{"id":"https://openalex.org/W3163150275","doi":"https://doi.org/10.1109/icassp39728.2021.9414550","title":"Unit Selection Synthesis Based Data Augmentation for Fixed Phrase Speaker Verification","display_name":"Unit Selection Synthesis Based Data Augmentation for Fixed Phrase Speaker Verification","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163150275","doi":"https://doi.org/10.1109/icassp39728.2021.9414550","mag":"3163150275"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5074673170","display_name":"Houjun Huang","orcid":"https://orcid.org/0000-0003-0757-0949"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Houjun Huang","raw_affiliation_strings":["AISpeech Ltd,Suzhou,China","MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, China","AISpeech Ltd, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"AISpeech Ltd,Suzhou,China","institution_ids":[]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"AISpeech Ltd, Suzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055220405","display_name":"Xu Xiang","orcid":"https://orcid.org/0000-0003-2530-9023"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Xiang","raw_affiliation_strings":["AISpeech Ltd,Suzhou,China","AISpeech Ltd, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"AISpeech Ltd,Suzhou,China","institution_ids":[]},{"raw_affiliation_string":"AISpeech Ltd, Suzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090607458","display_name":"Fei Zhao","orcid":"https://orcid.org/0000-0002-8198-3787"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei Zhao","raw_affiliation_strings":["AISpeech Ltd,Suzhou,China","AISpeech Ltd, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"AISpeech Ltd,Suzhou,China","institution_ids":[]},{"raw_affiliation_string":"AISpeech Ltd, Suzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328272","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0002-1595-3619"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab,Department of Computer Science and Engineering,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab,Department of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab,Department of Computer Science and Engineering,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab,Department of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5074673170"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.8158,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.77598216,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5849","last_page":"5853"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.998199999332428,"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":0.9955999851226807,"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":0.8272294998168945},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6433185338973999},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6379932165145874},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.60260409116745},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.562247633934021},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5139808058738708},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4406243860721588},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4353106617927551},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4230373501777649},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4124166965484619},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4075436294078827},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3826671540737152}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8272294998168945},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6433185338973999},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6379932165145874},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.60260409116745},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.562247633934021},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5139808058738708},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4406243860721588},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4353106617927551},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4230373501777649},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4124166965484619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4075436294078827},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3826671540737152},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":21,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1599623585","https://openalex.org/W1980719954","https://openalex.org/W2034940213","https://openalex.org/W2041823554","https://openalex.org/W2150658333","https://openalex.org/W2150769028","https://openalex.org/W2748488820","https://openalex.org/W2889048668","https://openalex.org/W2890964092","https://openalex.org/W2936774411","https://openalex.org/W2944613371","https://openalex.org/W2969985801","https://openalex.org/W2972315886","https://openalex.org/W2972668418","https://openalex.org/W3010925296","https://openalex.org/W3015503328","https://openalex.org/W3015611708","https://openalex.org/W3015678397","https://openalex.org/W6631362777","https://openalex.org/W6754473786"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2152483715","https://openalex.org/W2162158162","https://openalex.org/W4235705411","https://openalex.org/W1521299571","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2134501921","https://openalex.org/W2144470400"],"abstract_inverted_index":{"Data":[0],"augmentation":[1,20,80],"is":[2,51,65],"commonly":[3],"used":[4],"to":[5,56,82,101,120],"help":[6],"build":[7,57],"a":[8,58,74,122],"robust":[9],"speaker":[10,38,96],"verification":[11,39],"system,":[12,60],"especially":[13],"in":[14,114,131],"limited-resource":[15],"case.":[16],"However,":[17],"conventional":[18],"data":[19,46,64,79,87],"methods":[21],"usually":[22],"focus":[23],"on":[24,137],"the":[25,31,48,52,84,115,125,138,145,156],"diversity":[26],"of":[27,94],"acoustic":[28],"environment,":[29],"leaving":[30],"lexicon":[32],"variation":[33],"neglected.":[34],"For":[35],"text":[36],"dependent":[37],"tasks,":[40],"it\u2019s":[41],"well-known":[42],"that":[43,111,150],"preparing":[44],"training":[45],"with":[47,124],"target":[49,116,126],"transcript":[50,117,127],"most":[53],"effectual":[54],"approach":[55,91],"well-performing":[59],"however":[61],"collecting":[62],"such":[63],"time-consuming":[66],"and":[67,147],"expensive.":[68],"In":[69,89],"this":[70,90],"work,":[71],"we":[72],"propose":[73],"unit":[75],"selection":[76],"synthesis":[77],"based":[78],"method":[81,153],"leverage":[83],"abundant":[85],"text-independent":[86,92],"resources.":[88],"speeches":[93],"each":[95,104],"are":[97,118,134],"firstly":[98],"broke":[99],"up":[100],"speech":[102,123],"segments":[103,110],"contains":[105],"one":[106],"phone":[107],"unit.":[108],"Then":[109],"contain":[112],"phonetics":[113],"selected":[119],"produce":[121],"by":[128],"concatenating":[129],"them":[130],"turn.":[132],"Experiments":[133],"carried":[135],"out":[136],"AISHELL":[139],"Speaker":[140],"Verification":[141],"Challenge":[142],"2019":[143],"database,":[144],"results":[146],"analysis":[148],"shows":[149],"our":[151],"proposed":[152],"can":[154],"boost":[155],"system":[157],"performance":[158],"significantly.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
