{"id":"https://openalex.org/W4389381080","doi":"https://doi.org/10.1186/s13636-023-00317-3","title":"Lightweight target speaker separation network based on joint training","display_name":"Lightweight target speaker separation network based on joint training","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4389381080","doi":"https://doi.org/10.1186/s13636-023-00317-3"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-023-00317-3","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1186/s13636-023-00317-3","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13636-023-00317-3.pdf","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1186/s13636-023-00317-3.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100378497","display_name":"Jing Wang","orcid":"https://orcid.org/0000-0002-3653-9951"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jing Wang","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041853771","display_name":"Hanyue Liu","orcid":"https://orcid.org/0000-0001-8357-6010"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanyue Liu","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023681675","display_name":"Liang Xu","orcid":"https://orcid.org/0000-0002-6556-7521"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Xu","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016603628","display_name":"Wenjing Yang","orcid":"https://orcid.org/0000-0002-6997-0406"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjing Yang","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075613420","display_name":"Weiming Yi","orcid":"https://orcid.org/0009-0005-5217-5966"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I890469752","display_name":"Ministry of Industry and Information Technology","ror":"https://ror.org/0385nmy68","country_code":"CN","type":"government","lineage":["https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiming Yi","raw_affiliation_strings":["Key Laboratory of Language, Cognition and Computation Ministry of Industry and Information Technology, School of Foreign Languages, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-5217-5966","affiliations":[{"raw_affiliation_string":"Key Laboratory of Language, Cognition and Computation Ministry of Industry and Information Technology, School of Foreign Languages, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I890469752","https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100453123","display_name":"Fang Liu","orcid":"https://orcid.org/0000-0003-3028-5927"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I890469752","display_name":"Ministry of Industry and Information Technology","ror":"https://ror.org/0385nmy68","country_code":"CN","type":"government","lineage":["https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Liu","raw_affiliation_strings":["Key Laboratory of Language, Cognition and Computation Ministry of Industry and Information Technology, School of Foreign Languages, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Language, Cognition and Computation Ministry of Industry and Information Technology, School of Foreign Languages, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I890469752","https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100378497"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17101108,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2023","issue":"1","first_page":null,"last_page":null},"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":0.9995999932289124,"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":0.9991000294685364,"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":0.8083068132400513},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.7834614515304565},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6886624693870544},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6336816549301147},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5829209685325623},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5495516061782837},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.46630537509918213},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4347565770149231},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39038732647895813},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24431246519088745},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09839901328086853},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09494301676750183}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8083068132400513},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.7834614515304565},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6886624693870544},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6336816549301147},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5829209685325623},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5495516061782837},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.46630537509918213},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4347565770149231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39038732647895813},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24431246519088745},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09839901328086853},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09494301676750183},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-023-00317-3","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1186/s13636-023-00317-3","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13636-023-00317-3.pdf","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:4369696e6e854b868e5fda19c154156c","is_oa":true,"landing_page_url":"https://doaj.org/article/4369696e6e854b868e5fda19c154156c","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2023, Iss 1, Pp 1-10 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-023-00317-3","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1186/s13636-023-00317-3","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13636-023-00317-3.pdf","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4952363744","display_name":null,"funder_award_id":"No.62071039","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6471985988","display_name":"\u57fa\u4e8e\u5f20\u91cf\u6df1\u5ea6\u5b66\u4e60\u548c\u6ce8\u610f\u529b\u673a\u5236\u7684\u65e0\u53c2\u8003\u58f0\u97f3\u8d28\u91cf\u8bc4\u4ef7\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62071039","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389381080.pdf","grobid_xml":"https://content.openalex.org/works/W4389381080.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W185399533","https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1790748249","https://openalex.org/W1964940342","https://openalex.org/W1975163393","https://openalex.org/W1989337816","https://openalex.org/W1991139021","https://openalex.org/W2030534537","https://openalex.org/W2046056978","https://openalex.org/W2067295501","https://openalex.org/W2154278880","https://openalex.org/W2550143307","https://openalex.org/W2678916739","https://openalex.org/W2726515241","https://openalex.org/W2747898905","https://openalex.org/W2749510669","https://openalex.org/W2752782242","https://openalex.org/W2784163702","https://openalex.org/W2787692317","https://openalex.org/W2808631503","https://openalex.org/W2952218014","https://openalex.org/W2962788625","https://openalex.org/W2962866211","https://openalex.org/W2962898354","https://openalex.org/W2962935966","https://openalex.org/W2964238697","https://openalex.org/W2973062255","https://openalex.org/W3013020904","https://openalex.org/W3015199127","https://openalex.org/W3015598461","https://openalex.org/W3016361963","https://openalex.org/W3099330747","https://openalex.org/W3103152812","https://openalex.org/W3103434036","https://openalex.org/W3124794156","https://openalex.org/W3173905592","https://openalex.org/W4241874243","https://openalex.org/W4317616184","https://openalex.org/W4319780101","https://openalex.org/W6600710366","https://openalex.org/W6603625323","https://openalex.org/W6605299328","https://openalex.org/W6828894009"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"Abstract":[0],"Target":[1],"speaker":[2,13,84,113,132,140,143,167,186],"separation":[3,30,85,106,114,133,144,168,187,198],"aims":[4],"to":[5,56,76,122,153],"separate":[6],"the":[7,11,57,70,78,97,105,124,130,151,156,164,184,197,201],"speech":[8,16,29],"components":[9,20],"of":[10,129,150,183,200],"target":[12,83,112,131,166,185],"from":[14],"mixed":[15],"and":[17,36,51,73,100,127,142,180],"remove":[18],"extraneous":[19],"such":[21],"as":[22],"noise.":[23],"In":[24],"recent":[25],"years,":[26],"deep":[27],"learning-based":[28],"methods":[31,44,75],"have":[32,37],"made":[33],"significant":[34],"breakthroughs":[35],"gradually":[38],"become":[39],"mainstream.":[40],"However,":[41],"these":[42,63],"existing":[43],"generally":[45],"face":[46],"problems":[47],"with":[48,189],"system":[49],"latency":[50],"performance":[52,176,199],"upper":[53],"limits":[54],"due":[55],"large":[58],"model":[59,98],"size.":[60],"To":[61],"solve":[62],"problems,":[64],"this":[65,172],"paper":[66,173],"proposes":[67],"improvements":[68],"in":[69,171],"network":[71,86,152,169,188],"structure":[72],"training":[74,119,126,149,182],"enhance":[77],"model\u2019s":[79],"performance.":[80,107,158],"A":[81],"lightweight":[82,165],"based":[87,116,138],"on":[88,109,117,139],"long-short-term":[89],"memory":[90],"(LSTM)":[91],"is":[92,120],"proposed,":[93],"which":[94],"can":[95,194],"reduce":[96],"size":[99],"computational":[101],"delay":[102],"while":[103,177],"maintaining":[104],"Based":[108],"this,":[110],"a":[111],"method":[115],"joint":[118,148,181],"proposed":[121,146,170,191],"achieve":[123],"overall":[125],"optimization":[128],"system.":[134],"Joint":[135],"loss":[136,192],"functions":[137],"registration":[141],"are":[145],"for":[147],"further":[154,195],"improve":[155,196],"system\u2019s":[157],"The":[159],"experimental":[160],"results":[161],"show":[162],"that":[163],"has":[174],"better":[175],"being":[178],"lightweight,":[179],"our":[190],"function":[193],"original":[202],"model.":[203]},"counts_by_year":[],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2025-10-10T00:00:00"}
