{"id":"https://openalex.org/W4210631835","doi":"https://doi.org/10.1109/asru51503.2021.9688156","title":"Short-Utterance Embedding Enhancement Method Based on Time Series Forecasting Technique for Text-Independent Speaker Verification","display_name":"Short-Utterance Embedding Enhancement Method Based on Time Series Forecasting Technique for Text-Independent Speaker Verification","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4210631835","doi":"https://doi.org/10.1109/asru51503.2021.9688156"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688156","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5101610186","display_name":"Jeong-Hwan Choi","orcid":"https://orcid.org/0000-0002-3937-2333"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jeong-Hwan Choi","raw_affiliation_strings":["Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110972432","display_name":"Joon\u2010Young Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon-Young Yang","raw_affiliation_strings":["Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002418613","display_name":"Joon\u2010Hyuk Chang","orcid":"https://orcid.org/0000-0003-2610-2323"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon-Hyuk Chang","raw_affiliation_strings":["Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101610186"],"corresponding_institution_ids":["https://openalex.org/I4575257"],"apc_list":null,"apc_paid":null,"fwci":0.2513,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.53813797,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"130","last_page":"137"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9962000250816345,"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":0.9891999959945679,"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/utterance","display_name":"Utterance","score":0.9338638782501221},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7376434803009033},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7121252417564392},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6541379690170288},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6068625450134277},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5976316928863525},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5591179728507996},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5032228827476501},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.4982273578643799},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4268268942832947},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36608564853668213},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.31401482224464417}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.9338638782501221},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7376434803009033},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7121252417564392},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6541379690170288},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6068625450134277},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5976316928863525},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5591179728507996},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5032228827476501},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.4982273578643799},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4268268942832947},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36608564853668213},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.31401482224464417},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688156","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","score":0.6299999952316284,"display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W67277430","https://openalex.org/W1522301498","https://openalex.org/W2003602843","https://openalex.org/W2046056978","https://openalex.org/W2117014758","https://openalex.org/W2121812409","https://openalex.org/W2130942839","https://openalex.org/W2150769028","https://openalex.org/W2194775991","https://openalex.org/W2395750323","https://openalex.org/W2516764878","https://openalex.org/W2620629206","https://openalex.org/W2726515241","https://openalex.org/W2784163702","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2916104401","https://openalex.org/W2951019013","https://openalex.org/W2963077989","https://openalex.org/W2963371159","https://openalex.org/W2965791322","https://openalex.org/W3008104819","https://openalex.org/W3008533347","https://openalex.org/W3008911072","https://openalex.org/W3013020904","https://openalex.org/W3088315586","https://openalex.org/W3090254849","https://openalex.org/W3095851463","https://openalex.org/W3103152812","https://openalex.org/W4295312788","https://openalex.org/W6631190155","https://openalex.org/W6662018943","https://openalex.org/W6679436768","https://openalex.org/W6740167877","https://openalex.org/W6750144670","https://openalex.org/W6754496211","https://openalex.org/W6760057544","https://openalex.org/W6766978945","https://openalex.org/W6774329723","https://openalex.org/W6783527727","https://openalex.org/W6785404415"],"related_works":["https://openalex.org/W112947718","https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W1998549096","https://openalex.org/W3141593045","https://openalex.org/W1996621592","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506"],"abstract_inverted_index":{"Short-utterance":[0],"embedding,":[1],"which":[2],"is":[3,52,85,107],"a":[4,9,28,38,45,49,75,88,101,119,124,130],"speaker":[5,14,20,64,77,153],"embedding":[6,78],"extracted":[7,67],"from":[8,68],"short":[10,157],"utterance,":[11],"shows":[12],"poor":[13],"verification":[15,154],"performance":[16,155],"due":[17],"to":[18,30,37,118],"insufficient":[19],"information.":[21],"To":[22],"address":[23],"the":[24,32,63,69,81,113,127,138,143,151],"problem,":[25],"we":[26],"propose":[27],"method":[29,149],"map":[31],"set":[33,39],"of":[34,40,71,83,90,95,115,132],"short-utterance":[35,116],"embeddings":[36,42,65,84,92,117],"long-utterance":[41,96,133],"based":[43,104],"on":[44,137],"neural":[46],"network.":[47],"Specifically,":[48],"speech":[50],"utterance":[51,158],"cropped":[53,72],"into":[54,87,129],"multiple":[55],"segments":[56,73],"whose":[57],"durations":[58],"are":[59,66],"gradually":[60],"increasing,":[61],"and":[62,93,122,140],"sequence":[70,82],"using":[74],"pre-trained":[76],"extractor.":[79],"Subsequently,":[80],"divided":[86],"group":[89,114,131],"short-utterances":[91],"that":[94,147],"embeddings.":[97,134],"In":[98],"our":[99,148],"method,":[100],"sequence-to-sequence":[102],"model":[103],"forecasting":[105],"technique":[106],"employed,":[108],"where":[109],"an":[110],"encoder":[111],"transforms":[112],"fixed-dimensional":[120],"vector,":[121],"then":[123],"decoder":[125],"converts":[126],"vector":[128],"Experimental":[135],"results":[136],"VoxCeleb":[139],"Speakers":[141],"in":[142],"Wild":[144],"datasets":[145],"show":[146],"improves":[150],"text-independent":[152],"under":[156],"condition.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}