{"id":"https://openalex.org/W3097290232","doi":"https://doi.org/10.21437/interspeech.2020-1229","title":"Can Speaker Augmentation Improve Multi-Speaker End-to-End TTS?","display_name":"Can Speaker Augmentation Improve Multi-Speaker End-to-End TTS?","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3097290232","doi":"https://doi.org/10.21437/interspeech.2020-1229","mag":"3097290232"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1229","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1229","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":"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/A5082349516","display_name":"Erica Cooper","orcid":"https://orcid.org/0000-0002-2978-2793"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erica Cooper","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010825170","display_name":"Cheng-I Lai","orcid":"https://orcid.org/0000-0002-2343-8596"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng-I Lai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068072475","display_name":"Yusuke Yasuda","orcid":"https://orcid.org/0000-0002-2130-747X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yusuke Yasuda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.61,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.87179606,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3979","last_page":"3983"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9889000058174133,"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":0.9797000288963318,"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":0.7940311431884766},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7519761323928833},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6469428539276123},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5988951325416565},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5857670307159424},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5226214528083801},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5026156902313232},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4704930782318115},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4418639838695526},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4411371350288391},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2920510172843933},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09121492505073547},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07095080614089966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7940311431884766},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7519761323928833},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6469428539276123},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5988951325416565},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5857670307159424},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5226214528083801},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5026156902313232},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4704930782318115},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4418639838695526},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4411371350288391},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2920510172843933},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09121492505073547},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07095080614089966},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1229","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1229","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":[{"score":0.699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1601555150","display_name":"Encoder Factorization for Capturing Dialect and Articulation Level in End-to-End Speech Synthesis","funder_award_id":"19K24372","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"Previous":[0],"work":[1],"on":[2,94,104],"speaker":[3,13,23,26,97,109],"adaptation":[4,24],"for":[5,47,68],"end-to-end":[6],"speech":[7],"synthesis":[8,85,95],"still":[9],"falls":[10],"short":[11],"in":[12,54],"similarity.":[14],"We":[15],"investigate":[16],"an":[17,92],"orthogonal":[18],"approach":[19],"to":[20,45,83],"the":[21,48,105],"current":[22],"paradigms,":[25],"augmentation,":[27],"by":[28,33,91],"creating":[29],"artificial":[30],"speakers":[31],"and":[32,50,77,98,101],"taking":[34],"advantage":[35],"of":[36,86,107],"low-quality":[37],"data.":[38],"The":[39],"base":[40],"Tacotron2":[41,69],"model":[42],"is":[43,75,81,89],"modified":[44],"account":[46],"channel":[49],"dialect":[51,99],"factors":[52],"inherent":[53],"these":[55],"corpora.":[56],"In":[57],"addition,":[58],"we":[59,66],"describe":[60],"a":[61,78,102],"warm-start":[62],"training":[63],"strategy":[64],"that":[65],"adopted":[67,82],"training.":[70],"A":[71],"large-scale":[72],"listening":[73],"test":[74],"conducted,":[76],"distance":[79],"metric":[80],"evaluate":[84],"dialects.":[87],"This":[88],"followed":[90],"analysis":[93],"quality,":[96],"similarity,":[100],"remark":[103],"effectiveness":[106],"our":[108],"augmentation":[110],"approach.":[111],"Audio":[112],"samples":[113],"are":[114],"available":[115],"online.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}