{"id":"https://openalex.org/W4372260086","doi":"https://doi.org/10.1109/icassp49357.2023.10096664","title":"Target Speaker Extraction with Ultra-Short Reference Speech by VE-VE Framework","display_name":"Target Speaker Extraction with Ultra-Short Reference Speech by VE-VE Framework","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260086","doi":"https://doi.org/10.1109/icassp49357.2023.10096664"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":"https://openalex.org/A5069427874","display_name":"Lei Yang","orcid":"https://orcid.org/0000-0002-8022-2142"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lei Yang","raw_affiliation_strings":["Samsung Research China – Beijing (SRC-B)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research China – Beijing (SRC-B)","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431792","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-3865-8145"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["Samsung Research China – Beijing (SRC-B)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research China – Beijing (SRC-B)","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041351290","display_name":"Lufen Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lufen Tan","raw_affiliation_strings":["Samsung Research China – Beijing (SRC-B)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research China – Beijing (SRC-B)","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037641138","display_name":"Jaemo Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaemo Yang","raw_affiliation_strings":["Mobile Experience Business, Samsung Electronics Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobile Experience Business, Samsung Electronics Co., Ltd","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065271641","display_name":"Han-gil Moon","orcid":"https://orcid.org/0000-0002-4949-3112"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Han-Gil Moon","raw_affiliation_strings":["Mobile Experience Business, Samsung Electronics Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobile Experience Business, Samsung Electronics Co., Ltd","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5069427874"],"corresponding_institution_ids":["https://openalex.org/I4210155230"],"apc_list":null,"apc_paid":null,"fwci":3.3625,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.9365493,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.7869989275932312},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.7383915185928345},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7107657790184021},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6455470323562622},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5616999268531799},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5543661117553711},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4555346965789795},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08271268010139465}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7869989275932312},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.7383915185928345},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7107657790184021},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6455470323562622},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5616999268531799},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5543661117553711},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4555346965789795},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08271268010139465},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1991139021","https://openalex.org/W2143169494","https://openalex.org/W2787692317","https://openalex.org/W2891833136","https://openalex.org/W2939771864","https://openalex.org/W2951130829","https://openalex.org/W2964058413","https://openalex.org/W2972568703","https://openalex.org/W2973062255","https://openalex.org/W3008400075","https://openalex.org/W3015199127","https://openalex.org/W3015636705","https://openalex.org/W3016361963","https://openalex.org/W3096090308","https://openalex.org/W3097653961","https://openalex.org/W3097797867","https://openalex.org/W3103434036","https://openalex.org/W3162534564","https://openalex.org/W3198234746","https://openalex.org/W4289665794","https://openalex.org/W6631190155","https://openalex.org/W6748206876","https://openalex.org/W6755462816"],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W2640905660","https://openalex.org/W2122924390","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"The":[0,71],"goal":[1],"of":[2,18,27,100],"target":[3,11,29],"speaker":[4,30],"extraction":[5,75],"(TSE)":[6],"is":[7,132],"to":[8,23,51,96,124],"extract":[9],"the":[10,15,25,28,48,78,88,98,122],"speaker's":[12],"voice":[13,74,81],"from":[14],"mixture":[16],"speech":[17,26,43,128],"multiple":[19],"speakers.":[20],"It":[21],"needs":[22],"enroll":[24],"in":[31,37],"advance":[32],"as":[33],"a":[34,58,93,109],"reference.":[35],"However,":[36],"practical":[38],"applications,":[39],"too":[40],"long":[41],"reference":[42,127,136],"during":[44],"enrollment":[45,69,72],"will":[46],"decrease":[47],"user's":[49],"motivation":[50],"use.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56],"propose":[57],"Voice":[59],"Extractor-Voice":[60],"Extractor":[61],"(VE-VE)":[62],"framework":[63],"for":[64,134],"TSE":[65],"task":[66],"with":[67],"ultra-short":[68,126],"speech.":[70,137],"and":[73],"processes":[76],"utilize":[77],"same":[79],"RNN-based":[80],"extractor.":[82],"Speaker":[83],"characteristics":[84],"are":[85],"carried":[86],"by":[87],"RNN":[89],"state.":[90],"We":[91],"design":[92],"network":[94],"VEVEN":[95],"test":[97],"effectiveness":[99],"our":[101,119],"proposed":[102],"framework.":[103],"Experiments":[104],"show":[105],"that":[106],"it":[107],"achieves":[108],"new":[110],"state-of-the-art":[111],"(SOTA)":[112],"performance":[113],"on":[114],"public":[115],"WSJ0-2mix":[116],"datasets.":[117],"Furthermore,":[118],"approach":[120],"has":[121],"capacity":[123],"support":[125],"requirement.":[129],"17.7dB":[130],"SI-SDRi":[131],"achieved":[133],"0.2s":[135]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":2}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}