{"id":"https://openalex.org/W2973131224","doi":"https://doi.org/10.21437/interspeech.2019-1498","title":"Large-Scale Speaker Retrieval on Random Speaker Variability Subspace","display_name":"Large-Scale Speaker Retrieval on Random Speaker Variability Subspace","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2973131224","doi":"https://doi.org/10.21437/interspeech.2019-1498","mag":"2973131224"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1498","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1498","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/A5020263683","display_name":"Suwon Shon","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104771","display_name":"SiliconSapiens (South Korea)","ror":"https://ror.org/015rsk965","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210104771"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Suwon Shon","raw_affiliation_strings":["Neosapience, Inc., Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Neosapience, Inc., Seoul, South Korea","institution_ids":["https://openalex.org/I4210104771"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101974552","display_name":"Younggun Lee","orcid":"https://orcid.org/0000-0002-0596-9318"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Younggun Lee","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057610183","display_name":"Taesu Kim","orcid":"https://orcid.org/0000-0002-7956-3935"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taesu Kim","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020263683"],"corresponding_institution_ids":["https://openalex.org/I4210104771"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2963","last_page":"2967"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9994000196456909,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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/subspace-topology","display_name":"Subspace topology","score":0.7179878950119019},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.7160933613777161},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7126672863960266},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.6329643726348877},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5430055260658264},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5390874743461609},{"id":"https://openalex.org/keywords/rss","display_name":"RSS","score":0.5346502661705017},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5137108564376831},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.482557475566864},{"id":"https://openalex.org/keywords/random-projection","display_name":"Random projection","score":0.43950796127319336},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4344894289970398},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4337519109249115},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4162834882736206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3207437992095947}],"concepts":[{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.7179878950119019},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.7160933613777161},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7126672863960266},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.6329643726348877},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5430055260658264},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5390874743461609},{"id":"https://openalex.org/C2385561","wikidata":"https://www.wikidata.org/wiki/Q45432","display_name":"RSS","level":2,"score":0.5346502661705017},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5137108564376831},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.482557475566864},{"id":"https://openalex.org/C2777036070","wikidata":"https://www.wikidata.org/wiki/Q18393452","display_name":"Random projection","level":2,"score":0.43950796127319336},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4344894289970398},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4337519109249115},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4162834882736206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3207437992095947},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-1498","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1498","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W121456868","https://openalex.org/W1502916507","https://openalex.org/W2107542203","https://openalex.org/W2122992400","https://openalex.org/W2150769028","https://openalex.org/W2170702379","https://openalex.org/W2404719667","https://openalex.org/W2405236876","https://openalex.org/W2407964052","https://openalex.org/W2609517418","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2808631503","https://openalex.org/W2808706139","https://openalex.org/W2963609956","https://openalex.org/W4233464001"],"related_works":["https://openalex.org/W2135779989","https://openalex.org/W2144265691","https://openalex.org/W2754607325","https://openalex.org/W144856782","https://openalex.org/W2080135560","https://openalex.org/W2147226516","https://openalex.org/W2975588143","https://openalex.org/W2010970209","https://openalex.org/W2752074276","https://openalex.org/W3082824678"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,32,57,114,119],"fast":[4],"speaker":[5,80,91,121],"search":[6,139],"system":[7],"to":[8,55,87],"retrieve":[9],"segments":[10],"of":[11,31,104,116],"the":[12,17,36,89,94,123,126,137],"same":[13,90,95],"voice":[14,34],"identity":[15],"in":[16,35,39],"large-scale":[18,37],"data.A":[19],"recent":[20],"study":[21],"shows":[22,129],"that":[23,65],"Locality":[24],"Sensitive":[25],"Hashing":[26],"(LSH)":[27],"enables":[28],"quick":[29],"retrieval":[30],"relevant":[33],"data":[38,58],"conjunction":[40],"with":[41],"i-vector":[42],"while":[43],"maintaining":[44],"accuracy.In":[45],"this":[46],"paper,":[47],"we":[48,99],"proposed":[49,127],"Random":[50],"Speaker-variability":[51],"Subspace":[52],"(RSS)":[53],"projection":[54],"map":[56],"into":[59,93],"LSH":[60],"based":[61],"hash":[62,96,105],"tables.We":[63],"hypothesized":[64],"rather":[66],"than":[67,136],"projecting":[68,76],"on":[69,77],"completely":[70],"random":[71],"subspace":[72],"without":[73],"considering":[74],"data,":[75],"randomly":[78,112],"generated":[79,110],"variability":[81],"space":[82],"would":[83],"give":[84],"more":[85],"chance":[86],"put":[88],"representation":[92],"bins,":[97],"so":[98],"can":[100,108],"use":[101],"less":[102],"number":[103],"tables.Multiple":[106],"RSS":[107],"be":[109],"by":[111],"selecting":[113],"subset":[115],"speakers":[117],"from":[118],"large":[120],"cohort.From":[122],"experimental":[124],"result,":[125],"approach":[128],"100":[130],"times":[131,134],"and":[132,140],"7":[133],"faster":[135],"linear":[138],"LSH,":[141],"respectively.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}