{"id":"https://openalex.org/W3163003432","doi":"https://doi.org/10.1109/icassp39728.2021.9413604","title":"Prosodic Clustering for Phoneme-Level Prosody Control in End-to-End Speech Synthesis","display_name":"Prosodic Clustering for Phoneme-Level Prosody Control in End-to-End Speech Synthesis","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163003432","doi":"https://doi.org/10.1109/icassp39728.2021.9413604","mag":"3163003432"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413604","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2111.10177","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015840293","display_name":"Alexandra Vioni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandra Vioni","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061303593","display_name":"Myrsini Christidou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Myrsini Christidou","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052196585","display_name":"Nikolaos Ellinas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikolaos Ellinas","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022310876","display_name":"Georgios Vamvoukakis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georgios Vamvoukakis","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067728489","display_name":"Panos Kakoulidis","orcid":"https://orcid.org/0000-0003-2980-2528"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Panos Kakoulidis","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379045","display_name":"Taehoon Kim","orcid":"https://orcid.org/0000-0003-1819-968X"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Taehoon Kim","raw_affiliation_strings":["Mobile Communications Business, Samsung Electronics, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobile Communications Business, Samsung Electronics, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110947099","display_name":"June Sig Sung","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"June Sig Sung","raw_affiliation_strings":["Mobile Communications Business, Samsung Electronics, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobile Communications Business, Samsung Electronics, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006509336","display_name":"Hyoung-Min Park","orcid":"https://orcid.org/0000-0001-7397-8286"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyoungmin Park","raw_affiliation_strings":["Mobile Communications Business, Samsung Electronics, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobile Communications Business, Samsung Electronics, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108894078","display_name":"Aimilios Chalamandaris","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aimilios Chalamandaris","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027494724","display_name":"Pirros Tsiakoulis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pirros Tsiakoulis","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8396,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78281036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"15","issue":null,"first_page":"5719","last_page":"5723"},"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9984999895095825,"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/prosody","display_name":"Prosody","score":0.7643609046936035},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7519394755363464},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7288095951080322},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6127564907073975},{"id":"https://openalex.org/keywords/octave","display_name":"Octave (electronics)","score":0.5984205603599548},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5590841174125671},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5459293127059937},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5303678512573242},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.48174241185188293},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45533934235572815},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44455936551094055},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4301317036151886},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15373656153678894},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08075916767120361}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7643609046936035},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7519394755363464},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7288095951080322},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6127564907073975},{"id":"https://openalex.org/C85841341","wikidata":"https://www.wikidata.org/wiki/Q1135984","display_name":"Octave (electronics)","level":2,"score":0.5984205603599548},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5590841174125671},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5459293127059937},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5303678512573242},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.48174241185188293},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45533934235572815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44455936551094055},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4301317036151886},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15373656153678894},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08075916767120361},{"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413604","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"},{"id":"pmh:oai:arXiv.org:2111.10177","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.10177","pdf_url":"https://arxiv.org/pdf/2111.10177","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":"pmh:oai:arXiv.org:2111.10177","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.10177","pdf_url":"https://arxiv.org/pdf/2111.10177","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"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W1522301498","https://openalex.org/W1810943226","https://openalex.org/W2095705004","https://openalex.org/W2107831318","https://openalex.org/W2336378194","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2904459034","https://openalex.org/W2938102059","https://openalex.org/W2945544731","https://openalex.org/W2948211236","https://openalex.org/W2948238043","https://openalex.org/W2952269766","https://openalex.org/W2962970071","https://openalex.org/W2963091184","https://openalex.org/W2963272440","https://openalex.org/W2963568578","https://openalex.org/W2963609956","https://openalex.org/W2963927338","https://openalex.org/W2964121744","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2973158936","https://openalex.org/W2974194285","https://openalex.org/W2977311057","https://openalex.org/W2991417167","https://openalex.org/W2996573371","https://openalex.org/W3015440759","https://openalex.org/W3015922793","https://openalex.org/W3016021263","https://openalex.org/W3095389792","https://openalex.org/W3095459301","https://openalex.org/W3097892637","https://openalex.org/W3101882441","https://openalex.org/W4214968481","https://openalex.org/W4285719527","https://openalex.org/W4289383906","https://openalex.org/W4293714597","https://openalex.org/W4295731579","https://openalex.org/W4395958166","https://openalex.org/W6603616073","https://openalex.org/W6631190155","https://openalex.org/W6638273328","https://openalex.org/W6674330103","https://openalex.org/W6676245417","https://openalex.org/W6703356863","https://openalex.org/W6714142977","https://openalex.org/W6750489868","https://openalex.org/W6755300632","https://openalex.org/W6763100362","https://openalex.org/W6763316926","https://openalex.org/W6764068927","https://openalex.org/W6768443183","https://openalex.org/W6770943558","https://openalex.org/W6866227203"],"related_works":["https://openalex.org/W258725851","https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3149582125","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W152045069","https://openalex.org/W652196294","https://openalex.org/W2368700418"],"abstract_inverted_index":{"This":[0,69],"paper":[1],"presents":[2],"a":[3,26,61,89,93],"method":[4,103],"for":[5,66],"controlling":[6],"the":[7,10,42,46,76,83,86,101,105,121,128,135,140,143],"prosody":[8],"at":[9],"phoneme":[11,77],"level":[12],"in":[13,45,57,73,79],"an":[14],"autoregressive":[15],"attention-based":[16],"text-to-speech":[17],"system.":[18],"Instead":[19],"of":[20,63,88,108,115,142],"learning":[21],"latent":[22],"prosodic":[23,50,64,90],"features":[24,40],"with":[25,85,125],"variational":[27],"framework":[28],"as":[29],"is":[30,52,71],"commonly":[31],"done,":[32],"we":[33],"directly":[34],"extract":[35],"phoneme-level":[36,113],"F0":[37,116,122],"and":[38,92,117,137],"duration":[39],"from":[41],"speech":[43],"data":[44],"training":[47],"set.":[48],"Each":[49],"feature":[51],"discretized":[53],"using":[54],"unsupervised":[55],"clustering":[56],"order":[58,80],"to":[59,75,81],"produce":[60],"sequence":[62,70,78],"labels":[65],"each":[67],"utterance.":[68],"used":[72],"parallel":[74],"condition":[82],"decoder":[84],"utilization":[87],"encoder":[91],"corresponding":[94],"attention":[95],"module.":[96],"Experimental":[97],"results":[98],"show":[99],"that":[100],"proposed":[102],"retains":[104],"high":[106],"quality":[107],"generated":[109],"speech,":[110],"while":[111],"allowing":[112],"control":[114,133],"duration.":[118],"By":[119],"replacing":[120],"cluster":[123],"centroids":[124],"musical":[126],"notes,":[127],"model":[129],"can":[130],"also":[131],"provide":[132],"over":[134],"note":[136],"octave":[138],"within":[139],"range":[141],"speaker.":[144]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
