{"id":"https://openalex.org/W4372260289","doi":"https://doi.org/10.1109/icassp49357.2023.10096962","title":"Ensemble Prosody Prediction For Expressive Speech Synthesis","display_name":"Ensemble Prosody Prediction For Expressive Speech Synthesis","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260289","doi":"https://doi.org/10.1109/icassp49357.2023.10096962"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096962","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":"article","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/A5038517086","display_name":"Tian Huey Teh","orcid":null},"institutions":[{"id":"https://openalex.org/I2799766170","display_name":"Papworth Hospital","ror":"https://ror.org/05mqgrb58","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I2799766170","https://openalex.org/I4210104974"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Tian Huey Teh","raw_affiliation_strings":["Papercup Technologies Ltd.,United Kingdom","Papercup Technologies Ltd., United Kingdom"],"affiliations":[{"raw_affiliation_string":"Papercup Technologies Ltd.,United Kingdom","institution_ids":["https://openalex.org/I2799766170"]},{"raw_affiliation_string":"Papercup Technologies Ltd., United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017825726","display_name":"Vivian Hu","orcid":"https://orcid.org/0000-0002-5548-9283"},"institutions":[{"id":"https://openalex.org/I2799766170","display_name":"Papworth Hospital","ror":"https://ror.org/05mqgrb58","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I2799766170","https://openalex.org/I4210104974"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vivian Hu","raw_affiliation_strings":["Papercup Technologies Ltd.,United Kingdom","Papercup Technologies Ltd., United Kingdom"],"affiliations":[{"raw_affiliation_string":"Papercup Technologies Ltd.,United Kingdom","institution_ids":["https://openalex.org/I2799766170"]},{"raw_affiliation_string":"Papercup Technologies Ltd., United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024033876","display_name":"Devang S Ram Mohan","orcid":null},"institutions":[{"id":"https://openalex.org/I2799766170","display_name":"Papworth Hospital","ror":"https://ror.org/05mqgrb58","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I2799766170","https://openalex.org/I4210104974"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Devang S Ram Mohan","raw_affiliation_strings":["Papercup Technologies Ltd.,United Kingdom","Papercup Technologies Ltd., United Kingdom"],"affiliations":[{"raw_affiliation_string":"Papercup Technologies Ltd.,United Kingdom","institution_ids":["https://openalex.org/I2799766170"]},{"raw_affiliation_string":"Papercup Technologies Ltd., United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041839891","display_name":"Zack Hodari","orcid":null},"institutions":[{"id":"https://openalex.org/I2799766170","display_name":"Papworth Hospital","ror":"https://ror.org/05mqgrb58","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I2799766170","https://openalex.org/I4210104974"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zack Hodari","raw_affiliation_strings":["Papercup Technologies Ltd.,United Kingdom","Papercup Technologies Ltd., United Kingdom"],"affiliations":[{"raw_affiliation_string":"Papercup Technologies Ltd.,United Kingdom","institution_ids":["https://openalex.org/I2799766170"]},{"raw_affiliation_string":"Papercup Technologies Ltd., United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087090605","display_name":"Christopher G. R. Wallis","orcid":"https://orcid.org/0000-0001-7383-4186"},"institutions":[{"id":"https://openalex.org/I2799766170","display_name":"Papworth Hospital","ror":"https://ror.org/05mqgrb58","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I2799766170","https://openalex.org/I4210104974"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Christopher G. R. Wallis","raw_affiliation_strings":["Papercup Technologies Ltd.,United Kingdom","Papercup Technologies Ltd., United Kingdom"],"affiliations":[{"raw_affiliation_string":"Papercup Technologies Ltd.,United Kingdom","institution_ids":["https://openalex.org/I2799766170"]},{"raw_affiliation_string":"Papercup Technologies Ltd., United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018659206","display_name":"Tom\u00e1s G\u00f3mez Ibarrondo","orcid":null},"institutions":[{"id":"https://openalex.org/I2799766170","display_name":"Papworth Hospital","ror":"https://ror.org/05mqgrb58","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I2799766170","https://openalex.org/I4210104974"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tom\u00e1s G\u00f3mez Ibarrondo","raw_affiliation_strings":["Papercup Technologies Ltd.,United Kingdom","Papercup Technologies Ltd., United Kingdom"],"affiliations":[{"raw_affiliation_string":"Papercup Technologies Ltd.,United Kingdom","institution_ids":["https://openalex.org/I2799766170"]},{"raw_affiliation_string":"Papercup Technologies Ltd., United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083188961","display_name":"Alexandra Torresquintero","orcid":null},"institutions":[{"id":"https://openalex.org/I2799766170","display_name":"Papworth Hospital","ror":"https://ror.org/05mqgrb58","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I2799766170","https://openalex.org/I4210104974"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alexandra Torresquintero","raw_affiliation_strings":["Papercup Technologies Ltd.,United Kingdom","Papercup Technologies Ltd., United Kingdom"],"affiliations":[{"raw_affiliation_string":"Papercup Technologies Ltd.,United Kingdom","institution_ids":["https://openalex.org/I2799766170"]},{"raw_affiliation_string":"Papercup Technologies Ltd., United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044555381","display_name":"James Leoni","orcid":null},"institutions":[{"id":"https://openalex.org/I2799766170","display_name":"Papworth Hospital","ror":"https://ror.org/05mqgrb58","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I2799766170","https://openalex.org/I4210104974"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"James Leoni","raw_affiliation_strings":["Papercup Technologies Ltd.,United Kingdom","Papercup Technologies Ltd., United Kingdom"],"affiliations":[{"raw_affiliation_string":"Papercup Technologies Ltd.,United Kingdom","institution_ids":["https://openalex.org/I2799766170"]},{"raw_affiliation_string":"Papercup Technologies Ltd., United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219"},"institutions":[{"id":"https://openalex.org/I2799766170","display_name":"Papworth Hospital","ror":"https://ror.org/05mqgrb58","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I2799766170","https://openalex.org/I4210104974"]},{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark Gales","raw_affiliation_strings":["Papercup Technologies Ltd.,United Kingdom","University of Cambridge, United Kingdom","Papercup Technologies Ltd., United Kingdom"],"affiliations":[{"raw_affiliation_string":"Papercup Technologies Ltd.,United Kingdom","institution_ids":["https://openalex.org/I2799766170"]},{"raw_affiliation_string":"University of Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Papercup Technologies Ltd., United Kingdom","institution_ids":[]}]},{"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"]},{"id":"https://openalex.org/I2799766170","display_name":"Papworth Hospital","ror":"https://ror.org/05mqgrb58","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I2799766170","https://openalex.org/I4210104974"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["Papercup Technologies Ltd.,United Kingdom","Papercup Technologies Ltd., United Kingdom","University of Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Papercup Technologies Ltd.,United Kingdom","institution_ids":["https://openalex.org/I2799766170"]},{"raw_affiliation_string":"Papercup Technologies Ltd., United Kingdom","institution_ids":[]},{"raw_affiliation_string":"University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5038517086"],"corresponding_institution_ids":["https://openalex.org/I2799766170"],"apc_list":null,"apc_paid":null,"fwci":0.8741,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77873239,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"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":0.9993000030517578,"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":0.9986000061035156,"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":0.8707619905471802},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7725325226783752},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5691044330596924},{"id":"https://openalex.org/keywords/ensemble-forecasting","display_name":"Ensemble forecasting","score":0.5374048352241516},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5371665954589844},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5065485239028931},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.506543755531311},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5053896903991699},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.46112412214279175},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45190563797950745},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43227332830429077},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.42894691228866577}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8707619905471802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7725325226783752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5691044330596924},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.5374048352241516},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5371665954589844},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5065485239028931},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.506543755531311},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5053896903991699},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.46112412214279175},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45190563797950745},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43227332830429077},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.42894691228866577},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","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":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096962","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":[{"id":"https://metadata.un.org/sdg/4","score":0.5299999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W96472724","https://openalex.org/W173561343","https://openalex.org/W1904457459","https://openalex.org/W2000513720","https://openalex.org/W2949973225","https://openalex.org/W2964243274","https://openalex.org/W2972677740","https://openalex.org/W2973013313","https://openalex.org/W2982602185","https://openalex.org/W3026278778","https://openalex.org/W3033411150","https://openalex.org/W3097892637","https://openalex.org/W3102739662","https://openalex.org/W3150572638","https://openalex.org/W3196843885","https://openalex.org/W4221159457","https://openalex.org/W4226280312","https://openalex.org/W4286950013","https://openalex.org/W4296068797","https://openalex.org/W4298580827","https://openalex.org/W6607114211","https://openalex.org/W6748409065","https://openalex.org/W6778823374","https://openalex.org/W6802142237"],"related_works":["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","https://openalex.org/W1965141925"],"abstract_inverted_index":{"Generating":[0],"expressive":[1],"speech":[2],"with":[3,120],"rich":[4],"and":[5,100],"varied":[6],"prosody":[7,67,74,113],"continues":[8],"to":[9,24,66],"be":[10],"a":[11,98,109],"challenge":[12],"for":[13,43,57],"Text-to-Speech.":[14],"Most":[15],"efforts":[16],"have":[17],"focused":[18],"on":[19],"sophisticated":[20],"neural":[21],"architectures":[22],"intended":[23],"better":[25],"model":[26,40,79,82,128],"the":[27,88,91,121,130],"data":[28],"distribution.":[29],"Yet,":[30],"in":[31,90],"evaluations":[32],"it":[33],"is":[34,41],"generally":[35],"found":[36],"that":[37,51,107],"no":[38],"single":[39],"preferred":[42],"all":[44],"input":[45],"texts.":[46],"This":[47],"suggests":[48],"an":[49,59],"approach":[50],"has":[52],"rarely":[53],"been":[54],"used":[55],"before":[56],"Text-to-Speech:":[58],"ensemble":[60,64,92,111],"of":[61,73,112],"models.We":[62],"apply":[63],"learning":[65],"prediction.":[68],"We":[69,105],"construct":[70],"simple":[71],"ensembles":[72],"predictors":[75,114],"by":[76],"varying":[77],"either":[78],"architecture":[80],"or":[81],"parameter":[83],"values.To":[84],"automatically":[85],"select":[86],"amongst":[87],"models":[89],"when":[93],"performing":[94],"Text-to-Speech,":[95],"we":[96],"propose":[97],"novel,":[99],"computationally":[101],"trivial,":[102],"variance-based":[103],"criterion.":[104],"demonstrate":[106],"even":[108],"small":[110],"yields":[115],"useful":[116],"diversity,":[117],"which,":[118],"combined":[119],"proposed":[122],"selection":[123],"criterion,":[124],"outperforms":[125],"any":[126],"individual":[127],"from":[129],"ensemble.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}