{"id":"https://openalex.org/W3048768961","doi":"https://doi.org/10.1109/lsp.2020.3016564","title":"Modeling Prosodic Phrasing With Multi-Task Learning in Tacotron-Based TTS","display_name":"Modeling Prosodic Phrasing With Multi-Task Learning in Tacotron-Based TTS","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3048768961","doi":"https://doi.org/10.1109/lsp.2020.3016564","mag":"3048768961"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2020.3016564","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2020.3016564","pdf_url":"https://ieeexplore.ieee.org/ielx7/97/8966529/09166626.pdf","source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/97/8966529/09166626.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082746577","display_name":"Rui Liu","orcid":"https://orcid.org/0000-0003-4524-7413"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN","SG"],"is_corresponding":true,"raw_author_name":"Rui Liu","raw_affiliation_strings":["Department of Computer Science, Inner Mongolia University, Hohhot, China","National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001303929","display_name":"Berrak \u015ei\u015fman","orcid":"https://orcid.org/0000-0001-8078-3305"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Berrak Sisman","raw_affiliation_strings":["Information Systems Technology and Design (ISTD) Pillar, Singapore University of Technology and Design, Singapore"],"affiliations":[{"raw_affiliation_string":"Information Systems Technology and Design (ISTD) Pillar, Singapore University of Technology and Design, Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014372166","display_name":"Feilong Bao","orcid":"https://orcid.org/0000-0001-7312-1629"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feilong Bao","raw_affiliation_strings":["Department of Computer Science, Inner Mongolia University, Hohhot, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":["Department of Computer Science, Inner Mongolia University, Hohhot, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5082746577"],"corresponding_institution_ids":["https://openalex.org/I165932596","https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":2.5828,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.91725897,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"27","issue":null,"first_page":"1470","last_page":"1474"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.770551323890686},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7007878422737122},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6521438360214233},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5446069836616516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5439962148666382},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.5097624659538269},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.44070619344711304},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09527420997619629}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.770551323890686},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7007878422737122},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6521438360214233},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5446069836616516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5439962148666382},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.5097624659538269},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.44070619344711304},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09527420997619629},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2020.3016564","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2020.3016564","pdf_url":"https://ieeexplore.ieee.org/ielx7/97/8966529/09166626.pdf","source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2008.05284","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.05284","pdf_url":"https://arxiv.org/pdf/2008.05284","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1109/lsp.2020.3016564","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2020.3016564","pdf_url":"https://ieeexplore.ieee.org/ielx7/97/8966529/09166626.pdf","source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1094757534","display_name":null,"funder_award_id":"AISG-GC-2019-002","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G3070352347","display_name":null,"funder_award_id":"61773224","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3191157935","display_name":null,"funder_award_id":"AISG-100E-2018-006","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G3421629829","display_name":null,"funder_award_id":"RIE2020","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G4092667103","display_name":null,"funder_award_id":"A1687b0033","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G8219488318","display_name":null,"funder_award_id":"RIE2020","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G8332257624","display_name":null,"funder_award_id":"AISG-GC-2019-002","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324110","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3048768961.pdf","grobid_xml":"https://content.openalex.org/works/W3048768961.grobid-xml"},"referenced_works_count":65,"referenced_works":["https://openalex.org/W1499332833","https://openalex.org/W1604629200","https://openalex.org/W1614862348","https://openalex.org/W1993347555","https://openalex.org/W2025617415","https://openalex.org/W2102003408","https://openalex.org/W2106622015","https://openalex.org/W2111284386","https://openalex.org/W2120847449","https://openalex.org/W2365209858","https://openalex.org/W2404881427","https://openalex.org/W2526425061","https://openalex.org/W2604184139","https://openalex.org/W2742079690","https://openalex.org/W2755891984","https://openalex.org/W2786868129","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2795485067","https://openalex.org/W2804552794","https://openalex.org/W2885800352","https://openalex.org/W2888855092","https://openalex.org/W2889026195","https://openalex.org/W2889028433","https://openalex.org/W2889064624","https://openalex.org/W2889141918","https://openalex.org/W2907916773","https://openalex.org/W2911340057","https://openalex.org/W2913340405","https://openalex.org/W2936103087","https://openalex.org/W2941094131","https://openalex.org/W2944622002","https://openalex.org/W2962691331","https://openalex.org/W2963272440","https://openalex.org/W2963927338","https://openalex.org/W2963929654","https://openalex.org/W2963945466","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2972595148","https://openalex.org/W2972702018","https://openalex.org/W2972789651","https://openalex.org/W2972885185","https://openalex.org/W2973000405","https://openalex.org/W3015440759","https://openalex.org/W3016151052","https://openalex.org/W3025182306","https://openalex.org/W3209042722","https://openalex.org/W4295731579","https://openalex.org/W6675380101","https://openalex.org/W6676011374","https://openalex.org/W6713860685","https://openalex.org/W6736356763","https://openalex.org/W6741127994","https://openalex.org/W6744261651","https://openalex.org/W6748140763","https://openalex.org/W6750489868","https://openalex.org/W6753656201","https://openalex.org/W6757699683","https://openalex.org/W6758191806","https://openalex.org/W6768476578","https://openalex.org/W6770488218","https://openalex.org/W6773153034","https://openalex.org/W6773508076","https://openalex.org/W7025091378"],"related_works":["https://openalex.org/W1564680838","https://openalex.org/W2003125260","https://openalex.org/W2060591604","https://openalex.org/W2951720331","https://openalex.org/W1992291644","https://openalex.org/W2166791242","https://openalex.org/W2585162246","https://openalex.org/W1934413089","https://openalex.org/W2098419343","https://openalex.org/W2051178964"],"abstract_inverted_index":{"Tacotron-based":[0,39],"end-to-end":[1],"speech":[2,17,40],"synthesis":[3,41],"has":[4],"shown":[5],"remarkable":[6],"voice":[7,102],"quality.":[8],"However,":[9],"the":[10,15,38,46,61,77,101],"rendering":[11],"of":[12,80],"prosody":[13],"in":[14],"synthesized":[16],"remains":[18],"to":[19,43,63],"be":[20],"improved,":[21],"especially":[22],"for":[23,56,83,104],"long":[24],"sentences,":[25],"where":[26],"prosodic":[27,47,89],"phrasing":[28,90],"errors":[29],"can":[30],"occur":[31],"frequently.":[32],"In":[33],"this":[34,75],"letter,":[35],"we":[36],"extend":[37],"framework":[42],"explicitly":[44],"model":[45],"phrase":[48,69],"breaks.":[49,70],"We":[50],"propose":[51],"a":[52,88],"multi-task":[53,81],"learning":[54,82],"scheme":[55,98],"Tacotron":[57,84],"training,":[58],"that":[59,94],"optimizes":[60],"system":[62],"predict":[64],"both":[65,105],"Mel":[66],"spectrum":[67],"and":[68,107],"To":[71],"our":[72,95],"best":[73],"knowledge,":[74],"is":[76],"first":[78],"implementation":[79],"based":[85],"TTS":[86],"with":[87],"model.":[91],"Experiments":[92],"show":[93],"proposed":[96],"training":[97],"consistently":[99],"improves":[100],"quality":[103],"Chinese":[106],"Mongolian":[108],"systems.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}