{"id":"https://openalex.org/W4372270801","doi":"https://doi.org/10.1109/icassp49357.2023.10097200","title":"Prosody-Controllable Spontaneous TTS with Neural HMMS","display_name":"Prosody-Controllable Spontaneous TTS with Neural HMMS","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372270801","doi":"https://doi.org/10.1109/icassp49357.2023.10097200"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097200","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://kth.diva-portal.org/smash/get/diva2:1761460/FULLTEXT01","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090260243","display_name":"Harm Lameris","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Harm Lameris","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden","Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103054907","display_name":"Shivam Mehta","orcid":"https://orcid.org/0000-0002-1886-681X"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Shivam Mehta","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden","Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091432739","display_name":"Gustav Eje Henter","orcid":"https://orcid.org/0000-0002-1643-1054"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Gustav Eje Henter","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden","Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015417808","display_name":"Joakim Gustafson","orcid":"https://orcid.org/0000-0002-0397-6442"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Joakim Gustafson","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden","Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063795282","display_name":"\u00c9va Sz\u00e9kely","orcid":"https://orcid.org/0000-0003-1175-840X"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"\u00c9va Sz\u00e9kely","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden","Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Speech, Music and Hearing,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T12031","display_name":"Speech and dialogue systems","score":0.9980999827384949,"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":0.9969000220298767,"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":0.7934093475341797},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6785537004470825},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6682114005088806},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4741508364677429},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4070037603378296},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39559492468833923}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7934093475341797},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6785537004470825},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6682114005088806},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4741508364677429},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4070037603378296},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39559492468833923}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097200","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:DiVA.org:kth-327893","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-327893","pdf_url":"https://kth.diva-portal.org/smash/get/diva2:1761460/FULLTEXT01","source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:DiVA.org:kth-327893","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-327893","pdf_url":"https://kth.diva-portal.org/smash/get/diva2:1761460/FULLTEXT01","source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4300000071525574,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3102226089","display_name":null,"funder_award_id":"P20-0298","funder_id":"https://openalex.org/F4320322659","funder_display_name":"Riksbankens Jubileumsfond"}],"funders":[{"id":"https://openalex.org/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"},{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"},{"id":"https://openalex.org/F4320322659","display_name":"Riksbankens Jubileumsfond","ror":"https://ror.org/02jkbm893"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4372270801.pdf"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W2008741806","https://openalex.org/W2095176743","https://openalex.org/W2149730744","https://openalex.org/W2498127116","https://openalex.org/W2550497374","https://openalex.org/W2672179204","https://openalex.org/W2742149109","https://openalex.org/W2795109282","https://openalex.org/W2901285216","https://openalex.org/W2964140243","https://openalex.org/W2964243274","https://openalex.org/W2972606665","https://openalex.org/W2972746749","https://openalex.org/W2973177710","https://openalex.org/W2974194285","https://openalex.org/W3015440759","https://openalex.org/W3016151952","https://openalex.org/W3026874504","https://openalex.org/W3029933656","https://openalex.org/W3033411150","https://openalex.org/W3101882441","https://openalex.org/W3170320568","https://openalex.org/W3193828514","https://openalex.org/W3196843885","https://openalex.org/W3197824033","https://openalex.org/W3198332267","https://openalex.org/W3202098869","https://openalex.org/W4295731579","https://openalex.org/W4296069275","https://openalex.org/W6741822272","https://openalex.org/W6777694618","https://openalex.org/W6778823374"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Spontaneous":[0],"speech":[1,30,134],"has":[2],"many":[3],"affective":[4],"and":[5,11,25,34,61,104,126],"pragmatic":[6],"functions":[7],"that":[8,53,108,110],"are":[9],"interesting":[10],"challenging":[12],"to":[13,57,82],"model":[14],"in":[15,28,39,73],"TTS.":[16,47],"However,":[17],"the":[18,32,67,120,138],"presence":[19],"of":[20,69,92,122,141,145],"reduced":[21],"articulation,":[22],"fillers,":[23],"repetitions,":[24],"other":[26],"disfluencies":[27],"spontaneous":[29,74,97,133],"make":[31],"text":[33],"acoustics":[35],"less":[36],"aligned":[37],"than":[38],"read":[40],"speech,":[41],"which":[42,89],"is":[43,90],"problematic":[44],"for":[45,96,130],"attention-based":[46],"We":[48,99],"propose":[49],"a":[50],"TTS":[51,87],"architecture":[52],"can":[54],"rapidly":[55],"learn":[56],"speak":[58],"from":[59],"small":[60],"irregular":[62],"datasets,":[63],"while":[64],"also":[65],"reproducing":[66,131],"diversity":[68],"expressive":[70],"phenomena":[71],"present":[72],"speech.":[75,98],"Specifically,":[76],"we":[77,136],"add":[78],"utterance-level":[79],"prosody":[80,111,124],"control":[81,102,112,125],"an":[83],"existing":[84],"neural":[85],"HMM-based":[86],"system":[88],"capable":[91],"stable,":[93],"monotonic":[94],"alignments":[95],"objectively":[100],"evaluate":[101,137],"accuracy":[103],"perform":[105],"perceptual":[106],"tests":[107],"demonstrate":[109],"does":[113],"not":[114],"degrade":[115],"synthesis":[116],"quality.":[117],"To":[118],"exemplify":[119],"power":[121],"combining":[123],"ecologically":[127],"valid":[128],"data":[129],"intricate":[132],"phenomena,":[135],"system\u2019s":[139],"capability":[140],"synthesizing":[142],"two":[143],"types":[144],"creaky":[146],"voice.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}