{"id":"https://openalex.org/W3114532049","doi":"https://doi.org/10.1145/3430984.3431034","title":"Data-Efficient Training Strategies for Neural TTS Systems","display_name":"Data-Efficient Training Strategies for Neural TTS Systems","publication_year":2020,"publication_date":"2020-12-28","ids":{"openalex":"https://openalex.org/W3114532049","doi":"https://doi.org/10.1145/3430984.3431034","mag":"3114532049"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3430984.3431034","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5031415279","display_name":"K R Prajwal","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"K R Prajwal","raw_affiliation_strings":["IIIT Hyderabad"],"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053112307","display_name":"C. V. Jawahar","orcid":"https://orcid.org/0000-0001-6767-7057"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"C V Jawahar","raw_affiliation_strings":["IIIT Hyderabad"],"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.189,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.744604,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":86,"max":87},"biblio":{"volume":null,"issue":null,"first_page":"223","last_page":"227"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9999,"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":0.9999,"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":0.9994,"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/T10028","display_name":"Topic Modeling","score":0.9971,"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/training-set","display_name":"Training set","score":0.50479305}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.82977706},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.763131},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5567467},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5192947},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5115062},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.50479305},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.50218153},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.42030331},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37963036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37795582},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11145651},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.070750415},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3430984.3431034","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.62,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":11,"referenced_works":["https://openalex.org/W1980401417","https://openalex.org/W2404169761","https://openalex.org/W2427181987","https://openalex.org/W2914643958","https://openalex.org/W2963703197","https://openalex.org/W2964243274","https://openalex.org/W2972473628","https://openalex.org/W2987149083","https://openalex.org/W3095877226","https://openalex.org/W3115711567","https://openalex.org/W3201519611"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W40885451","https://openalex.org/W2946856121","https://openalex.org/W2535215250","https://openalex.org/W2433276473","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W1914543332","https://openalex.org/W1813881148","https://openalex.org/W1537411440"],"abstract_inverted_index":{"India":[0],"is":[1,52],"a":[2,12,25],"country":[3],"with":[4,83,117],"thousands":[5,134],"of":[6,41,59,87,122,135,144],"languages":[7,61,114],"and":[8,19,36,49,62,96,115,147],"dialects":[9],"spoken":[10],"across":[11,113,151],"billion-strong":[13],"population.":[14],"For":[15],"multi-lingual":[16,145],"content":[17],"creation":[18],"accessibility,":[20],"text-to-speech":[21],"systems":[22,33,82,105,155],"will":[23],"play":[24],"crucial":[26],"role.":[27],"However,":[28],"the":[29,56,88,127,133,142],"current":[30],"neural":[31,80,103,153],"TTS":[32,81,104,154],"are":[34],"data-hungry":[35],"need":[37],"about":[38,85],"20":[39],"hours":[40,121],"clean":[42],"single-speaker":[43],"speech":[44],"data":[45,89],"for":[46,55,129,156],"each":[47],"language":[48],"speaker.":[50],"This":[51],"not":[53],"scalable":[54],"large":[57],"number":[58],"Indian":[60,137,158],"dialects.":[63],"In":[64],"this":[65],"work,":[66],"we":[67],"demonstrate":[68],"three":[69],"simple,":[70],"yet":[71],"effective":[72],"pre-training":[73,146],"strategies":[74],"that":[75,100],"allow":[76],"us":[77],"to":[78,110,132],"train":[79],"just":[84],"one-tenth":[86],"needs":[90],"while":[91],"also":[92],"achieving":[93],"better":[94],"accuracy":[95],"naturalness.":[97],"We":[98,139],"show":[99],"such":[101],"pre-trained":[102],"can":[106],"be":[107],"quickly":[108],"adapted":[109],"different":[111],"speakers":[112],"genders":[116],"less":[118],"than":[119],"2":[120],"data,":[123],"thus":[124],"significantly":[125],"reducing":[126],"effort":[128],"future":[130],"expansions":[131],"rare":[136],"languages.":[138,159],"specifically":[140],"highlight":[141],"benefits":[143],"its":[148],"consistent":[149],"impact":[150],"our":[152],"8":[157]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3114532049","counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3}],"updated_date":"2025-01-05T18:41:22.424376","created_date":"2021-01-05"}