{"id":"https://openalex.org/W3035434165","doi":"https://doi.org/10.21437/interspeech.2020-2663","title":"Generic Indic Text-to-Speech Synthesisers with Rapid Adaptation in an End-to-End Framework","display_name":"Generic Indic Text-to-Speech Synthesisers with Rapid Adaptation in an End-to-End Framework","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3035434165","doi":"https://doi.org/10.21437/interspeech.2020-2663","mag":"3035434165"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2663","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2663","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":"preprint","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.06971.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091337351","display_name":"Anusha Prakash","orcid":"https://orcid.org/0000-0001-7913-9336"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Anusha Prakash","raw_affiliation_strings":["Indian Institute of Technology Madras, Chennai, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032418366","display_name":"Hema A. Murthy","orcid":"https://orcid.org/0000-0003-3611-6550"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hema A. Murthy","raw_affiliation_strings":["Indian Institute of Technology Madras, Chennai, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5091337351"],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":0.14685955,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52900204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2962","last_page":"2966"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.996399998664856,"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":0.9923999905586243,"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":0.790602445602417},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6717627048492432},{"id":"https://openalex.org/keywords/phonotactics","display_name":"Phonotactics","score":0.6036325097084045},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5699634552001953},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5019829273223877},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4791238307952881},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44987526535987854},{"id":"https://openalex.org/keywords/language-family","display_name":"Language family","score":0.4469531774520874},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4282100796699524},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4059005677700043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38787713646888733},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18047520518302917},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17700603604316711},{"id":"https://openalex.org/keywords/phonology","display_name":"Phonology","score":0.1455172300338745},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0729106068611145}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.790602445602417},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6717627048492432},{"id":"https://openalex.org/C4768521","wikidata":"https://www.wikidata.org/wiki/Q512366","display_name":"Phonotactics","level":3,"score":0.6036325097084045},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5699634552001953},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5019829273223877},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4791238307952881},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44987526535987854},{"id":"https://openalex.org/C2780566098","wikidata":"https://www.wikidata.org/wiki/Q25295","display_name":"Language family","level":2,"score":0.4469531774520874},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4282100796699524},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4059005677700043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38787713646888733},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18047520518302917},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17700603604316711},{"id":"https://openalex.org/C148934300","wikidata":"https://www.wikidata.org/wiki/Q40998","display_name":"Phonology","level":2,"score":0.1455172300338745},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0729106068611145},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2020-2663","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2663","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"},{"id":"mag:3035434165","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2006.06971.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"doi:10.48550/arxiv.2006.06971","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2006.06971","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article-journal"}],"best_oa_location":{"id":"mag:3035434165","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2006.06971.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1995565802","https://openalex.org/W2093107730","https://openalex.org/W2107860279","https://openalex.org/W2767052532","https://openalex.org/W2949382160","https://openalex.org/W2953022181","https://openalex.org/W2963300588","https://openalex.org/W2964002616","https://openalex.org/W2972473628","https://openalex.org/W3015484365"],"related_works":["https://openalex.org/W3095877226","https://openalex.org/W2973034126","https://openalex.org/W2032928894","https://openalex.org/W2554000662","https://openalex.org/W3096656663","https://openalex.org/W2767634090","https://openalex.org/W3168177482","https://openalex.org/W3093383192","https://openalex.org/W201861410","https://openalex.org/W1496384140","https://openalex.org/W16930393","https://openalex.org/W3160713074","https://openalex.org/W83374769","https://openalex.org/W2044081012","https://openalex.org/W3135619128","https://openalex.org/W3025286576","https://openalex.org/W3181257032","https://openalex.org/W2188780386","https://openalex.org/W2342913127","https://openalex.org/W261816329"],"abstract_inverted_index":{"Building":[0],"text-to-speech":[1],"(TTS)":[2],"synthesisers":[3],"for":[4,122],"Indian":[5,19],"languages":[6,20,50,132],"is":[7,120,137,157,166],"a":[8,13,25,44,70,82,150,195],"difficult":[9],"task":[10],"owing":[11],"to":[12,42,81,146,181,194],"large":[14],"number":[15],"of":[16,28,68,72,92,109,118,128,161,178,192],"active":[17],"languages.":[18,75],"can":[21,102],"be":[22,103],"classified":[23],"into":[24],"finite":[26],"set":[27],"families,":[29],"prominent":[30],"among":[31],"them,":[32],"Indo-Aryan":[33],"and":[34,184],"Dravidian.":[35],"The":[36],"proposed":[37],"work":[38],"exploits":[39],"this":[40],"property":[41],"build":[43],"generic":[45,135,179],"TTS":[46,100],"system":[47],"using":[48,89,105],"multiple":[49],"from":[51],"the":[52,86,123,134,159,162,176,190],"same":[53,87],"family":[54,88],"in":[55,85,133,149],"an":[56],"end-to-end":[57],"framework.":[58],"Generic":[59],"systems":[60,77,101],"are":[61,66,78,141,170],"quite":[62,171],"robust":[63],"as":[64,143,173],"they":[65,174],"capable":[67],"capturing":[69],"variety":[71],"phonotactics":[73],"across":[74],"These":[76,168],"then":[79],"adapted":[80,124],"new":[83,196],"language":[84,185],"small":[90],"amounts":[91],"adaptation":[93,110,193],"data.":[94,111],"Experiments":[95],"indicate":[96,175],"that":[97,158],"good":[98],"quality":[99],"built":[104],"only":[106],"7":[107],"minutes":[108],"An":[112,154],"average":[113],"degradation":[114],"mean":[115],"opinion":[116],"score":[117],"3.98":[119],"obtained":[121],"TTSes.":[125],"Extensive":[126],"analysis":[127],"systematic":[129],"interactions":[130],"between":[131],"TTSes":[136,180],"carried":[138],"out.":[139],"x-vectors":[140],"included":[142],"speaker":[144,183],"embedding":[145],"synthesise":[147],"text":[148],"particular":[151],"speaker's":[152,164],"voice.":[153],"interesting":[155],"observation":[156],"prosody":[160],"target":[163],"voice":[165],"preserved.":[167],"results":[169],"promising":[172],"capability":[177],"handle":[182],"switching":[186],"seamlessly,":[187],"along":[188],"with":[189],"ease":[191],"language.":[197]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}