{"id":"https://openalex.org/W4375868833","doi":"https://doi.org/10.1109/icassp49357.2023.10095131","title":"Do Prosody Transfer Models Transfer Prosody?","display_name":"Do Prosody Transfer Models Transfer Prosody?","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868833","doi":"https://doi.org/10.1109/icassp49357.2023.10095131"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095131","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070862331","display_name":"Atli Thor Sigurgeirsson","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Atli Thor Sigurgeirsson","raw_affiliation_strings":["University of Edinburgh,The Centre for Speech Technology Research,UK","The Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,The Centre for Speech Technology Research,UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["University of Edinburgh,The Centre for Speech Technology Research,UK","The Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,The Centre for Speech Technology Research,UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","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/T12031","display_name":"Speech and dialogue systems","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.9609625339508057},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.8765040040016174},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7163879871368408},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6142609119415283},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5527066588401794},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5426247119903564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5349472761154175},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.41845810413360596}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9609625339508057},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8765040040016174},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7163879871368408},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6142609119415283},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5527066588401794},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5426247119903564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5349472761154175},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.41845810413360596},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095131","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1882958252","https://openalex.org/W2000633092","https://openalex.org/W2011976355","https://openalex.org/W2069859485","https://openalex.org/W2107860279","https://openalex.org/W2130086727","https://openalex.org/W2406982350","https://openalex.org/W2619368999","https://openalex.org/W2747874407","https://openalex.org/W2760103357","https://openalex.org/W2794490148","https://openalex.org/W2901997113","https://openalex.org/W2904459034","https://openalex.org/W2922232786","https://openalex.org/W2948238043","https://openalex.org/W2962691331","https://openalex.org/W2962723986","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2973158936","https://openalex.org/W3022876224","https://openalex.org/W3025528898","https://openalex.org/W3033411150","https://openalex.org/W3092028330","https://openalex.org/W3188160682","https://openalex.org/W4295731579","https://openalex.org/W6639480849","https://openalex.org/W6749555683","https://openalex.org/W6750489868","https://openalex.org/W6751281049","https://openalex.org/W6756197946","https://openalex.org/W6765987481","https://openalex.org/W6778083308","https://openalex.org/W6778823374","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W2562096895","https://openalex.org/W2333799855","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W4214652783","https://openalex.org/W258725851","https://openalex.org/W4307784074"],"abstract_inverted_index":{"Some":[0],"recent":[1],"models":[2,55,162],"for":[3],"Text-to-Speech":[4],"synthesis":[5],"aim":[6],"to":[7,15,36,47,59,79,96,98,123],"transfer":[8,60,99,113,117,161],"the":[9,16,30,42,48,68,94,104,127,148,182],"prosody":[10,61,112,118,160],"of":[11,29,169],"a":[12,26,63,81,135,152,166,173],"reference":[13,31,43,64,105,183,186],"utterance":[14,44,85,150],"generated":[17],"target":[18,49,107,149],"synthetic":[19],"speech.":[20],"This":[21],"is":[22,34,45,177],"done":[23],"by":[24],"using":[25,147],"learned":[27],"embedding":[28],"utterance,":[32],"which":[33,176],"used":[35,58],"condition":[37],"speech":[38],"generation.":[39],"During":[40],"training,":[41],"identical":[46],"utterance.":[50],"Yet,":[51],"during":[52,86],"synthesis,":[53],"these":[54,139],"are":[56],"often":[57],"from":[62,67],"that":[65,103,134,159],"differs":[66],"text":[69],"or":[70],"speaker":[71,184],"being":[72],"synthesized.To":[73],"address":[74],"this":[75,91],"inconsistency,":[76],"we":[77,129,157],"propose":[78],"use":[80],"different,":[82],"but":[83,171],"prosodically-related,":[84],"training":[87],"too.":[88],"We":[89],"believe":[90],"should":[92,120],"encourage":[93],"model":[95,136],"learn":[97,165],"only":[100],"those":[101],"characteristics":[102],"and":[106,185],"have":[108],"in":[109,126],"common.":[110],"If":[111],"methods":[114],"do":[115,163],"indeed":[116],"they":[119],"be":[121,124],"able":[122],"trained":[125,137,146],"way":[128],"propose.":[130],"However,":[131],"results":[132],"show":[133],"under":[138],"conditions":[140],"performs":[141],"significantly":[142],"worse":[143],"than":[144],"one":[145],"as":[151],"reference.":[153],"To":[154],"explain":[155],"this,":[156],"hypothesize":[158],"not":[164],"transferable":[167],"representation":[168,175],"prosody,":[170],"rather":[172],"utterance-level":[174],"highly":[178],"dependent":[179],"on":[180],"both":[181],"text.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2023-05-10T00:00:00"}