Yang","raw_affiliation_strings":["Samsung Research China - Beijing (SRC-B)"],"affiliations":[{"raw_affiliation_string":"Samsung Research China - Beijing (SRC-B)","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103162335","display_name":"Weiqin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiqin Wang","raw_affiliation_strings":["Samsung Research China - Beijing (SRC-B)"],"affiliations":[{"raw_affiliation_string":"Samsung Research China - Beijing (SRC-B)","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"last","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,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5013809674"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":2.4297,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.91501416,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"681","last_page":"685"},"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":0.9994000196456909,"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":0.9977999925613403,"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":0.7576467990875244},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6511934995651245},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5722851157188416},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.4482816755771637},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.438377320766449},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.41350215673446655},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0936066210269928}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7576467990875244},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6511934995651245},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5722851157188416},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.4482816755771637},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.438377320766449},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.41350215673446655},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0936066210269928},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746372","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2064675550","https://openalex.org/W2067295501","https://openalex.org/W2221409856","https://openalex.org/W2302255633","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2891833136","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962905190","https://openalex.org/W2962935966","https://openalex.org/W2972460025","https://openalex.org/W2973062255","https://openalex.org/W2996969697","https://openalex.org/W3008283340","https://openalex.org/W3015199127","https://openalex.org/W3016232124","https://openalex.org/W3036069164","https://openalex.org/W3099330747","https://openalex.org/W3124972797","https://openalex.org/W3133834828","https://openalex.org/W3151851237","https://openalex.org/W3161201807","https://openalex.org/W3163652268","https://openalex.org/W3163842642","https://openalex.org/W3187990717","https://openalex.org/W3193846000","https://openalex.org/W3195010976","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6698183232","https://openalex.org/W6739901393","https://openalex.org/W6779963951"],"related_works":["https://openalex.org/W4307784074","https://openalex.org/W3205411230","https://openalex.org/W4286899009","https://openalex.org/W9168048","https://openalex.org/W4300849822","https://openalex.org/W4376480820","https://openalex.org/W3155891479","https://openalex.org/W3029351463","https://openalex.org/W2885352820","https://openalex.org/W4296591952"],"abstract_inverted_index":{"Continuous":[0],"speech":[1,19,37,51],"separation":[2,38,52,104],"for":[3,58,88,136],"meeting":[4],"pre-processing":[5],"has":[6,27],"recently":[7,42],"become":[8],"a":[9,47,67,79,133],"focused":[10],"research":[11],"topic.":[12],"Compared":[13],"to":[14,45,71,119],"the":[15,21,35,41,59,89,109,156],"data":[16],"in":[17,155],"utterance-level":[18],"separation,":[20],"meeting-style":[22,158],"audio":[23],"stream":[24],"lasts":[25],"longer,":[26],"an":[28,72],"uncertain":[29],"number":[30],"of":[31,112],"speakers.":[32],"We":[33,77],"adopt":[34],"time-domain":[36,64],"method":[39],"and":[40,127],"proposed":[43,78],"Graph-PIT":[44],"build":[46],"super":[48],"low-latency":[49,63],"online":[50,137],"model,":[53],"which":[54],"is":[55,114],"very":[56],"important":[57],"real":[60],"application.":[61],"The":[62,121],"encoder":[65],"with":[66,150],"small":[68],"stride":[69],"leads":[70],"extremely":[73],"long":[74,90,123],"feature":[75],"sequence.":[76],"simple":[80],"yet":[81],"efficient":[82],"model":[83,135,143],"named":[84],"Skipping":[85],"Memory":[86],"(SkiM)":[87],"sequence":[91,124],"modeling.":[92],"Experimental":[93],"results":[94],"show":[95],"that":[96],"SkiM":[97,113,132],"achieves":[98],"on":[99],"par":[100],"or":[101],"even":[102],"better":[103],"performance":[105],"than":[106,152],"DPRNN.":[107,120],"Meanwhile,":[108],"computational":[110,129],"cost":[111,130],"reduced":[115],"by":[116],"75%":[117],"compared":[118],"strong":[122],"modeling":[125],"capability":[126],"low":[128],"make":[131],"suitable":[134],"CSS":[138],"applications.":[139],"Our":[140],"fastest":[141],"real-time":[142],"gets":[144],"17.1":[145],"dB":[146],"signal-to-distortion":[147],"(SDR)":[148],"improvement":[149],"less":[151],"1-millisecond":[153],"latency":[154],"simulated":[157],"evaluation.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}