{"id":"https://openalex.org/W2938102059","doi":"https://doi.org/10.1109/icassp.2019.8683827","title":"Phonemic-level Duration Control Using Attention Alignment for Natural Speech Synthesis","display_name":"Phonemic-level Duration Control Using Attention Alignment for Natural Speech Synthesis","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2938102059","doi":"https://doi.org/10.1109/icassp.2019.8683827","mag":"2938102059"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5046603228","display_name":"Jungbae Park","orcid":"https://orcid.org/0000-0003-4104-5857"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I181942792","display_name":"Humber Polytechnic","ror":"https://ror.org/05xv2md42","country_code":"CA","type":"education","lineage":["https://openalex.org/I181942792"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Jungbae Park","raw_affiliation_strings":["Humelo Inc","Korea Advanced Institute of Science and Technology (KAIST)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Humelo Inc","institution_ids":["https://openalex.org/I181942792"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST)","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058873797","display_name":"Kijong Han","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kijong Han","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST)","Korea Advanced Institute of Science and Technology KAIST,#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST)","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology KAIST,#TAB#","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005835733","display_name":"Yuneui Jeong","orcid":null},"institutions":[{"id":"https://openalex.org/I181942792","display_name":"Humber Polytechnic","ror":"https://ror.org/05xv2md42","country_code":"CA","type":"education","lineage":["https://openalex.org/I181942792"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yuneui Jeong","raw_affiliation_strings":["Humelo Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Humelo Inc","institution_ids":["https://openalex.org/I181942792"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075631319","display_name":"Sang Wan Lee","orcid":"https://orcid.org/0000-0001-6266-9613"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I181942792","display_name":"Humber Polytechnic","ror":"https://ror.org/05xv2md42","country_code":"CA","type":"education","lineage":["https://openalex.org/I181942792"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Sang Wan Lee","raw_affiliation_strings":["Humelo Inc","Korea Advanced Institute of Science and Technology (KAIST)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Humelo Inc","institution_ids":["https://openalex.org/I181942792"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST)","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5896","last_page":"5900"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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":0.9984999895095825,"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/duration","display_name":"Duration (music)","score":0.8010646104812622},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7913236618041992},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6332459449768066},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5585934519767761},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.504083514213562},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.48452848196029663},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4682387411594391},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3716413974761963}],"concepts":[{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.8010646104812622},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7913236618041992},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6332459449768066},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5585934519767761},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.504083514213562},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.48452848196029663},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4682387411594391},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3716413974761963},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1902237438","https://openalex.org/W1922655562","https://openalex.org/W2102003408","https://openalex.org/W2120847449","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2251701780","https://openalex.org/W2327501763","https://openalex.org/W2399979888","https://openalex.org/W2515943672","https://openalex.org/W2519091744","https://openalex.org/W2591927543","https://openalex.org/W2608207374","https://openalex.org/W2619368999","https://openalex.org/W2750077311","https://openalex.org/W2767052532","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2901997113","https://openalex.org/W2914049472","https://openalex.org/W2949382160","https://openalex.org/W2962902328","https://openalex.org/W2963609956","https://openalex.org/W2963691546","https://openalex.org/W2963712897","https://openalex.org/W2963782041","https://openalex.org/W2963927338","https://openalex.org/W2963971656","https://openalex.org/W2963975282","https://openalex.org/W2964243274","https://openalex.org/W2964308564","https://openalex.org/W4294619240","https://openalex.org/W4295731579","https://openalex.org/W4300416988","https://openalex.org/W6630875275","https://openalex.org/W6640090968","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6734815144","https://openalex.org/W6738277540","https://openalex.org/W6746700228","https://openalex.org/W6749489859","https://openalex.org/W6750489868","https://openalex.org/W6753855596","https://openalex.org/W6756197946","https://openalex.org/W6843615328","https://openalex.org/W6843673214","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W2333799855","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2580934630","https://openalex.org/W2038117447","https://openalex.org/W4307784074","https://openalex.org/W127416991"],"abstract_inverted_index":{"Recent":[0],"attention-based":[1],"end-to-end":[2,53],"speech":[3,71,166],"synthesis":[4,167],"from":[5],"text":[6],"systems":[7],"have":[8],"achieved":[9],"human-level":[10],"performance.":[11],"However,":[12],"many":[13],"approaches":[14],"cause":[15],"a":[16,42,51,63,85,132,159],"sequence-to-sequence":[17],"model":[18,112,143],"to":[19,31,57,90,107,113,179],"generate":[20],"only":[21],"averaged":[22],"results":[23],"of":[24,35,84,122,149,183],"the":[25,33,79,82,100,111,117,142,147,177,181],"input":[26],"text,":[27],"making":[28],"it":[29],"difficult":[30],"control":[32,48,116,180],"duration":[34,47,83,105,154,182],"utterance.":[36],"In":[37],"this":[38,59],"study,":[39],"we":[40,161],"present":[41],"novel":[43],"mechanism":[44],"for":[45],"phonemic-level":[46,153],"(PDC)":[49],"in":[50,55,152,185],"nearly":[52],"manner":[54],"order":[56],"solve":[58],"problem.":[60],"We":[61,124],"used":[62],"teacher":[64,133],"attention":[65,101],"alignment":[66,102,129,169],"generated":[67],"by":[68,78,103],"an":[69],"annotation":[70],"analyzer":[72],"program.":[73],"Our":[74],"method":[75],"is":[76,87],"inspired":[77],"idea":[80],"that":[81,127,163],"phoneme":[86],"highly":[88],"related":[89],"its":[91],"phonemic":[92,95,118],"features.":[93],"These":[94],"features":[96,121],"are":[97],"saved":[98],"on":[99],"adding":[104],"embedding":[106],"it.":[108],"This":[109],"enables":[110],"learn":[114],"and":[115,119,139],"rhythmic":[120],"speech.":[123],"also":[125],"show":[126,162],"providing":[128],"information":[130],"as":[131],"loss":[134,170],"term":[135],"improves":[136],"training":[137],"speed":[138,148],"notably,":[140],"makes":[141],"better":[144],"at":[145],"controlling":[146],"dramatic":[150],"change":[151],"with":[155,168,189],"subjective":[156],"demonstration.":[157],"As":[158],"result,":[160],"our":[164],"PDC":[165],"outperforms":[171],"other":[172],"baseline":[173],"methods":[174],"without":[175],"losing":[176],"ability":[178],"phonemes":[184],"extremely":[186],"adjusted":[187],"environments":[188],"faster":[190],"convergence.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}