{"id":"https://openalex.org/W7126082349","doi":"https://doi.org/10.1007/978-3-032-15984-7_37","title":"The Impact of\u00a0Prosodic Segmentation on\u00a0Speech Synthesis of\u00a0Spontaneous Speech","display_name":"The Impact of\u00a0Prosodic Segmentation on\u00a0Speech Synthesis of\u00a0Spontaneous Speech","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7126082349","doi":"https://doi.org/10.1007/978-3-032-15984-7_37"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-032-15984-7_37","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-15984-7_37","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/978-3-032-15984-7_37","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124295744","display_name":"Julio Galdino","orcid":null},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Julio Galdino","raw_affiliation_strings":["University of S\u00e3o Paulo, S\u00e3o Carlos, SP, Brazil"],"raw_orcid":"https://orcid.org/0000-0001-6378-4648","affiliations":[{"raw_affiliation_string":"University of S\u00e3o Paulo, S\u00e3o Carlos, SP, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124154106","display_name":"Sidney Leal","orcid":null},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]},{"id":"https://openalex.org/I4210115983","display_name":"Versor Inova\u00e7\u00e3o Tecnol\u00f3gica (Brazil)","ror":"https://ror.org/024f41j50","country_code":"BR","type":"company","lineage":["https://openalex.org/I4210115983"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Sidney Leal","raw_affiliation_strings":["University of S\u00e3o Paulo, S\u00e3o Carlos, SP, Brazil","Venturus - Centro de Inova\u00e7\u00e3o Tecnol\u00f3gica, Campinas, SP, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-8817-2063","affiliations":[{"raw_affiliation_string":"University of S\u00e3o Paulo, S\u00e3o Carlos, SP, Brazil","institution_ids":["https://openalex.org/I17974374"]},{"raw_affiliation_string":"Venturus - Centro de Inova\u00e7\u00e3o Tecnol\u00f3gica, Campinas, SP, Brazil","institution_ids":["https://openalex.org/I4210115983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124281301","display_name":"Leticia de Souza","orcid":null},"institutions":[{"id":"https://openalex.org/I879563668","display_name":"Universidade Estadual Paulista (Unesp)","ror":"https://ror.org/00987cb86","country_code":"BR","type":"education","lineage":["https://openalex.org/I879563668"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Leticia de Souza","raw_affiliation_strings":["Universidade Estadual Paulista, S\u00e3o Jos\u00e9 do Rio Preto, SP, Brazil"],"raw_orcid":"https://orcid.org/0009-0009-7191-9296","affiliations":[{"raw_affiliation_string":"Universidade Estadual Paulista, S\u00e3o Jos\u00e9 do Rio Preto, SP, Brazil","institution_ids":["https://openalex.org/I879563668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124235722","display_name":"Rodrigo Lima","orcid":null},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Rodrigo Lima","raw_affiliation_strings":["University of S\u00e3o Paulo, S\u00e3o Carlos, SP, Brazil"],"raw_orcid":"https://orcid.org/0009-0009-4344-1109","affiliations":[{"raw_affiliation_string":"University of S\u00e3o Paulo, S\u00e3o Carlos, SP, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Antonio Moreira","orcid":"https://orcid.org/0009-0001-9867-3101"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Antonio Moreira","raw_affiliation_strings":["University of S\u00e3o Paulo, S\u00e3o Carlos, SP, Brazil"],"raw_orcid":"https://orcid.org/0009-0001-9867-3101","affiliations":[{"raw_affiliation_string":"University of S\u00e3o Paulo, S\u00e3o Carlos, SP, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122639861","display_name":"Arnaldo Candido Junior","orcid":null},"institutions":[{"id":"https://openalex.org/I879563668","display_name":"Universidade Estadual Paulista (Unesp)","ror":"https://ror.org/00987cb86","country_code":"BR","type":"education","lineage":["https://openalex.org/I879563668"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Arnaldo Candido","raw_affiliation_strings":["Universidade Estadual Paulista, S\u00e3o Jos\u00e9 do Rio Preto, SP, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-5647-0891","affiliations":[{"raw_affiliation_string":"Universidade Estadual Paulista, S\u00e3o Jos\u00e9 do Rio Preto, SP, Brazil","institution_ids":["https://openalex.org/I879563668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122568263","display_name":"Miguel Alexandre Pereira Pinto Noronha de Oliveira","orcid":null},"institutions":[{"id":"https://openalex.org/I79889768","display_name":"Universidade Federal de Alagoas","ror":"https://ror.org/00dna7t83","country_code":"BR","type":"education","lineage":["https://openalex.org/I79889768"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Miguel Oliveira","raw_affiliation_strings":["Universidade Federal de Alagoas, Macei\u00f3, AL, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-0866-0535","affiliations":[{"raw_affiliation_string":"Universidade Federal de Alagoas, Macei\u00f3, AL, Brazil","institution_ids":["https://openalex.org/I79889768"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025318789","display_name":"Edresson Casanova","orcid":"https://orcid.org/0000-0003-0160-7173"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Edresson Casanova","raw_affiliation_strings":["NVIDIA Corporation, S\u00e3o Paulo, SP, Brazil"],"raw_orcid":"https://orcid.org/0000-0003-0160-7173","affiliations":[{"raw_affiliation_string":"NVIDIA Corporation, S\u00e3o Paulo, SP, Brazil","institution_ids":["https://openalex.org/I4210127875","https://openalex.org/I1304085615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124161891","display_name":"Sandra Alu\u00edsio","orcid":null},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Sandra Alu\u00edsio","raw_affiliation_strings":["University of S\u00e3o Paulo, S\u00e3o Carlos, SP, Brazil"],"raw_orcid":"https://orcid.org/0000-0001-5108-2630","affiliations":[{"raw_affiliation_string":"University of S\u00e3o Paulo, S\u00e3o Carlos, SP, Brazil","institution_ids":["https://openalex.org/I17974374"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5124295744"],"corresponding_institution_ids":["https://openalex.org/I17974374"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.312749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"547","last_page":"561"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.6456999778747559,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.6456999778747559,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.13449999690055847,"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/T10863","display_name":"Voice and Speech Disorders","score":0.047200001776218414,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7930999994277954},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.762499988079071},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.7458999752998352},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.6202999949455261},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5202999711036682},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.47360000014305115},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.45910000801086426},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.38499999046325684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8378000259399414},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7930999994277954},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.762499988079071},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7458999752998352},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6919000148773193},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.6202999949455261},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5566999912261963},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5202999711036682},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.47360000014305115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4668999910354614},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.45910000801086426},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38499999046325684},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.37439998984336853},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.3456000089645386},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.34310001134872437},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.33899998664855957},{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.298799991607666},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2720000147819519}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-032-15984-7_37","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-15984-7_37","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-032-15984-7_37","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-15984-7_37","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4738328456878662,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W52922326","https://openalex.org/W2088160102","https://openalex.org/W2106564373","https://openalex.org/W3157237193","https://openalex.org/W4211032490","https://openalex.org/W4232760665","https://openalex.org/W4308599760","https://openalex.org/W4386058741","https://openalex.org/W4390912421","https://openalex.org/W4390926689","https://openalex.org/W4400165240","https://openalex.org/W4402112175","https://openalex.org/W4402112533","https://openalex.org/W4406461681","https://openalex.org/W4416036034","https://openalex.org/W4416037241"],"related_works":[],"abstract_inverted_index":{"Spontaneous":[0],"speech":[1,6,22,62,86],"presents":[2],"several":[3],"challenges":[4],"for":[5],"synthesis,":[7],"particularly":[8],"in":[9,29,79],"capturing":[10],"the":[11,49,70,83,142,148,175],"natural":[12,31,108,129,155],"flow":[13],"of":[14,51,72,85,132],"conversation,":[15],"including":[16],"turn-taking,":[17],"pauses,":[18],"and":[19,32,47,57,74,106,161,168],"disfluencies.":[20],"Although":[21,110],"synthesis":[23,63],"systems":[24],"have":[25],"made":[26],"significant":[27],"progress":[28],"generating":[30],"intelligible":[33,105],"speech,":[34],"primarily":[35],"through":[36],"architectures":[37],"that":[38,97,137],"implicitly":[39],"model":[40,150],"prosodic":[41,55,76,100,120,149],"features,":[42],"such":[43],"as":[44],"pitch,":[45],"intensity,":[46],"duration,":[48],"construction":[50],"datasets":[52],"with":[53,99,154],"explicit":[54],"segmentation":[56,77,101,112,121],"their":[58],"impact":[59],"on":[60,82],"spontaneous":[61],"remains":[64],"largely":[65],"unexplored.":[66],"This":[67],"paper":[68],"evaluates":[69],"effects":[71],"manual":[73,119],"automatic":[75,111],"annotations":[78],"Brazilian":[80],"Portuguese":[81],"quality":[84],"synthesized":[87],"by":[88],"a":[89],"non-autoregressive":[90],"model,":[91],"FastSpeech":[92],"2.":[93],"Experimental":[94],"results":[95],"show":[96],"training":[98,139],"produced":[102],"slightly":[103],"more":[104,116,128,152],"acoustically":[107],"speech.":[109],"tends":[113],"to":[114,127],"create":[115],"regular":[117],"segments,":[118],"introduces":[122],"greater":[123],"variability,":[124],"which":[125],"contributes":[126],"prosody.":[130],"Analysis":[131],"neutral":[133],"declarative":[134],"utterances":[135],"showed":[136],"both":[138],"approaches":[140],"reproduced":[141],"expected":[143],"nuclear":[144],"accent":[145],"pattern,":[146],"but":[147],"aligned":[151],"closely":[153],"pre-nuclear":[156],"contours.":[157],"To":[158],"support":[159],"reproducibility":[160],"future":[162],"research,":[163],"all":[164],"datasets,":[165],"source":[166],"codes,":[167],"trained":[169],"models":[170],"are":[171],"publicly":[172],"available":[173],"under":[174],"CC":[176],"BY-NC-ND":[177],"4.0":[178],"license.":[179]},"counts_by_year":[],"updated_date":"2026-02-01T03:34:12.195049","created_date":"2026-01-30T00:00:00"}
