{"id":"https://openalex.org/W3161294170","doi":"https://doi.org/10.1109/icassp39728.2021.9414438","title":"SynAug: Synthesis-Based Data Augmentation for Text-Dependent Speaker Verification","display_name":"SynAug: Synthesis-Based Data Augmentation for Text-Dependent Speaker Verification","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161294170","doi":"https://doi.org/10.1109/icassp39728.2021.9414438","mag":"3161294170"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414438","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":"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/A5035532752","display_name":"Chenpeng Du","orcid":"https://orcid.org/0000-0001-5329-0847"},"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":"Chenpeng Du","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100690517","display_name":"Bing Han","orcid":"https://orcid.org/0000-0002-6319-6755"},"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":"Bing Han","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"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":["MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","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":["MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"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":"Kai Yu","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute SpeechLab, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5844","last_page":"5848"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9990000128746033,"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":0.9973000288009644,"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":0.8343855142593384},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.6180123090744019},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6084840893745422},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5561714768409729},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5550569891929626},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.49234020709991455},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.49112555384635925},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4775315523147583},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.42802560329437256},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.4243982434272766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40509799122810364},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3969426453113556},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32075732946395874},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08045873045921326}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8343855142593384},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.6180123090744019},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6084840893745422},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5561714768409729},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5550569891929626},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.49234020709991455},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.49112555384635925},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4775315523147583},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.42802560329437256},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.4243982434272766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40509799122810364},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3969426453113556},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32075732946395874},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08045873045921326},{"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414438","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2046056978","https://openalex.org/W2120847449","https://openalex.org/W2150769028","https://openalex.org/W2186774823","https://openalex.org/W2406778302","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2890964092","https://openalex.org/W2898727538","https://openalex.org/W2936774411","https://openalex.org/W2944613371","https://openalex.org/W2962691331","https://openalex.org/W2963272440","https://openalex.org/W2963927338","https://openalex.org/W2964307104","https://openalex.org/W2972359262","https://openalex.org/W2972668418","https://openalex.org/W3008480565","https://openalex.org/W3015394728","https://openalex.org/W3015611708","https://openalex.org/W3015654635","https://openalex.org/W3033411150","https://openalex.org/W4295731579","https://openalex.org/W4298580827","https://openalex.org/W6631362777","https://openalex.org/W6686645966","https://openalex.org/W6713287686","https://openalex.org/W6748409065","https://openalex.org/W6750489868","https://openalex.org/W6756385397","https://openalex.org/W6775549941","https://openalex.org/W6778823374"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W3141593045","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W2407001684","https://openalex.org/W3096066489","https://openalex.org/W3119184205"],"abstract_inverted_index":{"Text-dependent":[0],"speaker":[1],"verification":[2],"systems":[3,110],"trained":[4],"on":[5,62],"large":[6],"amount":[7,89],"of":[8,21,58,90],"labelled":[9],"data":[10,40,100],"exhibit":[11],"remarkable":[12],"performance.":[13],"However,":[14],"collecting":[15],"the":[16,46,63,73,78,84,88,109],"speech":[17,92],"from":[18],"a":[19,27,37],"lot":[20],"speakers":[22,51],"with":[23,49,98],"target":[24],"transcript":[25],"is":[26,60,93],"lengthy":[28],"and":[29,52,107],"expensive":[30],"process.":[31],"In":[32],"this":[33],"work,":[34],"we":[35],"propose":[36],"synthesis":[38],"based":[39],"augmentation":[41,101],"method":[42],"(SynAug)":[43],"to":[44],"expand":[45],"training":[47],"set":[48],"more":[50],"text-controlled":[53],"synthesized":[54],"speech.":[55],"The":[56],"performance":[57,80],"SynAug":[59],"evaluated":[61],"RSR2015":[64],"dataset.":[65],"Experimental":[66],"results":[67],"show":[68],"that":[69],"for":[70,83],"i-vector":[71],"framework,":[72],"proposed":[74],"methods":[75,102],"can":[76],"boost":[77],"system":[79],"significantly,":[81],"especially":[82],"low-resource":[85],"condition":[86],"where":[87],"genuine":[91],"extremely":[94,116],"limited.":[95],"Moreover,":[96],"combined":[97],"traditional":[99],"such":[103],"as":[104],"adding":[105],"noises":[106],"reverberation,":[108],"could":[111],"be":[112],"further":[113],"strengthened":[114],"in":[115],"limited":[117],"resource":[118],"situation.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}