{"id":"https://openalex.org/W4413221907","doi":"https://doi.org/10.1145/3749644","title":"Enhanced Prosody Modeling and Character Voice Controlling for Audiobook Speech Synthesis","display_name":"Enhanced Prosody Modeling and Character Voice Controlling for Audiobook Speech Synthesis","publication_year":2025,"publication_date":"2025-08-11","ids":{"openalex":"https://openalex.org/W4413221907","doi":"https://doi.org/10.1145/3749644"},"language":"en","primary_location":{"id":"doi:10.1145/3749644","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3749644","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-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/A5082235402","display_name":"Ning-Qian Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning-Qian Wu","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China","National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0008-5102-1182","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China","National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-7853-5273","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.396,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85386401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"24","issue":"10","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9937000274658203,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9904999732971191,"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/prosody","display_name":"Prosody","score":0.8712146878242493},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.830842137336731},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7205338478088379},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6970285773277283},{"id":"https://openalex.org/keywords/chinese-speech-synthesis","display_name":"Chinese speech synthesis","score":0.6278636455535889},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5717864632606506},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.511716365814209},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43302056193351746},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.43213173747062683},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4234987795352936},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40045738220214844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.336544394493103},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.24621903896331787},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.12505587935447693}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8712146878242493},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.830842137336731},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7205338478088379},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6970285773277283},{"id":"https://openalex.org/C73411735","wikidata":"https://www.wikidata.org/wiki/Q16369","display_name":"Chinese speech synthesis","level":4,"score":0.6278636455535889},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5717864632606506},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.511716365814209},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43302056193351746},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.43213173747062683},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4234987795352936},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40045738220214844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.336544394493103},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.24621903896331787},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12505587935447693},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3749644","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3749644","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2883670753","display_name":null,"funder_award_id":"U23B2053","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W2471520273","https://openalex.org/W2593414223","https://openalex.org/W2808631503","https://openalex.org/W2885800352","https://openalex.org/W2890964092","https://openalex.org/W2903739847","https://openalex.org/W2904459034","https://openalex.org/W2962691331","https://openalex.org/W2963341956","https://openalex.org/W2964243274","https://openalex.org/W2972951102","https://openalex.org/W3015338123","https://openalex.org/W3015440759","https://openalex.org/W3024869864","https://openalex.org/W3081488690","https://openalex.org/W3094917204","https://openalex.org/W3095545636","https://openalex.org/W3096086473","https://openalex.org/W3097777922","https://openalex.org/W3097795905","https://openalex.org/W3150572638","https://openalex.org/W3151450932","https://openalex.org/W3158374895","https://openalex.org/W3161113899","https://openalex.org/W3161296985","https://openalex.org/W3161732385","https://openalex.org/W3162746464","https://openalex.org/W3163339651","https://openalex.org/W3193700177","https://openalex.org/W3196027980","https://openalex.org/W3198123658","https://openalex.org/W3216941316","https://openalex.org/W4224928640","https://openalex.org/W4285218396","https://openalex.org/W4296068776","https://openalex.org/W4319586596","https://openalex.org/W4372341043","https://openalex.org/W4372346850","https://openalex.org/W4375868902","https://openalex.org/W4375869257","https://openalex.org/W4385329631","https://openalex.org/W4385822787","https://openalex.org/W4385823163","https://openalex.org/W4385993905","https://openalex.org/W4391020683","https://openalex.org/W4391021635","https://openalex.org/W4392903591","https://openalex.org/W4392904630","https://openalex.org/W4395961599","https://openalex.org/W4396542467","https://openalex.org/W4398152753","https://openalex.org/W4402112010","https://openalex.org/W4402112210","https://openalex.org/W4406794071"],"related_works":["https://openalex.org/W4392904630","https://openalex.org/W3149582125","https://openalex.org/W2946856121","https://openalex.org/W2465421051","https://openalex.org/W1914543332","https://openalex.org/W2181715843","https://openalex.org/W2370805772","https://openalex.org/W652196294","https://openalex.org/W2395605663","https://openalex.org/W1984347656"],"abstract_inverted_index":{"Conventional":[0],"speech":[1,17,27,64],"synthesis":[2,18,65],"techniques":[3],"have":[4],"made":[5],"significant":[6],"strides":[7],"towards":[8],"achieving":[9],"human-like":[10],"performance.":[11],"However,":[12],"the":[13,26,41,44,69,78,94,106,121,125,135,147,150],"domain":[14],"of":[15,46,54,128,149],"audiobook":[16,130,143],"still":[19],"presents":[20],"notable":[21],"challenges.":[22],"On":[23,40],"one":[24],"hand,":[25,43],"in":[28,37,62],"audiobooks":[29,47],"exhibits":[30],"rich":[31],"prosodic":[32,126],"expressiveness,":[33],"posing":[34],"substantial":[35],"difficulties":[36],"prosody":[38,75,90],"modeling.":[39],"other":[42],"reader":[45],"uses":[48],"different":[49,55,142],"voices":[50,140],"to":[51,137],"perform":[52],"dialogues":[53],"characters,":[56],"which":[57],"has":[58],"been":[59],"inadequately":[60],"explored":[61],"existing":[63],"methods.":[66],"To":[67],"address":[68],"first":[70],"challenge,":[71,96],"we":[72,97],"integrate":[73],"discourse-scale":[74],"modeling":[76],"into":[77,113],"conventional":[79],"autoencoder-based":[80],"framework":[81],"and":[82],"introduce":[83],"generative":[84],"adversarial":[85],"networks":[86],"(GANs)":[87],"for":[88,141],"phoneme-level":[89],"code":[91],"prediction.":[92],"Regarding":[93],"second":[95],"further":[98],"explore":[99],"a":[100],"character":[101],"voice":[102],"encoder":[103],"based":[104],"on":[105],"pretrained":[107],"speaker":[108],"verification":[109],"model,":[110],"integrating":[111],"it":[112,133],"our":[114],"proposed":[115,122],"method.":[116],"Experimental":[117],"results":[118],"validate":[119],"that":[120],"method":[123],"enhances":[124],"expressiveness":[127],"synthesized":[129,151],"speech.":[131,152],"Moreover,":[132],"demonstrates":[134],"capacity":[136],"produce":[138],"distinctive":[139],"characters":[144],"without":[145],"compromising":[146],"naturalness":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}