{"id":"https://openalex.org/W4406461933","doi":"https://doi.org/10.1109/slt61566.2024.10832359","title":"Enhancing Open-Set Speaker Identification Through Rapid Tuning With Speaker Reciprocal Points and Negative Sample","display_name":"Enhancing Open-Set Speaker Identification Through Rapid Tuning With Speaker Reciprocal Points and Negative Sample","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461933","doi":"https://doi.org/10.1109/slt61566.2024.10832359"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832359","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":"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/A5100370053","display_name":"Zhiyong Chen","orcid":"https://orcid.org/0000-0002-2033-4249"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiyong Chen","raw_affiliation_strings":["Shanghai University,School of Communication and Information Engineering"],"affiliations":[{"raw_affiliation_string":"Shanghai University,School of Communication and Information Engineering","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025619660","display_name":"Zhilong Ai","orcid":"https://orcid.org/0000-0002-5264-8875"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqi Ai","raw_affiliation_strings":["Shanghai University,School of Communication and Information Engineering"],"affiliations":[{"raw_affiliation_string":"Shanghai University,School of Communication and Information Engineering","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015889784","display_name":"Xinnuo Li","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinnuo Li","raw_affiliation_strings":["Shanghai University,School of Communication and Information Engineering"],"affiliations":[{"raw_affiliation_string":"Shanghai University,School of Communication and Information Engineering","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084521046","display_name":"Shugong Xu","orcid":"https://orcid.org/0000-0003-1905-6269"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shugong Xu","raw_affiliation_strings":["Shanghai University,School of Communication and Information Engineering"],"affiliations":[{"raw_affiliation_string":"Shanghai University,School of Communication and Information Engineering","institution_ids":["https://openalex.org/I113940042"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100370053"],"corresponding_institution_ids":["https://openalex.org/I113940042"],"apc_list":null,"apc_paid":null,"fwci":0.375,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62308598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1144","last_page":"1149"},"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":0.9993000030517578,"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":0.9951000213623047,"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/speaker-identification","display_name":"Speaker identification","score":0.7599111199378967},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6842623353004456},{"id":"https://openalex.org/keywords/reciprocal","display_name":"Reciprocal","score":0.6513931751251221},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6442993879318237},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6057514548301697},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6003801226615906},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5292434096336365},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.511043906211853},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.48156431317329407},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08120927214622498}],"concepts":[{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.7599111199378967},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6842623353004456},{"id":"https://openalex.org/C2777742833","wikidata":"https://www.wikidata.org/wiki/Q1964083","display_name":"Reciprocal","level":2,"score":0.6513931751251221},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6442993879318237},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6057514548301697},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6003801226615906},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5292434096336365},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.511043906211853},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.48156431317329407},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08120927214622498},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832359","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W3015499614","https://openalex.org/W3024144824","https://openalex.org/W3092956463","https://openalex.org/W3128793294","https://openalex.org/W3134961575","https://openalex.org/W3137249133","https://openalex.org/W3173355548","https://openalex.org/W3209984917","https://openalex.org/W4224925560","https://openalex.org/W4226439436","https://openalex.org/W4319862271","https://openalex.org/W4323519273","https://openalex.org/W4372341266","https://openalex.org/W4385823483","https://openalex.org/W4389363808","https://openalex.org/W4391692021","https://openalex.org/W4399096462","https://openalex.org/W4402111799","https://openalex.org/W6859665146","https://openalex.org/W6861764568"],"related_works":["https://openalex.org/W4389984014","https://openalex.org/W36105149","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W2545131480","https://openalex.org/W2249138175","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W4401661962","https://openalex.org/W2096510939"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,14,40],"novel":[4],"framework":[5],"for":[6,48,110],"open-set":[7,88,120],"speaker":[8,27,100],"identification":[9],"in":[10,17,106,141],"household":[11,112],"environments,":[12],"playing":[13],"crucial":[15],"role":[16],"facilitating":[18],"seamless":[19],"human-computer":[20],"interactions.":[21],"Addressing":[22],"the":[23,127],"limitations":[24],"of":[25,70,130],"current":[26],"models":[28],"and":[29,81],"classification":[30],"approaches,":[31],"our":[32,142],"work":[33],"integrates":[34],"an":[35,67],"pretrained":[36],"WavLM":[37,132],"frontend":[38],"with":[39,78],"few-shot":[41],"rapid":[42],"tuning":[43],"neural":[44],"network":[45],"(NN)":[46],"backend":[47],"enrollment,":[49],"employing":[50],"task-optimized":[51],"Speaker":[52],"Reciprocal":[53],"Points":[54],"Learning":[55],"(SRPL)":[56],"to":[57,85,124],"enhance":[58],"discrimination":[59],"across":[60,96],"multiple":[61],"target":[62],"speakers.":[63],"Furthermore,":[64],"we":[65],"propose":[66],"enhanced":[68,119],"version":[69],"SRPL":[71],"(SRPL+),":[72],"which":[73],"incorporates":[74],"negative":[75,83],"sample":[76],"learning":[77],"both":[79],"speech-synthesized":[80],"real":[82],"samples":[84],"significantly":[86],"improve":[87],"SID":[89],"accuracy.":[90],"Our":[91],"approach":[92],"is":[93],"thoroughly":[94],"evaluated":[95],"various":[97],"multi-language":[98],"textdependent":[99],"recognition":[101,114],"datasets,":[102],"demonstrating":[103],"its":[104],"effectiveness":[105],"achieving":[107],"high":[108],"usability":[109],"complex":[111],"multi-speaker":[113],"scenarios.":[115],"The":[116],"proposed":[117],"system":[118],"performance":[121],"by":[122],"up":[123],"27%":[125],"over":[126],"directly":[128],"use":[129],"efficient":[131],"base+":[133],"model.":[134],"For":[135],"detailed":[136],"information":[137],"on":[138],"open-sourced":[139],"implementation":[140],"project":[143],"website":[144],"1.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}