{"id":"https://openalex.org/W3094650042","doi":"https://doi.org/10.21437/interspeech.2020-1361","title":"Speaking Speed Control of End-to-End Speech Synthesis Using Sentence-Level Conditioning","display_name":"Speaking Speed Control of End-to-End Speech Synthesis Using Sentence-Level Conditioning","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3094650042","doi":"https://doi.org/10.21437/interspeech.2020-1361","mag":"3094650042"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1361","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1361","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":"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/A5060429696","display_name":"Jae\u2010sung Bae","orcid":"https://orcid.org/0000-0002-8270-0072"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jae-Sung Bae","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046330926","display_name":"Hanbin Bae","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanbin Bae","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101800027","display_name":"Young-Sun Joo","orcid":"https://orcid.org/0000-0002-7428-5868"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Young-Sun Joo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043151268","display_name":"Junmo Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junmo Lee","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049034341","display_name":"Gyeong-Hoon Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gyeong-Hoon Lee","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5052468556","display_name":"Hoon Young Cho","orcid":"https://orcid.org/0000-0002-6850-6580"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hoon-Young Cho","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5060429696"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7233,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.87847157,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4402","last_page":"4406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9930999875068665,"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":0.9930999875068665,"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":0.9927999973297119,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9362999796867371,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.8344713449478149},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6420976519584656},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5373780727386475},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5204085111618042},{"id":"https://openalex.org/keywords/conditioning","display_name":"Conditioning","score":0.4972362816333771},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4969189465045929},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.29695403575897217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2964720129966736},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10423484444618225}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8344713449478149},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6420976519584656},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5373780727386475},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5204085111618042},{"id":"https://openalex.org/C45262634","wikidata":"https://www.wikidata.org/wiki/Q5159291","display_name":"Conditioning","level":2,"score":0.4972362816333771},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4969189465045929},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29695403575897217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2964720129966736},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10423484444618225},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1361","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1361","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W2344176346","https://openalex.org/W2052307325","https://openalex.org/W1489675464","https://openalex.org/W1881653995","https://openalex.org/W2151749779","https://openalex.org/W1999612375","https://openalex.org/W2365635896","https://openalex.org/W2062287200","https://openalex.org/W2938107654"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3],"controllable":[4],"end-to-end":[5,109],"text-to-speech":[6],"(TTS)":[7],"system":[8,50,60],"to":[9,39,51,98],"control":[10,52,62,135],"the":[11,31,34,40,48,53,57,63,73,77,124,143,147,152],"speaking":[12,54,64],"speed":[13,65],"(speed-controllable":[14],"TTS;":[15],"SCTTS)":[16],"of":[17,33,36,42,154],"synthesized":[18],"speech":[19,69,96,121,130],"with":[20],"sentence-level":[21],"speaking-rate":[22,29],"value":[23],"as":[24,72],"an":[25,94,108],"additional":[26,90],"input.":[27],"The":[28,83],"value,":[30],"ratio":[32],"number":[35],"input":[37,43],"phonemes":[38],"length":[41],"speech,":[44],"is":[45],"adopted":[46],"in":[47,107,151],"proposed":[49,58,84],"speed.":[55],"Furthermore,":[56],"SCTTS":[59,85,125],"can":[61,104,126],"while":[66],"retaining":[67],"other":[68,132],"attributes,":[70],"such":[71],"pitch,":[74],"by":[75],"adopting":[76],"global":[78],"style":[79,81],"token-based":[80],"encoder.":[82],"does":[86],"not":[87],"require":[88],"any":[89],"well-trained":[91],"model":[92],"or":[93,139],"external":[95],"database":[97],"extract":[99],"phoneme-level":[100],"duration":[101,134,141],"information":[102],"and":[103,119],"be":[105],"trained":[106],"manner.":[110],"In":[111],"addition,":[112],"our":[113],"listening":[114],"tests":[115],"on":[116],"fast-,":[117],"normal-,":[118],"slow-speed":[120,155],"showed":[122],"that":[123],"generate":[127],"more":[128],"natural":[129],"than":[131],"phoneme":[133],"approaches":[136],"which":[137],"increase":[138],"decrease":[140],"at":[142],"same":[144],"rate":[145],"for":[146],"entire":[148],"sentence,":[149],"especially":[150],"case":[153],"speech.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}