{"id":"https://openalex.org/W3208625370","doi":"https://doi.org/10.1109/sped53181.2021.9587411","title":"An analysis of the data efficiency in Tacotron2 speech synthesis system","display_name":"An analysis of the data efficiency in Tacotron2 speech synthesis system","publication_year":2021,"publication_date":"2021-10-13","ids":{"openalex":"https://openalex.org/W3208625370","doi":"https://doi.org/10.1109/sped53181.2021.9587411","mag":"3208625370"},"language":"en","primary_location":{"id":"doi:10.1109/sped53181.2021.9587411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped53181.2021.9587411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"},"type":"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/A5013743048","display_name":"Georgiana Saracu","orcid":null},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Georgiana Saracu","raw_affiliation_strings":["Technical University of Cluj-Napoca, Romania"],"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018126799","display_name":"Adriana Stan","orcid":"https://orcid.org/0000-0003-2894-5770"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Adriana Stan","raw_affiliation_strings":["Technical University of Cluj-Napoca, Romania"],"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5013743048"],"corresponding_institution_ids":["https://openalex.org/I158333966"],"apc_list":null,"apc_paid":null,"fwci":0.5439,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73222845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"45","issue":null,"first_page":"172","last_page":"176"},"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/T10028","display_name":"Topic Modeling","score":0.9922000169754028,"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":0.9919000267982483,"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":0.8504519462585449},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6931036710739136},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6160250902175903},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6076520085334778},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4897892475128174},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.46621257066726685},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.44110655784606934},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41731715202331543},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40066301822662354},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1808129847049713}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8504519462585449},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6931036710739136},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6160250902175903},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6076520085334778},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4897892475128174},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.46621257066726685},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.44110655784606934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41731715202331543},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40066301822662354},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1808129847049713},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sped53181.2021.9587411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped53181.2021.9587411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1836465849","https://openalex.org/W2120847449","https://openalex.org/W2131774270","https://openalex.org/W2148154194","https://openalex.org/W2519091744","https://openalex.org/W2738884019","https://openalex.org/W2769810959","https://openalex.org/W2819579046","https://openalex.org/W2949117887","https://openalex.org/W2963300588","https://openalex.org/W2963975282","https://openalex.org/W2964243274","https://openalex.org/W2991356003","https://openalex.org/W3015484365","https://openalex.org/W3015826515","https://openalex.org/W3025528898","https://openalex.org/W3034949308","https://openalex.org/W3149617007","https://openalex.org/W3150572638","https://openalex.org/W3196568361","https://openalex.org/W3197294703","https://openalex.org/W4294619240","https://openalex.org/W6623517193","https://openalex.org/W6638667902","https://openalex.org/W6741399199","https://openalex.org/W6753855596","https://openalex.org/W6755592152","https://openalex.org/W6778083308","https://openalex.org/W6793584814","https://openalex.org/W6800865813","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W4252942110","https://openalex.org/W1604114751","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W4391272374","https://openalex.org/W4400309480","https://openalex.org/W2549308614","https://openalex.org/W2081919107"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"an":[3,95],"evaluation":[4],"of":[5,8,30,56,79,97,105,118],"the":[6,12,28,31,77,80,84,98,106,111,116,138,147,151,153],"amount":[7],"data":[9,41,61,140,155],"required":[10],"by":[11,82],"Tacotron2":[13,112],"speech":[14,101,126],"synthesis":[15],"model":[16,32,68],"in":[17,38,150],"order":[18],"to":[19,33,35,62,144],"achieve":[20],"a":[21,65,70,119],"good":[22],"quality":[23,102],"output":[24],"synthesis.":[25],"We":[26,43,74],"evaluate":[27],"capabilities":[29],"adapt":[34],"new":[36],"speakers":[37,47],"very":[39],"limited":[40],"scenarios.":[42],"use":[44,59],"three":[45],"Romanian":[46],"for":[48],"which":[49],"we":[50],"gathered":[51],"at":[52,76],"most":[53],"5":[54],"minutes":[55],"speech,":[57],"and":[58,87,103],"this":[60],"fine":[63],"tune":[64],"large":[66],"pre-trained":[67],"over":[69],"few":[71],"training":[72,139],"epochs.":[73],"look":[75],"performance":[78],"system":[81],"evaluating":[83],"intelligibility,":[85],"naturalness":[86],"speaker":[88,120],"similarity":[89],"measures,":[90],"as":[91,93,122,124],"well":[92],"performing":[94],"analysis":[96],"trade-off":[99],"between":[100],"overfitting":[104],"network.The":[107],"results":[108],"show":[109],"that":[110,136],"network":[113],"can":[114,157],"replicate":[115],"identity":[117],"from":[121],"little":[123],"one":[125],"sample.":[127],"Also":[128],"it":[129],"inherently":[130],"learns":[131],"individual":[132],"grapheme":[133],"representations,":[134],"such":[135],"if":[137],"is":[141],"carefully":[142],"selected":[143],"present":[145],"all":[146],"common":[148],"graphemes":[149],"language,":[152],"adaptation":[154],"requirements":[156],"be":[158],"significantly":[159],"lowered.":[160]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}