{"id":"https://openalex.org/W4318620573","doi":"https://doi.org/10.48550/arxiv.2301.11446","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":"2023-01-26","ids":{"openalex":"https://openalex.org/W4318620573","doi":"https://doi.org/10.48550/arxiv.2301.11446"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2301.11446","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.11446","pdf_url":"https://arxiv.org/pdf/2301.11446","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2301.11446","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047648376","display_name":"Mikolaj Babianski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Babianski, Mikolaj","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"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":"Pokora, Kamil","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089445018","display_name":"Raahil Shah","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shah, Raahil","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016102002","display_name":"Rafa\u0142 Sienkiewicz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sienkiewicz, Rafal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"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":"Korzekwa, Daniel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5026578737","display_name":"Viacheslav Klimkov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Klimkov, Viacheslav","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9911999702453613,"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":0.9829000234603882,"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":0.7392669320106506},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7088534235954285},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6886469125747681},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6456105709075928},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6184951066970825},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5647493600845337},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5621328353881836},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5054192543029785},{"id":"https://openalex.org/keywords/predictability","display_name":"Predictability","score":0.4986410140991211},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48882362246513367},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.427230566740036},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3929063081741333},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09402617812156677}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7392669320106506},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7088534235954285},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6886469125747681},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6456105709075928},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6184951066970825},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5647493600845337},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5621328353881836},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5054192543029785},{"id":"https://openalex.org/C197640229","wikidata":"https://www.wikidata.org/wiki/Q2534066","display_name":"Predictability","level":2,"score":0.4986410140991211},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48882362246513367},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.427230566740036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3929063081741333},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09402617812156677},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2301.11446","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.11446","pdf_url":"https://arxiv.org/pdf/2301.11446","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},{"id":"doi:10.48550/arxiv.2301.11446","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2301.11446","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2301.11446","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.11446","pdf_url":"https://arxiv.org/pdf/2301.11446","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"score":0.6499999761581421,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4318620573.pdf","grobid_xml":"https://content.openalex.org/works/W4318620573.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W169399214","https://openalex.org/W4252942110","https://openalex.org/W1604114751","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W258725851","https://openalex.org/W2081919107","https://openalex.org/W1984347656"],"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":2025,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}