{"id":"https://openalex.org/W3158102353","doi":"https://doi.org/10.21437/interspeech.2021-1774","title":"SC-GlowTTS: An Efficient Zero-Shot Multi-Speaker Text-To-Speech Model","display_name":"SC-GlowTTS: An Efficient Zero-Shot Multi-Speaker Text-To-Speech Model","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3158102353","doi":"https://doi.org/10.21437/interspeech.2021-1774","mag":"3158102353"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1774","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1774","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.05557","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025318789","display_name":"Edresson Casanova","orcid":"https://orcid.org/0000-0003-0160-7173"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Edresson Casanova","raw_affiliation_strings":["University of S\u00e3o Paulo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of S\u00e3o Paulo","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057570319","display_name":"Christopher Shulby","orcid":"https://orcid.org/0000-0001-9637-9657"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christopher Shulby","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021987215","display_name":"Eren G\u00f6lge","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eren G\u00f6lge","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064235660","display_name":"Nicolas M. M\u00fcller","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicolas Michael M\u00fcller","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057639095","display_name":"Frederico Santos de Oliveira","orcid":"https://orcid.org/0000-0002-5885-6747"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frederico Santos de Oliveira","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083987838","display_name":"Arnaldo C\u00e2ndido","orcid":"https://orcid.org/0000-0002-5647-0891"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arnaldo Candido Jr.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038260547","display_name":"Anderson da Silva Soares","orcid":"https://orcid.org/0000-0002-2967-6077"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anderson da Silva Soares","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059202822","display_name":"Sandra Maria Alu\u00edsio","orcid":"https://orcid.org/0000-0001-5108-2630"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sandra Maria Aluisio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5029845097","display_name":"Moacir Antonelli Ponti","orcid":"https://orcid.org/0000-0003-2059-9463"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moacir Antonelli Ponti","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":0.5861,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66717283,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3645","last_page":"3649"},"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":0.9993000030517578,"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":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7519654035568237},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7433538436889648},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7382292151451111},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6166497468948364},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5188487768173218},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4878730773925781},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.4775187075138092},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4643087387084961},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3915204405784607},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1904875934123993},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11285755038261414},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07966336607933044},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06960305571556091},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.057235389947891235}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7519654035568237},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7433538436889648},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7382292151451111},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6166497468948364},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5188487768173218},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4878730773925781},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.4775187075138092},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4643087387084961},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3915204405784607},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1904875934123993},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11285755038261414},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07966336607933044},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06960305571556091},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.057235389947891235},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.21437/interspeech.2021-1774","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1774","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.05557","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.05557","pdf_url":"https://arxiv.org/pdf/2104.05557","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3158102353","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2104.05557.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:fraunhofer.de:N-646675","is_oa":false,"landing_page_url":"http://publica.fraunhofer.de/documents/N-646675.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer AISEC","raw_type":"Conference Paper"},{"id":"pmh:oai:null:publica/417243","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/417243","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"},{"id":"doi:10.48550/arxiv.2104.05557","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.05557","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.05557","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.05557","pdf_url":"https://arxiv.org/pdf/2104.05557","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3158102353.pdf","grobid_xml":"https://content.openalex.org/works/W3158102353.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2160473997","https://openalex.org/W2527729766","https://openalex.org/W2587284713","https://openalex.org/W2766812927","https://openalex.org/W2767052532","https://openalex.org/W2792995953","https://openalex.org/W2796495654","https://openalex.org/W2796898542","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2962788625","https://openalex.org/W2963192573","https://openalex.org/W2963403868","https://openalex.org/W2963432880","https://openalex.org/W2963970792","https://openalex.org/W2964243274","https://openalex.org/W2969937244","https://openalex.org/W2970730223","https://openalex.org/W2994689640","https://openalex.org/W2995929068","https://openalex.org/W3013020904","https://openalex.org/W3015826515","https://openalex.org/W3025528898","https://openalex.org/W3025671734","https://openalex.org/W3026874504","https://openalex.org/W3035083561","https://openalex.org/W3048173247","https://openalex.org/W3048423403","https://openalex.org/W3048593389","https://openalex.org/W3087074707","https://openalex.org/W3092028330"],"related_works":["https://openalex.org/W3196584150","https://openalex.org/W3033194228","https://openalex.org/W3160950295","https://openalex.org/W3174102645","https://openalex.org/W2594927458","https://openalex.org/W3024786082","https://openalex.org/W3177506141","https://openalex.org/W3162424266","https://openalex.org/W3163929126","https://openalex.org/W3016048045","https://openalex.org/W3034058691","https://openalex.org/W3197659778","https://openalex.org/W3040867037","https://openalex.org/W2345067732","https://openalex.org/W2898798322","https://openalex.org/W3211614993","https://openalex.org/W2563906718","https://openalex.org/W2963252329","https://openalex.org/W3108184206","https://openalex.org/W3094457719"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,39,53],"propose":[4,21],"SC-GlowTTS:":[5],"an":[6],"efficient":[7],"zero-shot":[8,34],"multi-speaker":[9],"text-to-speech":[10],"model":[11,68,85],"that":[12,25,30,56],"improves":[13],"similarity":[14,77,95],"for":[15,61,81,94],"speakers":[16],"unseen":[17],"during":[18],"training.":[19],"We":[20],"a":[22,27,33,41,58],"speaker-conditional":[23],"architecture":[24],"explores":[26],"flow-based":[28],"decoder":[29],"works":[31],"in":[32],"scenario.":[35],"As":[36],"text":[37],"encoders,":[38],"explore":[40],"dilated":[42],"residual":[43],"convolutional-based":[44,47],"encoder,":[45,48],"gated":[46],"and":[49,78],"transformer-based":[50],"encoder.":[51],"Additionally,":[52],"have":[54],"shown":[55],"adjusting":[57],"GAN-based":[59],"vocoder":[60],"the":[62,66,70,76],"spectrograms":[63],"predicted":[64],"by":[65],"TTS":[67],"on":[69],"training":[71],"dataset":[72],"can":[73],"significantly":[74],"improve":[75],"speech":[79,103],"quality":[80],"new":[82,97],"speakers.":[83],"Our":[84],"converges":[86],"using":[87],"only":[88],"11":[89],"speakers,":[90,98],"reaching":[91],"state-of-the-art":[92],"results":[93],"with":[96],"as":[99,101],"well":[100],"high":[102],"quality.":[104]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}