{"id":"https://openalex.org/W4402159790","doi":"https://doi.org/10.1109/taslp.2024.3446242","title":"Speech Separation With Pretrained Frontend to Minimize Domain Mismatch","display_name":"Speech Separation With Pretrained Frontend to Minimize Domain Mismatch","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402159790","doi":"https://doi.org/10.1109/taslp.2024.3446242"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3446242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3446242","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.03085","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006131727","display_name":"Wupeng Wang","orcid":"https://orcid.org/0009-0000-5360-2054"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Wupeng Wang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060530570","display_name":"Zexu Pan","orcid":"https://orcid.org/0000-0002-8106-1176"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zexu Pan","raw_affiliation_strings":["Alibaba Group, Singapore"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077099558","display_name":"Xinke Li","orcid":"https://orcid.org/0009-0003-9780-4952"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xinke Li","raw_affiliation_strings":["Industrial Systems Engineering and Management, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Industrial Systems Engineering and Management, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328340","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0003-1523-9631"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["Shenzhen Research Institute of Big Data, Chinese University of Hong Kong, Shenzhen, Guangdong, China","Computer En-gineering, National University of Singapore, 119077 Singapore","Shenzhen Research Institute of Big Data, Chinese University of Hong Kong, Shenzhen, Guangdong, 518172 P.R. China","Industrial Systems Engineering and Man-agement, National University of Singapore, 119077 Singapore"],"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, Chinese University of Hong Kong, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]},{"raw_affiliation_string":"Computer En-gineering, National University of Singapore, 119077 Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, Chinese University of Hong Kong, Shenzhen, Guangdong, 518172 P.R. China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]},{"raw_affiliation_string":"Industrial Systems Engineering and Man-agement, National University of Singapore, 119077 Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Shenzhen Research Institute of Big Data, Chinese University of Hong Kong, Shenzhen, Guangdong, China","Shenzhen Research Institute of Big Data, Chinese University of Hong Kong, Shenzhen, Guangdong, 518172 P.R. China","Computer En-gineering, National University of Singapore, 119077 Singapore"],"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, Chinese University of Hong Kong, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]},{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, Chinese University of Hong Kong, Shenzhen, Guangdong, 518172 P.R. China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]},{"raw_affiliation_string":"Computer En-gineering, National University of Singapore, 119077 Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5006131727"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":2.7118,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.91200466,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"4184","last_page":"4198"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9966999888420105,"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/separation","display_name":"Separation (statistics)","score":0.6202894449234009},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5735850930213928},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5645758509635925},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5552131533622742},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12122619152069092},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.07723695039749146}],"concepts":[{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6202894449234009},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5735850930213928},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5645758509635925},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5552131533622742},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12122619152069092},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07723695039749146},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2024.3446242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3446242","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2411.03085","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.03085","pdf_url":"https://arxiv.org/pdf/2411.03085","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.03085","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.03085","pdf_url":"https://arxiv.org/pdf/2411.03085","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2799040894","display_name":null,"funder_award_id":"62271432","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2981938667","display_name":null,"funder_award_id":"Shenzhen","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3085993365","display_name":null,"funder_award_id":"(Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3757194791","display_name":null,"funder_award_id":"JCYJ20","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402159790.pdf","grobid_xml":"https://content.openalex.org/works/W4402159790.grobid-xml"},"referenced_works_count":101,"referenced_works":["https://openalex.org/W418741597","https://openalex.org/W1485161427","https://openalex.org/W1494198834","https://openalex.org/W1591575995","https://openalex.org/W1946152311","https://openalex.org/W1964538581","https://openalex.org/W2013603898","https://openalex.org/W2036245667","https://openalex.org/W2046466396","https://openalex.org/W2088368716","https://openalex.org/W2104969945","https://openalex.org/W2119885245","https://openalex.org/W2123157731","https://openalex.org/W2125336414","https://openalex.org/W2131953535","https://openalex.org/W2150415460","https://openalex.org/W2171590421","https://openalex.org/W2221409856","https://openalex.org/W2259472270","https://openalex.org/W2270070752","https://openalex.org/W2405589348","https://openalex.org/W2554757134","https://openalex.org/W2593768305","https://openalex.org/W2726515241","https://openalex.org/W2734774145","https://openalex.org/W2808631503","https://openalex.org/W2890952074","https://openalex.org/W2896457183","https://openalex.org/W2899663614","https://openalex.org/W2952218014","https://openalex.org/W2972460025","https://openalex.org/W2973049979","https://openalex.org/W2973054998","https://openalex.org/W2982223350","https://openalex.org/W3007376164","https://openalex.org/W3011500442","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3015265920","https://openalex.org/W3016011332","https://openalex.org/W3027008958","https://openalex.org/W3034640977","https://openalex.org/W3035524453","https://openalex.org/W3041561163","https://openalex.org/W3043140951","https://openalex.org/W3096090308","https://openalex.org/W3097286738","https://openalex.org/W3097906045","https://openalex.org/W3099330747","https://openalex.org/W3106605409","https://openalex.org/W3124666641","https://openalex.org/W3148040514","https://openalex.org/W3161480375","https://openalex.org/W3163573274","https://openalex.org/W3163652268","https://openalex.org/W3174632922","https://openalex.org/W3190394743","https://openalex.org/W3197103473","https://openalex.org/W3198771897","https://openalex.org/W3205293880","https://openalex.org/W3205533980","https://openalex.org/W3206116612","https://openalex.org/W3206252155","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4205654098","https://openalex.org/W4225304461","https://openalex.org/W4226380987","https://openalex.org/W4233392025","https://openalex.org/W4285231507","https://openalex.org/W4285250921","https://openalex.org/W4285821318","https://openalex.org/W4292969786","https://openalex.org/W4297808394","https://openalex.org/W4310638450","https://openalex.org/W4312540993","https://openalex.org/W4317581828","https://openalex.org/W4372260140","https://openalex.org/W4372342491","https://openalex.org/W4375869164","https://openalex.org/W4375869189","https://openalex.org/W4375869385","https://openalex.org/W4375869413","https://openalex.org/W4389474152","https://openalex.org/W4391021811","https://openalex.org/W4393863141","https://openalex.org/W6639480849","https://openalex.org/W6678040779","https://openalex.org/W6682948231","https://openalex.org/W6688325169","https://openalex.org/W6692563993","https://openalex.org/W6755977528","https://openalex.org/W6777776875","https://openalex.org/W6779997284","https://openalex.org/W6780218876","https://openalex.org/W6780226713","https://openalex.org/W6784499681","https://openalex.org/W6789284391","https://openalex.org/W6810007534","https://openalex.org/W6844194202","https://openalex.org/W6844662008"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2071676784","https://openalex.org/W2376932109","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Speech":[0],"separation":[1,14,49,125,144,167,176,182,202,220],"seeks":[2],"to":[3,22,68,99,154,169,212],"separate":[4],"individual":[5],"speech":[6,10,48,124,143,181,201,219],"signals":[7],"from":[8,147,159],"a":[9,34,38,59,82,117,165],"mixture.":[11],"Typically,":[12],"most":[13],"models":[15,50,126],"are":[16],"trained":[17],"on":[18,127,184],"synthetic":[19,44,107,128,148],"data":[20,45,70,149],"due":[21],"the":[23,72,113,122,132,136,142,160,171,175,180,193,207,214],"unavailability":[24],"of":[25,174,195,209,218],"target":[26,75],"reference":[27,76],"in":[28,51,221],"real-world":[29,52,188,222],"cocktail":[30],"party":[31],"scenarios.":[32],"As":[33],"result,":[35],"there":[36],"exists":[37],"domain":[39],"gap":[40],"between":[41,104],"real":[42,105,155],"and":[43,94,106,187,216],"when":[46,120],"deploying":[47],"applications.":[53,223],"In":[54],"this":[55],"paper,":[56],"we":[57,111,139,163],"propose":[58],"self-supervised":[60],"domain-invariant":[61],"pretrained":[62],"(DIP)":[63],"frontend":[64,80,115,134,198],"that":[65,141],"is":[66],"exposed":[67],"mixture":[69,90,95],"without":[71],"need":[73],"for":[74],"speech.":[77],"The":[78,190],"DIP":[79,114,133,161,197],"utilizes":[81],"Siamese":[83],"network":[84],"with":[85,135],"two":[86],"innovative":[87],"pretext":[88],"tasks,":[89],"predictive":[91],"coding":[92,97],"(MPC)":[93],"invariant":[96],"(MIC),":[98],"capture":[100],"shared":[101],"contextual":[102,137],"cues":[103],"unlabeled":[108],"mixtures.":[109],"Subsequently,":[110],"freeze":[112],"as":[116],"feature":[118,172],"extractor":[119],"training":[121],"downstream":[123],"data.":[129,156],"By":[130],"pretraining":[131,211],"cues,":[138],"expect":[140],"skills":[145],"learned":[146],"can":[150],"be":[151],"effectively":[152],"transferred":[153],"To":[157],"benefit":[158],"frontend,":[162],"introduce":[164],"novel":[166],"pipeline":[168],"align":[170],"resolution":[173],"models.":[177,203],"We":[178],"evaluate":[179],"quality":[183,215],"standard":[185],"benchmarks":[186],"datasets.":[189],"results":[191],"confirm":[192],"superiority":[194],"our":[196],"over":[199],"existing":[200],"This":[204],"study":[205],"underscores":[206],"potential":[208],"large-scale":[210],"enhance":[213],"intelligibility":[217]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}