{"id":"https://openalex.org/W4319862228","doi":"https://doi.org/10.1109/slt54892.2023.10022793","title":"On Granularity of Prosodic Representations in Expressive Text-to-Speech","display_name":"On Granularity of Prosodic Representations in Expressive Text-to-Speech","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862228","doi":"https://doi.org/10.1109/slt54892.2023.10022793"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022793","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022793","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5047648376","display_name":"Mikolaj Babianski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mikolaj Babianski","raw_affiliation_strings":["Amazon Text-to-Speech Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Text-to-Speech Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000904701","display_name":"Kamil Pokora","orcid":"https://orcid.org/0009-0006-0756-4118"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kamil Pokora","raw_affiliation_strings":["Amazon Text-to-Speech Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Text-to-Speech Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089445018","display_name":"Raahil Shah","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raahil Shah","raw_affiliation_strings":["Amazon Text-to-Speech Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Text-to-Speech Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016102002","display_name":"Rafa\u0142 Sienkiewicz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rafal Sienkiewicz","raw_affiliation_strings":["Amazon Text-to-Speech Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Text-to-Speech Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039620116","display_name":"Daniel Korzekwa","orcid":"https://orcid.org/0000-0003-1470-4968"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Korzekwa","raw_affiliation_strings":["Amazon Text-to-Speech Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Text-to-Speech Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026578737","display_name":"Viacheslav Klimkov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Viacheslav Klimkov","raw_affiliation_strings":["Amazon Text-to-Speech Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Text-to-Speech Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3067,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81363979,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"892","last_page":"899"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987000226974487,"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":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.7597768902778625},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6972915530204773},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6957181096076965},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6412242650985718},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6302125453948975},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6169993877410889},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5630283951759338},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5461803674697876},{"id":"https://openalex.org/keywords/predictability","display_name":"Predictability","score":0.49466297030448914},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47076132893562317},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4172763526439667},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10547345876693726}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7597768902778625},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6972915530204773},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6957181096076965},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6412242650985718},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6302125453948975},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6169993877410889},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5630283951759338},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5461803674697876},{"id":"https://openalex.org/C197640229","wikidata":"https://www.wikidata.org/wiki/Q2534066","display_name":"Predictability","level":2,"score":0.49466297030448914},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47076132893562317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4172763526439667},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10547345876693726},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022793","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022793","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6499999761581421,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2102003408","https://openalex.org/W2107223151","https://openalex.org/W2116046013","https://openalex.org/W2129142580","https://openalex.org/W2519091744","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2885800352","https://openalex.org/W2896457183","https://openalex.org/W2904459034","https://openalex.org/W2941649920","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2972702018","https://openalex.org/W2972951102","https://openalex.org/W2973158936","https://openalex.org/W3015922793","https://openalex.org/W3022876224","https://openalex.org/W3033411150","https://openalex.org/W3091928890","https://openalex.org/W3098557217","https://openalex.org/W3161113899","https://openalex.org/W3161296985","https://openalex.org/W3161732385","https://openalex.org/W3162770051","https://openalex.org/W3194822862","https://openalex.org/W3195171908","https://openalex.org/W3198020407","https://openalex.org/W3200540417","https://openalex.org/W4221159457","https://openalex.org/W4221167022","https://openalex.org/W4295731579","https://openalex.org/W4296069283","https://openalex.org/W4395957972","https://openalex.org/W6631362777","https://openalex.org/W6677333272","https://openalex.org/W6750489868","https://openalex.org/W6755207826","https://openalex.org/W6778823374","https://openalex.org/W6784545093","https://openalex.org/W6803425590"],"related_works":["https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W4214652783","https://openalex.org/W1604114751","https://openalex.org/W2032941915","https://openalex.org/W3100825170","https://openalex.org/W258725851","https://openalex.org/W2075706796","https://openalex.org/W2549308614","https://openalex.org/W3018584924"],"abstract_inverted_index":{"In":[0],"expressive":[1],"speech":[2,117],"synthesis":[3],"it":[4],"is":[5,31],"widely":[6],"adopted":[7],"to":[8,13,26,54,89],"use":[9],"latent":[10],"prosody":[11],"representations":[12,44,97],"deal":[14],"with":[15],"variability":[16],"of":[17,70],"the":[18,109],"data":[19],"during":[20],"training.":[21],"Same":[22],"text":[23],"may":[24],"correspond":[25],"various":[27],"acoustic":[28],"realizations,":[29],"which":[30],"known":[32],"as":[33],"a":[34,105],"one-to-many":[35],"mapping":[36],"problem":[37],"in":[38,50,111],"text-to-speech.":[39],"Utterance,":[40],"word,":[41],"or":[42],"phoneme-level":[43,87],"are":[45],"extracted":[46],"from":[47,76,94],"target":[48],"signal":[49],"an":[51],"auto-encoding":[52],"setup,":[53],"complement":[55],"phonetic":[56],"input":[57],"and":[58,72,86,102,118],"simplify":[59],"that":[60,80],"mapping.":[61],"This":[62],"paper":[63],"compares":[64],"prosodic":[65],"embeddings":[66,82],"at":[67],"different":[68],"levels":[69],"granularity":[71],"examines":[73],"their":[74],"prediction":[75],"text.":[77,95],"We":[78],"show":[79],"utterance-level":[81],"have":[83],"insufficient":[84],"capacity":[85,101],"tend":[88],"introduce":[90],"instabilities":[91],"when":[92],"predicted":[93],"Word-level":[96],"impose":[98],"balance":[99],"between":[100,115],"predictability.":[103],"As":[104],"result,":[106],"we":[107],"close":[108],"gap":[110],"naturalness":[112],"by":[113],"90%":[114],"synthetic":[116],"recordings":[119],"on":[120],"LibriTTS":[121],"dataset,":[122],"without":[123],"sacrificing":[124],"intelligibility.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}