{"id":"https://openalex.org/W3095877226","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":"2020-06-12","ids":{"openalex":"https://openalex.org/W3095877226","doi":"https://doi.org/10.21437/interspeech.2020-2663","mag":"3095877226"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2006.06971","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.06971","pdf_url":"https://arxiv.org/pdf/2006.06971","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":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.06971","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":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Prakash, Anusha","raw_affiliation_strings":["Dept of Electrical Engineering, Indian Institute of Technology Madras, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept of Electrical Engineering, Indian Institute of Technology Madras, 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":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Murthy, Hema A","raw_affiliation_strings":["Dept of Computer Science & Engineering, Indian Institute of Technology Madras, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept of Computer Science & Engineering, Indian Institute of Technology Madras, India","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5091337351"],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9977999925613403,"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":0.9970999956130981,"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":0.8151713013648987},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.638580858707428},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5782523155212402},{"id":"https://openalex.org/keywords/phonotactics","display_name":"Phonotactics","score":0.5701969265937805},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47542956471443176},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4630328416824341},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43448615074157715},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4253138303756714},{"id":"https://openalex.org/keywords/language-family","display_name":"Language family","score":0.42521756887435913},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.41935116052627563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.410084992647171},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3909580707550049},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.181916743516922},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15850505232810974},{"id":"https://openalex.org/keywords/phonology","display_name":"Phonology","score":0.14167627692222595},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07424736022949219}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8151713013648987},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.638580858707428},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5782523155212402},{"id":"https://openalex.org/C4768521","wikidata":"https://www.wikidata.org/wiki/Q512366","display_name":"Phonotactics","level":3,"score":0.5701969265937805},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47542956471443176},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4630328416824341},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43448615074157715},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4253138303756714},{"id":"https://openalex.org/C2780566098","wikidata":"https://www.wikidata.org/wiki/Q25295","display_name":"Language family","level":2,"score":0.42521756887435913},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.41935116052627563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.410084992647171},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3909580707550049},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.181916743516922},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15850505232810974},{"id":"https://openalex.org/C148934300","wikidata":"https://www.wikidata.org/wiki/Q40998","display_name":"Phonology","level":2,"score":0.14167627692222595},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07424736022949219},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2006.06971","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.06971","pdf_url":"https://arxiv.org/pdf/2006.06971","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2006.06971","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.06971","pdf_url":"https://arxiv.org/pdf/2006.06971","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":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7799999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1995565802","https://openalex.org/W2025638820","https://openalex.org/W2093107730","https://openalex.org/W2107860279","https://openalex.org/W2494654097","https://openalex.org/W2507136895","https://openalex.org/W2510374792","https://openalex.org/W2519091744","https://openalex.org/W2575483272","https://openalex.org/W2746132399","https://openalex.org/W2748488820","https://openalex.org/W2767052532","https://openalex.org/W2888922844","https://openalex.org/W2890964092","https://openalex.org/W2891730843","https://openalex.org/W2892140764","https://openalex.org/W2963300588","https://openalex.org/W2963609956","https://openalex.org/W2964002616","https://openalex.org/W2964243274","https://openalex.org/W2972473628","https://openalex.org/W2973213036","https://openalex.org/W3015484365","https://openalex.org/W3016160783"],"related_works":["https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3149582125","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W152045069","https://openalex.org/W652196294","https://openalex.org/W2368700418","https://openalex.org/W1965141925"],"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":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2020-11-09T00:00:00"}