{"id":"https://openalex.org/W3097448764","doi":"https://doi.org/10.21437/interspeech.2020-2970","title":"Learning Speaker Embedding from Text-to-Speech","display_name":"Learning Speaker Embedding from Text-to-Speech","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3097448764","doi":"https://doi.org/10.21437/interspeech.2020-2970","mag":"3097448764"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2970","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2970","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5059500729","display_name":"Jaejin Cho","orcid":"https://orcid.org/0000-0001-5672-6765"},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Jaejin Cho","raw_affiliation_strings":["Center for Language and Speech Processing,"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing,","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027217976","display_name":"Piotr \u017belasko","orcid":"https://orcid.org/0000-0002-8245-0413"},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Piotr \u017belasko","raw_affiliation_strings":["Center for Language and Speech Processing,"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing,","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057010207","display_name":"Jes\u00fas Villalba","orcid":"https://orcid.org/0000-0001-9459-8426"},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]},{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["GR","US"],"is_corresponding":false,"raw_author_name":"Jes\u00fas Villalba","raw_affiliation_strings":["Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","Center for Language and Speech Processing,"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing,","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR","US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","Center for Language and Speech Processing,"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing,","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]},{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["GR","US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","Center for Language and Speech Processing,"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing,","institution_ids":["https://openalex.org/I4210098364"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5059500729"],"corresponding_institution_ids":["https://openalex.org/I4210098364"],"apc_list":null,"apc_paid":null,"fwci":0.7954,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78864263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3256","last_page":"3260"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9908000230789185,"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":0.9810000061988831,"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":0.7678539752960205},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6553648710250854},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5269325971603394},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4432591497898102},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4160693883895874},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40508466958999634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3292887508869171}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7678539752960205},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6553648710250854},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5269325971603394},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4432591497898102},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4160693883895874},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40508466958999634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3292887508869171}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2970","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2970","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W2024490156","https://openalex.org/W2129142580","https://openalex.org/W2150769028","https://openalex.org/W2406312423","https://openalex.org/W2514741789","https://openalex.org/W2734864502","https://openalex.org/W2766812927","https://openalex.org/W2794490148","https://openalex.org/W2808706139","https://openalex.org/W2884607399","https://openalex.org/W2888867175","https://openalex.org/W2890964092","https://openalex.org/W2907262790","https://openalex.org/W2962691331","https://openalex.org/W2962699523","https://openalex.org/W2963035245","https://openalex.org/W2963371159","https://openalex.org/W2963466847","https://openalex.org/W2963739817","https://openalex.org/W2963799213","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2972705840","https://openalex.org/W2972818416","https://openalex.org/W2972894903","https://openalex.org/W2979593053","https://openalex.org/W2981087920","https://openalex.org/W2983539408","https://openalex.org/W4288107125","https://openalex.org/W4289383906","https://openalex.org/W4298174729"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1521049138","https://openalex.org/W2144208207","https://openalex.org/W1813780412","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2148232863","https://openalex.org/W2160753975","https://openalex.org/W2118860825","https://openalex.org/W2161543916"],"abstract_inverted_index":{"Zero-shot":[0],"multi-speaker":[1],"Text-to-Speech":[2],"(TTS)":[3],"generates":[4],"target":[5],"speaker":[6,15,33,42,76,85,91,160,175],"voices":[7],"given":[8],"an":[9],"input":[10],"text":[11],"and":[12,41,126,167,180],"the":[13,21,24,51,59,67,84,90,95,98,135,156],"corresponding":[14],"embedding.In":[16],"this":[17],"work,":[18],"we":[19],"investigate":[20],"effectiveness":[22],"of":[23,97],"TTS":[25,40,60,99,105,131,144],"reconstruction":[26,70],"objective":[27],"to":[28,78,115,140,153],"improve":[29],"representation":[30],"learning":[31],"for":[32,89,155],"verification.We":[34],"jointly":[35],"trained":[36],"endto-end":[37],"Tacotron":[38],"2":[39],"embedding":[43],"networks":[44],"in":[45,178],"a":[46,171],"self-supervised":[47],"fashion.We":[48],"hypothesize":[49],"that":[50,64,134],"embeddings":[52,81,117,145],"will":[53,62],"contain":[54],"minimal":[55],"phonetic":[56],"information":[57,65],"since":[58],"decoder":[61],"obtain":[63],"from":[66,106,170],"textual":[68],"input.TTS":[69],"can":[71],"also":[72],"be":[73],"combined":[74],"with":[75,151,159],"classification":[77,161,176],"enhance":[79],"these":[80],"further.Once":[82],"trained,":[83],"encoder":[86],"computes":[87],"representations":[88],"verification":[92],"task,":[93],"while":[94],"rest":[96],"blocks":[100],"are":[101],"discarded.We":[102],"investigated":[103],"training":[104],"either":[107],"manual":[108,121],"or":[109],"ASR-generated":[110],"transcripts.The":[111],"latter":[112,136],"allows":[113],"us":[114],"train":[116],"on":[118],"datasets":[119],"without":[120],"transcripts.We":[122],"compared":[123],"ASR":[124],"transcripts":[125],"Kaldi":[127],"phone":[128],"alignments":[129],"as":[130],"inputs,":[132],"showing":[133],"performed":[137],"better":[138],"due":[139],"their":[141],"finer":[142],"resolution.Unsupervised":[143],"improved":[146,163],"EER":[147,164],"by":[148,165],"2.06%":[149],"absolute":[150],"regard":[152],"i-vectors":[154],"LibriTTS":[157,179],"dataset.TTS":[158],"loss":[162,177],"0.28%":[166],"0.73%":[168],"absolutely":[169],"model":[172],"using":[173],"only":[174],"Voxceleb1":[181],"respectively.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}