{"id":"https://openalex.org/W4319586675","doi":"https://doi.org/10.1109/iscslp57327.2022.10038203","title":"Improving Speech Separation with Knowledge Distilled from Self-supervised Pre-trained Models","display_name":"Improving Speech Separation with Knowledge Distilled from Self-supervised Pre-trained Models","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319586675","doi":"https://doi.org/10.1109/iscslp57327.2022.10038203"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10038203","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscslp57327.2022.10038203","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"2022 13th 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/A5084511663","display_name":"Bowen Qu","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":"Bowen Qu","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/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":false,"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/A5050743863","display_name":"Jinfeng Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210151703","display_name":"China Coal Technology and Engineering Group Corp (China)","ror":"https://ror.org/045d9gj14","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210151703"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinfeng Bai","raw_affiliation_strings":["TAL Education Group,China","TAL Education Group, China"],"affiliations":[{"raw_affiliation_string":"TAL Education Group,China","institution_ids":["https://openalex.org/I4210151703"]},{"raw_affiliation_string":"TAL Education Group, China","institution_ids":[]}]},{"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/A5084511663"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18041074,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"329","last_page":"333"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7911847829818726},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5976393222808838},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5822073221206665},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5642968416213989},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.550500214099884},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.518441915512085},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.484123557806015},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4127333462238312},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3951966464519501},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3563646674156189},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.060837358236312866}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7911847829818726},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5976393222808838},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5822073221206665},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5642968416213989},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.550500214099884},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.518441915512085},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.484123557806015},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4127333462238312},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3951966464519501},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3563646674156189},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.060837358236312866},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp57327.2022.10038203","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscslp57327.2022.10038203","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W1946152311","https://openalex.org/W1977812963","https://openalex.org/W1979099822","https://openalex.org/W1991139021","https://openalex.org/W2047527596","https://openalex.org/W2135823751","https://openalex.org/W2296073425","https://openalex.org/W2460742184","https://openalex.org/W2510642588","https://openalex.org/W2734774145","https://openalex.org/W2792764867","https://openalex.org/W2794289187","https://openalex.org/W2896457183","https://openalex.org/W2922709902","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2970597249","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W3027008958","https://openalex.org/W3036601975","https://openalex.org/W3099330747","https://openalex.org/W3161223924","https://openalex.org/W3163842642","https://openalex.org/W3198275944","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221145109","https://openalex.org/W4224933800","https://openalex.org/W4297808394","https://openalex.org/W4385245566","https://openalex.org/W6755207826","https://openalex.org/W6780218876","https://openalex.org/W6795346631"],"related_works":["https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2131711534","https://openalex.org/W2289873871","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Large-scale":[0],"self-supervised":[1],"learning":[2],"(SSL)":[3],"models":[4,18,41,53,73],"have":[5],"shown":[6],"outstanding":[7],"ability":[8],"in":[9,19,50,74],"many":[10,47],"speech":[11,43,60,76,99,124],"processing":[12],"tasks.":[13,45],"Most":[14],"of":[15,58,70,80,122],"the":[16,20,27,55,59,68,75,82,98,108,112,120,132],"SSL":[17,40,52,72,83,89,102,133],"literature":[21],"are":[22],"trained":[23,106],"with":[24,107],"datasets":[25],"where":[26],"single-talker":[28],"utterances":[29],"dominate.":[30],"It":[31],"may":[32],"not":[33],"be":[34,127],"optimal":[35],"to":[36,42,92],"directly":[37],"apply":[38],"these":[39],"separation":[44,61,77,125],"Besides,":[46],"computational":[48],"costs":[49],"large-scale":[51],"increase":[54],"overall":[56],"complexity":[57],"system.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66,86],"explore":[67],"application":[69],"pre-trained":[71,113],"task.":[78],"Instead":[79],"using":[81],"model":[84],"directly,":[85],"designed":[87],"an":[88],"feature":[90,103],"predictor":[91,104],"estimate":[93],"single-talker\u2019s":[94],"deep":[95],"features":[96],"from":[97,111],"mixture.":[100],"The":[101],"is":[105],"knowledge":[109],"distilled":[110],"Wav2Vec2.0":[114],"model.":[115],"Our":[116],"experiments":[117],"show":[118],"that":[119],"performance":[121],"time-domain":[123],"can":[126],"improved":[128],"obviously":[129],"by":[130],"leveraging":[131],"embedding":[134],"predictor.":[135]},"counts_by_year":[],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}
