{"id":"https://openalex.org/W4410737562","doi":"https://doi.org/10.1109/lsp.2025.3573951","title":"Enhancing Intelligibility for Generative Target Speech Extraction via Joint Optimization With Target Speaker ASR","display_name":"Enhancing Intelligibility for Generative Target Speech Extraction via Joint Optimization With Target Speaker ASR","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4410737562","doi":"https://doi.org/10.1109/lsp.2025.3573951"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3573951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3573951","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-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/A5101108881","display_name":"Hao Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Ma","raw_affiliation_strings":["School of Information Science and Engineering, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0009-0001-2651-8524","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rujin Chen","orcid":"https://orcid.org/0009-0008-1606-7265"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rujin Chen","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China","Institute of Artificial Intelligence (TeleAI), China Telecom., China"],"raw_orcid":"https://orcid.org/0009-0008-1606-7265","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]},{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom., China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450091","display_name":"Xiao-Lei Zhang","orcid":"https://orcid.org/0000-0001-7694-193X"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Lei Zhang","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China","Institute of Artificial Intelligence (TeleAI), China Telecom., China"],"raw_orcid":"https://orcid.org/0000-0001-7694-193X","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]},{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom., China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100763011","display_name":"Ju Liu","orcid":"https://orcid.org/0000-0003-3160-9233"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ju Liu","raw_affiliation_strings":["School of Information Science and Engineering, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-3160-9233","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106943753","display_name":"Xuelong Li","orcid":"https://orcid.org/0000-0003-2924-946X"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuelong Li","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China","Institute of Artificial Intelligence (TeleAI), China Telecom., China"],"raw_orcid":"https://orcid.org/0000-0003-2924-946X","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]},{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom., China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.188,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93726518,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"32","issue":null,"first_page":"2309","last_page":"2313"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9950000047683716,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9950000047683716,"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/T10860","display_name":"Speech and Audio Processing","score":0.9611999988555908,"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/speech-recognition","display_name":"Speech recognition","score":0.7611645460128784},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7129985690116882},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6500271558761597},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5795881748199463},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5483806133270264},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4614850878715515},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4547244608402252},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42569243907928467},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4148194491863251},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32855573296546936},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09852129220962524}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7611645460128784},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7129985690116882},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6500271558761597},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5795881748199463},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5483806133270264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4614850878715515},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4547244608402252},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42569243907928467},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4148194491863251},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32855573296546936},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09852129220962524},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3573951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3573951","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2221409856","https://openalex.org/W2800022361","https://openalex.org/W2951130829","https://openalex.org/W2962866211","https://openalex.org/W3015636705","https://openalex.org/W3016361963","https://openalex.org/W4225302959","https://openalex.org/W4372263659","https://openalex.org/W4372271325","https://openalex.org/W4372342485","https://openalex.org/W4385245566","https://openalex.org/W4385822449","https://openalex.org/W4385823321","https://openalex.org/W4392903379","https://openalex.org/W4392903977","https://openalex.org/W4392904451","https://openalex.org/W4392904673","https://openalex.org/W4392909571","https://openalex.org/W4392931276","https://openalex.org/W4402111636","https://openalex.org/W4402116591","https://openalex.org/W4405179268","https://openalex.org/W4408352717","https://openalex.org/W4409348214","https://openalex.org/W4409363098","https://openalex.org/W6757817989","https://openalex.org/W6777776875","https://openalex.org/W6783867762","https://openalex.org/W6796581206","https://openalex.org/W6846539466","https://openalex.org/W6847363464","https://openalex.org/W6870225445","https://openalex.org/W6872989720"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W4406496871","https://openalex.org/W1521049138","https://openalex.org/W2023466863"],"abstract_inverted_index":{"Target":[0],"speech":[1,6,15,56,74,149],"extraction":[2],"(TSE)":[3],"isolates":[4],"the":[5,32,59,85,90,106,112,138],"of":[7,44,81],"a":[8,12,27,100],"specific":[9],"speaker":[10,63,96],"from":[11,133],"multi-talker":[13],"overlapped":[14],"mixture.":[16],"Most":[17],"existing":[18,142],"TSE":[19,102],"models":[20],"rely":[21],"on":[22,58,105,151],"discriminative":[23,145],"methods,":[24,51],"typically":[25],"predicting":[26],"time-frequency":[28],"spectrogram":[29],"mask":[30],"for":[31],"target":[33,55,62,95],"speech.":[34,87],"However,":[35],"imperfections":[36],"in":[37,42,84,94],"these":[38,70],"masks":[39],"often":[40,72],"result":[41],"over-/under-suppression":[43],"target/non-target":[45],"speech,":[46],"degrading":[47],"perceptual":[48,67,130],"quality.":[49,68,131],"Generative":[50],"by":[52,89],"contrast,":[53],"re-synthesize":[54],"based":[57,104],"mixture":[60],"and":[61,129,144],"cues,":[64],"achieving":[65],"superior":[66],"Nevertheless,":[69],"methods":[71],"overlook":[73],"intelligibility,":[75],"leading":[76],"to":[77,110,124],"alterations":[78],"or":[79],"loss":[80],"semantic":[82,118],"content":[83],"re-synthesized":[86],"Inspired":[88],"Whisper":[91,108],"model's":[92],"success":[93],"ASR,":[97],"we":[98],"propose":[99],"generative":[101,143],"framework":[103,116],"pre-trained":[107],"model":[109],"address":[111],"above":[113],"issues.":[114],"This":[115],"integrates":[117],"modeling":[119,123],"with":[120],"flow-based":[121],"acoustic":[122],"achieve":[125],"both":[126],"high":[127],"intelligibility":[128],"Results":[132],"multiple":[134],"benchmarks":[135],"demonstrate":[136],"that":[137],"proposed":[139],"method":[140],"outperforms":[141],"baselines.":[146],"We":[147],"present":[148],"samples":[150],"<uri":[152],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[153],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://aisaka0v0.github.io/GenerativeTSE_demo/</uri>.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}