{"id":"https://openalex.org/W4406461495","doi":"https://doi.org/10.1109/slt61566.2024.10832217","title":"On the Effectiveness of Enrollment Speech Augmentation For Target Speaker Extraction","display_name":"On the Effectiveness of Enrollment Speech Augmentation For Target Speaker Extraction","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461495","doi":"https://doi.org/10.1109/slt61566.2024.10832217"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100367662","display_name":"Junjie Li","orcid":"https://orcid.org/0000-0002-9107-5563"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Junjie Li","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering,Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering,Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100643115","display_name":"Ke Zhang","orcid":"https://orcid.org/0000-0002-2536-6426"},"institutions":[{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Zhang","raw_affiliation_strings":["Shenzhen Research Institute of Big Data,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data,Shenzhen,China","institution_ids":["https://openalex.org/I4210099586"]}]},{"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/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["Shenzhen Research Institute of Big Data,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data,Shenzhen,China","institution_ids":["https://openalex.org/I4210099586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Shenzhen Research Institute of Big Data,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data,Shenzhen,China","institution_ids":["https://openalex.org/I4210099586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068768998","display_name":"Man\u2010Wai Mak","orcid":"https://orcid.org/0000-0001-8854-3760"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Man-Wai Mak","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering,Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering,Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004287909","display_name":"Kong Aik Lee","orcid":"https://orcid.org/0000-0001-9133-3000"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kong Aik Lee","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering,Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering,Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"325","last_page":"332"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9994000196456909,"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":0.9889000058174133,"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":0.7414212226867676},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6941611766815186},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4967826008796692},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41344085335731506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3829129636287689}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7414212226867676},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6941611766815186},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4967826008796692},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41344085335731506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3829129636287689}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.46000000834465027,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W2080219784","https://openalex.org/W2127851351","https://openalex.org/W2170864449","https://openalex.org/W2219249508","https://openalex.org/W2296073425","https://openalex.org/W2514828952","https://openalex.org/W2696967604","https://openalex.org/W2808631503","https://openalex.org/W2889373351","https://openalex.org/W2890964092","https://openalex.org/W2936774411","https://openalex.org/W2964058413","https://openalex.org/W2972541922","https://openalex.org/W2973062255","https://openalex.org/W2973190269","https://openalex.org/W3015199127","https://openalex.org/W3015636705","https://openalex.org/W3016361963","https://openalex.org/W3024869864","https://openalex.org/W3027008958","https://openalex.org/W3049278490","https://openalex.org/W3097653961","https://openalex.org/W3103434036","https://openalex.org/W3142849873","https://openalex.org/W3151851237","https://openalex.org/W4200634403","https://openalex.org/W4226021932","https://openalex.org/W4246307810","https://openalex.org/W4288091954","https://openalex.org/W4367597591","https://openalex.org/W4372262790","https://openalex.org/W4372267288","https://openalex.org/W4372271325","https://openalex.org/W4372340947","https://openalex.org/W4372341334","https://openalex.org/W4375928773","https://openalex.org/W4379058083","https://openalex.org/W4381327724","https://openalex.org/W4385822305","https://openalex.org/W4385822391","https://openalex.org/W4385822829","https://openalex.org/W4385823401","https://openalex.org/W4392902644","https://openalex.org/W4392902910","https://openalex.org/W4392903066","https://openalex.org/W4392903247","https://openalex.org/W4392909318","https://openalex.org/W4395471087","https://openalex.org/W4402112342","https://openalex.org/W6688816777","https://openalex.org/W6769178842","https://openalex.org/W6777776875"],"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":{"Deep":[0],"learning":[1],"technologies":[2],"have":[3],"significantly":[4],"advanced":[5],"the":[6,16,47,51,68,101],"performance":[7,74],"of":[8,20,49,114],"target":[9],"speaker":[10,64],"extraction":[11],"(TSE)":[12],"tasks.":[13],"To":[14],"enhance":[15],"generalization":[17],"and":[18,61,84],"robustness":[19],"these":[21],"algorithms":[22],"when":[23],"training":[24],"data":[25,28,37],"is":[26,30],"insufficient,":[27],"augmentation":[29,38,91,96],"a":[31,89],"commonly":[32],"adopted":[33],"technique.":[34],"Unlike":[35],"typical":[36],"applied":[39],"to":[40,72,78,116],"speech":[41,53,70,95],"mixtures,":[42],"this":[43],"work":[44],"thoroughly":[45],"investigates":[46],"effectiveness":[48],"augmenting":[50,67],"enrollment":[52,69],"space.":[54],"We":[55],"found":[56],"that":[57,106],"for":[58],"both":[59],"pretrained":[60],"jointly":[62],"optimized":[63],"encoders,":[65],"directly":[66],"leads":[71],"consistent":[73],"improvement.":[75],"In":[76],"addition":[77],"conventional":[79],"methods":[80],"such":[81],"as":[82],"noise":[83],"reverberation":[85],"addition,":[86],"we":[87],"propose":[88],"novel":[90],"method":[92,109],"called":[93],"self-estimated":[94],"(SSA).":[97],"Experimental":[98],"results":[99],"on":[100],"Libri2Mix":[102],"test":[103],"set":[104],"show":[105],"our":[107],"proposed":[108],"can":[110],"achieve":[111],"an":[112],"improvement":[113],"up":[115],"2.5":[117],"dB.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}