{"id":"https://openalex.org/W3145003630","doi":"https://doi.org/10.1109/slt48900.2021.9383525","title":"Synth2Aug: Cross-Domain Speaker Recognition with TTS Synthesized Speech","display_name":"Synth2Aug: Cross-Domain Speaker Recognition with TTS Synthesized Speech","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3145003630","doi":"https://doi.org/10.1109/slt48900.2021.9383525","mag":"3145003630"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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/A5053487978","display_name":"Yiling Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yiling Huang","raw_affiliation_strings":["Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101904983","display_name":"Yutian Chen","orcid":"https://orcid.org/0009-0003-5202-0054"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yutian Chen","raw_affiliation_strings":["DeepMind, London, UK"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029030495","display_name":"Jason Pelecanos","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Pelecanos","raw_affiliation_strings":["Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108047863","display_name":"Quan Wang","orcid":"https://orcid.org/0000-0001-5483-0243"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Quan Wang","raw_affiliation_strings":["Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5053487978"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.8158,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77345786,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"316","last_page":"322"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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/T12031","display_name":"Speech and dialogue systems","score":0.9961000084877014,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8172808885574341},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7695788145065308},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6082064509391785},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5816245079040527},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.571794867515564},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.5049102902412415},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5023288726806641},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4659247100353241},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.464401513338089},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.44638490676879883},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40400630235671997},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3906025290489197},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07369127869606018}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8172808885574341},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7695788145065308},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6082064509391785},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5816245079040527},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.571794867515564},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.5049102902412415},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5023288726806641},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4659247100353241},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.464401513338089},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.44638490676879883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40400630235671997},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3906025290489197},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07369127869606018},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W15681643","https://openalex.org/W748732769","https://openalex.org/W1485222997","https://openalex.org/W1574170747","https://openalex.org/W1959608418","https://openalex.org/W2046056978","https://openalex.org/W2114925438","https://openalex.org/W2136439176","https://openalex.org/W2293634267","https://openalex.org/W2402195372","https://openalex.org/W2519091744","https://openalex.org/W2575249418","https://openalex.org/W2584329820","https://openalex.org/W2612434969","https://openalex.org/W2617258110","https://openalex.org/W2696967604","https://openalex.org/W2748488820","https://openalex.org/W2766812927","https://openalex.org/W2808706139","https://openalex.org/W2890964092","https://openalex.org/W2892620417","https://openalex.org/W2936774411","https://openalex.org/W2949382160","https://openalex.org/W2962788625","https://openalex.org/W2963432880","https://openalex.org/W2963568578","https://openalex.org/W2963912924","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2972359262","https://openalex.org/W2973190269","https://openalex.org/W2983434507","https://openalex.org/W3006741730","https://openalex.org/W3012367631","https://openalex.org/W3015280134","https://openalex.org/W3024464021","https://openalex.org/W3026777299","https://openalex.org/W3099825973","https://openalex.org/W3107298252","https://openalex.org/W3127686677","https://openalex.org/W3198123200","https://openalex.org/W4289383906","https://openalex.org/W4298580827","https://openalex.org/W6634468015","https://openalex.org/W6640963894","https://openalex.org/W6696934422","https://openalex.org/W6713401928","https://openalex.org/W6737575990","https://openalex.org/W6745697700","https://openalex.org/W6748409065","https://openalex.org/W6752888775","https://openalex.org/W6755135894","https://openalex.org/W6755300632","https://openalex.org/W6776336016","https://openalex.org/W6780755494","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"In":[0,42],"recent":[1],"years,":[2],"Text-To-Speech":[3],"(TTS)":[4],"has":[5],"been":[6],"used":[7,95],"as":[8],"a":[9,30,52,111,120,123],"data":[10],"augmentation":[11],"technique":[12],"for":[13,60,96],"speech":[14,36,70],"recognition":[15,74],"to":[16,34],"help":[17],"complement":[18],"inadequacies":[19],"in":[20,37],"the":[21,27,47,87,103,107],"training":[22],"data.":[23],"Correspondingly,":[24],"we":[25,45,85],"investigate":[26],"use":[28],"of":[29,39,56,89,92,106],"multi-speaker":[31],"TTS":[32,68,97],"system":[33],"synthesize":[35],"support":[38],"speaker":[40,73],"recognition.":[41],"this":[43],"study":[44],"focus":[46],"analysis":[48],"on":[49,64],"tasks":[50],"where":[51],"relatively":[53],"small":[54],"number":[55],"speakers":[57],"is":[58,110,117,127],"available":[59],"training.":[61,83],"We":[62],"observe":[63],"our":[65],"datasets":[66],"that":[67,101,116],"synthesized":[69],"improves":[71],"cross-domain":[72],"performance":[75],"and":[76,114],"can":[77],"be":[78],"combined":[79],"effectively":[80],"with":[81,122],"multi-style":[82],"Additionally,":[84],"explore":[86],"effectiveness":[88],"different":[90],"types":[91],"text":[93],"transcripts":[94],"synthesis.":[98],"Results":[99],"suggest":[100],"matching":[102],"textual":[104],"content":[105],"target":[108],"domain":[109],"good":[112],"practice,":[113],"if":[115],"not":[118],"feasible,":[119],"transcript":[121],"sufficiently":[124],"large":[125],"vocabulary":[126],"recommended.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}