{"id":"https://openalex.org/W4408352533","doi":"https://doi.org/10.1109/icassp49660.2025.10889137","title":"Augmenting Short Enrollment Speech via Synthesis for Target Speaker Extraction","display_name":"Augmenting Short Enrollment Speech via Synthesis for Target Speaker Extraction","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352533","doi":"https://doi.org/10.1109/icassp49660.2025.10889137"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889137","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":null,"display_name":"Zikang Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zikang Huang","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004441972","display_name":"Jingru Lin","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"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jingru Lin","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer and Engineering"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer and Engineering","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071074013","display_name":"Meng Ge","orcid":"https://orcid.org/0000-0003-2017-4529"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Ge","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086017661","display_name":"Yu Jiang","orcid":"https://orcid.org/0000-0002-0728-5673"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Jiang","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103015888","display_name":"Xiaobao Wang","orcid":"https://orcid.org/0000-0001-5086-4964"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobao Wang","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101745212","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-6970-4765"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017251198","display_name":"Jianwu Dang","orcid":"https://orcid.org/0000-0002-9237-4821"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwu Dang","raw_affiliation_strings":["Chinese Academy of Sciences,Shenzhen Institute of Advanced Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shenzhen Institute of Advanced Technology,Shenzhen,China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":4.3637,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93371589,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9937000274658203,"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":0.9937000274658203,"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":0.9549999833106995,"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":0.7044024467468262},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7005596160888672},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5954302549362183},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.44640350341796875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7044024467468262},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7005596160888672},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5954302549362183},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.44640350341796875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889137","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2143169494","https://openalex.org/W2962866211","https://openalex.org/W2964058413","https://openalex.org/W3015636705","https://openalex.org/W3016361963","https://openalex.org/W3162534564","https://openalex.org/W4200634403","https://openalex.org/W4225592424","https://openalex.org/W4288054834","https://openalex.org/W4321600175","https://openalex.org/W4367597591","https://openalex.org/W4372260086","https://openalex.org/W4372270801","https://openalex.org/W4385822305","https://openalex.org/W4385823321","https://openalex.org/W4387422805","https://openalex.org/W4391020683","https://openalex.org/W4391021666","https://openalex.org/W4391021721","https://openalex.org/W4392903066","https://openalex.org/W4392903389","https://openalex.org/W4392931276","https://openalex.org/W4402112053","https://openalex.org/W4408352172","https://openalex.org/W6777776875","https://openalex.org/W6847363464","https://openalex.org/W6850334629","https://openalex.org/W6851724922","https://openalex.org/W6853611000","https://openalex.org/W6853723667","https://openalex.org/W6862144568","https://openalex.org/W6870225445"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4313854686","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2368768466","https://openalex.org/W2757081366","https://openalex.org/W3197877226"],"abstract_inverted_index":{"A":[0],"high-quality":[1],"enrollment":[2,32,53,63,77,109,132],"speech":[3,64,70,78,110,133],"is":[4,134],"crucial":[5],"to":[6,59,88,100],"target":[7,19],"speaker":[8,20,81],"extraction":[9,90],"(TSE),":[10],"since":[11],"it":[12],"provides":[13,43],"essential":[14],"cues":[15],"for":[16,38],"identifying":[17],"the":[18,22,61,75,102],"in":[21,107,124],"mixture.":[23],"However,":[24],"real":[25],"applications":[26],"usually":[27],"only":[28,128],"permit":[29],"a":[30,35,39,95,121],"short":[31,108],"speech,":[33],"e.g.":[34],"wakeup":[36],"word":[37],"mobile":[40],"device,":[41],"that":[42,56,116],"limited":[44,62],"cues.":[45],"To":[46],"address":[47],"this":[48],"issue,":[49],"we":[50,93],"propose":[51,94],"an":[52],"augmentation":[54,98],"strategy":[55,99],"allows":[57],"us":[58],"enrich":[60],"with":[65],"massive":[66],"text":[67],"data":[68,97],"through":[69],"synthesis.":[71],"By":[72],"doing":[73],"so,":[74],"extended":[76],"contains":[79],"enhanced":[80],"timbre":[82],"and":[83,105,130],"phonetic":[84],"content":[85],"which":[86],"leads":[87],"better":[89],"quality.":[91],"Furthermore,":[92],"training":[96],"improve":[101],"model\u2019s":[103],"robustness":[104],"generalization":[106],"scenarios.":[111],"Experiments":[112],"on":[113],"Libri2Mix":[114],"demonstrate":[115],"our":[117,139],"proposed":[118],"strategies":[119],"bring":[120],"significant":[122],"improvement":[123],"extreme":[125],"scenarios":[126],"where":[127],"0.5s":[129],"1-word":[131],"provided.":[135],"We":[136],"also":[137],"release":[138],"code":[140],"at":[141],"https://github.com/HuangZikang-TJU/Aug4TSE.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}