{"id":"https://openalex.org/W3160844600","doi":"https://doi.org/10.1109/icassp39728.2021.9414720","title":"Improving Naturalness and Controllability of Sequence-to-Sequence Speech Synthesis by Learning Local Prosody Representations","display_name":"Improving Naturalness and Controllability of Sequence-to-Sequence Speech Synthesis by Learning Local Prosody Representations","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160844600","doi":"https://doi.org/10.1109/icassp39728.2021.9414720","mag":"3160844600"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5107748760","display_name":"Gong Cheng","orcid":"https://orcid.org/0009-0004-0272-3541"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Cheng Gong","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, P.R.China"],"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, P.R.China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101745213","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-8094-6861"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, P.R.China"],"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, P.R.China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhua Ling","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000235693","display_name":"Shaotong Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaotong Guo","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, P.R.China"],"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, P.R.China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101768584","display_name":"Zhang Ju","orcid":"https://orcid.org/0000-0001-5380-2072"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ju Zhang","raw_affiliation_strings":["Huiyan Technology (Tianjin) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Huiyan Technology (Tianjin) Co., Ltd","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017251198","display_name":"Jianwu Dang","orcid":"https://orcid.org/0000-0002-9237-4821"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]},{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Jianwu Dang","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Ishikawa, Japan","Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, P.R.China"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, P.R.China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5107748760"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":1.2189,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.7851927,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5724","last_page":"5728"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7973155975341797},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7304694056510925},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7100569009780884},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7038649916648865},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6946844458580017},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.5288729667663574},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5189452171325684},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.4947511553764343},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.48651403188705444},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.45310303568840027},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4320247769355774},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4226731061935425},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4104064106941223},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13605016469955444},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.08615747094154358}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7973155975341797},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7304694056510925},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7100569009780884},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7038649916648865},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6946844458580017},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.5288729667663574},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5189452171325684},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.4947511553764343},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.48651403188705444},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.45310303568840027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4320247769355774},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4226731061935425},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4104064106941223},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13605016469955444},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.08615747094154358},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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":0.5699999928474426}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2091425152","https://openalex.org/W2242818861","https://openalex.org/W2519091744","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2885800352","https://openalex.org/W2935711438","https://openalex.org/W2945544731","https://openalex.org/W2952269766","https://openalex.org/W2962691331","https://openalex.org/W2963091184","https://openalex.org/W2963272440","https://openalex.org/W2963609956","https://openalex.org/W2963927338","https://openalex.org/W2963945466","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2972849140","https://openalex.org/W3010916717","https://openalex.org/W3015419784","https://openalex.org/W3015440759","https://openalex.org/W3016007107","https://openalex.org/W3016021263","https://openalex.org/W3086296097","https://openalex.org/W3094917204","https://openalex.org/W3097892637","https://openalex.org/W3100270690","https://openalex.org/W3125709657","https://openalex.org/W4295731579","https://openalex.org/W6690026940","https://openalex.org/W6736996214","https://openalex.org/W6750489868","https://openalex.org/W6762643587"],"related_works":["https://openalex.org/W4392904630","https://openalex.org/W169399214","https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W2108985546","https://openalex.org/W2081919107"],"abstract_inverted_index":{"State-of-the-art":[0],"neural":[1],"text-to-speech":[2],"(TTS)":[3],"networks":[4],"are":[5],"trained":[6],"with":[7,23,72,91],"a":[8,73],"large":[9],"amount":[10],"of":[11,19,31,113,120],"speech":[12,21,34,116],"data,":[13],"which":[14,53],"significantly":[15],"improves":[16],"the":[17,27,32,43,50,61,83,96,106,111,114,146],"quality":[18,112],"synthetic":[20],"compared":[22],"traditional":[24,92],"approaches.":[25],"However,":[26],"prosody":[28,45],"and":[29],"controllability":[30],"generated":[33,44,115],"is":[35,46,88],"still":[36],"insufficient,":[37],"especially":[38],"in":[39],"tonal":[40],"languages.":[41],"Moreover,":[42,124],"solely":[47],"defined":[48],"by":[49,137],"input":[51],"text,":[52],"does":[54],"not":[55],"allow":[56],"for":[57,60],"different":[58],"styles":[59],"same":[62],"sentence":[63],"or":[64],"words.":[65],"In":[66],"this":[67],"study,":[68],"we":[69,125,128],"extended":[70],"Tacotron2":[71],"pitch":[74,133],"prediction":[75],"task":[76],"to":[77,98,145],"capture":[78],"discrete":[79],"pitch-related":[80,85,140],"representations.":[81],"Specifically,":[82],"learned":[84],"suprasegmental":[86],"information":[87],"fed":[89],"simultaneously":[90],"character":[93],"features":[94],"into":[95],"decoder":[97,147],"generate":[99],"final":[100],"Mel":[101],"spectrogram.":[102],"Experiments":[103],"show":[104],"that":[105,127],"proposed":[107],"method":[108],"can":[109,129],"improve":[110],"(mean":[117],"opinion":[118],"score":[119],"4.37":[121],"vs.":[122],"4.22).":[123],"demonstrated":[126],"easily":[130],"achieve":[131],"word-level":[132],"control":[134],"during":[135],"generation":[136],"changing":[138],"local":[139],"representations":[141],"before":[142],"passing":[143],"them":[144],"network.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}