{"id":"https://openalex.org/W2913512413","doi":"https://doi.org/10.1109/slt.2018.8639642","title":"Data Selection for Improving Naturalness of TTS Voices Trained on Small Found Corpuses","display_name":"Data Selection for Improving Naturalness of TTS Voices Trained on Small Found Corpuses","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2913512413","doi":"https://doi.org/10.1109/slt.2018.8639642","mag":"2913512413"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","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/A5052506993","display_name":"Fang-Yu Kuo","orcid":"https://orcid.org/0000-0001-8469-2937"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"F.-Y. Kuo","raw_affiliation_strings":["ObEN, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ObEN, Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036468647","display_name":"Sandesh Aryal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. Aryal","raw_affiliation_strings":["ObEN, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ObEN, Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028787670","display_name":"Gilles Degottex","orcid":"https://orcid.org/0000-0003-1346-9919"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"G. Degottex","raw_affiliation_strings":["ObEN, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ObEN, Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112519050","display_name":"Sam Seok Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. Kang","raw_affiliation_strings":["ObEN, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ObEN, Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003588321","display_name":"Pierre Lanchantin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"P. Lanchantin","raw_affiliation_strings":["ObEN, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ObEN, Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070531353","display_name":"Iris Chuoying Ouyang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"I. Ouyang","raw_affiliation_strings":["ObEN, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ObEN, Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3516,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.86407338,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"319","last_page":"324"},"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"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/naturalness","display_name":"Naturalness","score":0.990542471408844},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8033092617988586},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5907690525054932},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5737224817276001},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5722564458847046},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.5267131924629211},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5255780816078186},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5132501125335693},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.4595251679420471},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4550212323665619},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1790294647216797}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.990542471408844},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8033092617988586},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5907690525054932},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5737224817276001},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5722564458847046},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.5267131924629211},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5255780816078186},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5132501125335693},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.4595251679420471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4550212323665619},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1790294647216797},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2018.8639642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7699999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W10731371","https://openalex.org/W142887051","https://openalex.org/W203760253","https://openalex.org/W1480268964","https://openalex.org/W1516533146","https://openalex.org/W1517939602","https://openalex.org/W1586345832","https://openalex.org/W1588593315","https://openalex.org/W1975113979","https://openalex.org/W2011168910","https://openalex.org/W2015412875","https://openalex.org/W2102003408","https://openalex.org/W2137564956","https://openalex.org/W2143577772","https://openalex.org/W2145880678","https://openalex.org/W2165143604","https://openalex.org/W2177575896","https://openalex.org/W2181715383","https://openalex.org/W2250270880","https://openalex.org/W2250745814","https://openalex.org/W2289874485","https://openalex.org/W2293596383","https://openalex.org/W2296111744","https://openalex.org/W2402146185","https://openalex.org/W2471520273","https://openalex.org/W2483256596","https://openalex.org/W2527515520","https://openalex.org/W2598638573","https://openalex.org/W2749074593","https://openalex.org/W3023073374","https://openalex.org/W6600436803","https://openalex.org/W6605850914","https://openalex.org/W6630961876","https://openalex.org/W6630997582","https://openalex.org/W6634963458","https://openalex.org/W6675380101","https://openalex.org/W6685473641","https://openalex.org/W6685955031","https://openalex.org/W6691459416","https://openalex.org/W6691607309","https://openalex.org/W6697477453","https://openalex.org/W6712930963","https://openalex.org/W6776783807"],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W172797710","https://openalex.org/W3165080709","https://openalex.org/W2945105049","https://openalex.org/W2626699140","https://openalex.org/W2909357361","https://openalex.org/W4387098302","https://openalex.org/W4288365855","https://openalex.org/W2948317131","https://openalex.org/W2111961547"],"abstract_inverted_index":{"This":[0],"work":[1],"investigates":[2],"techniques":[3],"that":[4,39,59,73],"select":[5],"training":[6,37],"data":[7,38,83],"from":[8,55],"small,":[9],"found":[10],"corpuses":[11],"in":[12,25,63,112,118],"order":[13],"to":[14,31,86,91,107],"improve":[15],"the":[16,42,45,101,108,113],"naturalness":[17],"of":[18,36,44,65,82],"synthesized":[19],"text-to-speech":[20,88],"voices.":[21],"The":[22],"approach":[23],"outlined":[24],"this":[26],"paper":[27,114],"examines":[28],"different":[29,61],"metrics":[30,105],"detect":[32],"and":[33,69],"reject":[34],"segments":[35],"can":[40,84],"degrade":[41],"performance":[43],"system.":[46],"We":[47,71],"conducted":[48],"experiments":[49],"on":[50,100],"two":[51],"small":[52],"datasets":[53],"extracted":[54],"Mandarin":[56],"Chinese":[57],"audiobooks":[58],"have":[60],"characteristics":[62],"terms":[64],"recording":[66],"conditions,":[67],"narrator,":[68],"transcriptions.":[70],"show":[72],"using":[74],"a":[75,87,97],"even":[76],"smaller,":[77],"yet":[78],"carefully":[79],"selected,":[80],"set":[81],"lead":[85],"system":[89,98],"able":[90],"generate":[92],"more":[93],"natural":[94],"speech":[95],"than":[96],"trained":[99],"complete":[102],"dataset.":[103],"Three":[104],"related":[106],"narrator's":[109],"articulation":[110],"proposed":[111],"give":[115],"significant":[116],"improvements":[117],"naturalness.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}