{"id":"https://openalex.org/W4224928640","doi":"https://doi.org/10.1109/icassp43922.2022.9746238","title":"Discourse-Level Prosody Modeling with a Variational Autoencoder for Non-Autoregressive Expressive Speech Synthesis","display_name":"Discourse-Level Prosody Modeling with a Variational Autoencoder for Non-Autoregressive Expressive Speech Synthesis","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224928640","doi":"https://doi.org/10.1109/icassp43922.2022.9746238"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746238","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/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"]},{"id":"https://openalex.org/I4210103894","display_name":"Hefei National Center for Physical Sciences at Nanoscale","ror":"https://ror.org/01jeedh73","country_code":"CN","type":"facility","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I4210103894"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning-Qian Wu","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,P.R.China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,P.R.China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I4210103894"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000176539","display_name":"Zhao-Ci Liu","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"]},{"id":"https://openalex.org/I4210103894","display_name":"Hefei National Center for Physical Sciences at Nanoscale","ror":"https://ror.org/01jeedh73","country_code":"CN","type":"facility","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I4210103894"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao-Ci Liu","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,P.R.China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,P.R.China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I4210103894"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.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"]},{"id":"https://openalex.org/I4210103894","display_name":"Hefei National Center for Physical Sciences at Nanoscale","ror":"https://ror.org/01jeedh73","country_code":"CN","type":"facility","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366","https://openalex.org/I4210103894"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,P.R.China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,P.R.China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I4210103894"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7592","last_page":"7596"},"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/T11309","display_name":"Music and Audio Processing","score":0.9957000017166138,"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":0.9945999979972839,"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/naturalness","display_name":"Naturalness","score":0.8947960138320923},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.8570016026496887},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.8237553834915161},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7156724333763123},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.6154998540878296},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6154736280441284},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5886074304580688},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5809639096260071},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5165666341781616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4823038578033447},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4202296733856201},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.26456671953201294},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.25698184967041016},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1597609519958496}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8947960138320923},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8570016026496887},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8237553834915161},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7156724333763123},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6154998540878296},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6154736280441284},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5886074304580688},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5809639096260071},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5165666341781616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4823038578033447},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4202296733856201},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26456671953201294},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25698184967041016},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1597609519958496},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746238","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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","display_name":"Quality Education","score":0.5099999904632568}],"awards":[],"funders":[{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2471520273","https://openalex.org/W2587284713","https://openalex.org/W2747874407","https://openalex.org/W2896457183","https://openalex.org/W2903739847","https://openalex.org/W2904459034","https://openalex.org/W2911933223","https://openalex.org/W2946200149","https://openalex.org/W2962688977","https://openalex.org/W2962691331","https://openalex.org/W2963223306","https://openalex.org/W2964243274","https://openalex.org/W2990883660","https://openalex.org/W3021636956","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3092028330","https://openalex.org/W3102725307","https://openalex.org/W3113076898","https://openalex.org/W3161296985","https://openalex.org/W3161732385","https://openalex.org/W3163339651","https://openalex.org/W3172148458","https://openalex.org/W3193700177","https://openalex.org/W4289383906","https://openalex.org/W6640963894","https://openalex.org/W6733471323","https://openalex.org/W6755300632","https://openalex.org/W6763832098","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6795261426"],"related_works":["https://openalex.org/W4392904630","https://openalex.org/W169399214","https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W2108985546","https://openalex.org/W2081919107"],"abstract_inverted_index":{"To":[0],"address":[1],"the":[2,33,104],"issue":[3],"of":[4,22,36,95,108],"one-to-many":[5],"mapping":[6],"from":[7,46],"phoneme":[8],"sequences":[9],"to":[10],"acoustic":[11],"features":[12,48,60],"in":[13,70],"expressive":[14],"speech":[15],"synthesis,":[16],"this":[17,39],"paper":[18],"proposes":[19],"a":[20,27,82],"method":[21,90],"discourse-level":[23,58,96],"prosody":[24,42,47],"modeling":[25],"with":[26,52,62],"variational":[28],"autoencoder":[29],"(VAE)":[30],"based":[31],"on":[32,81,103],"non-autoregressive":[34],"architecture":[35],"FastSpeech.":[37],"In":[38],"method,":[40],"phone-level":[41],"codes":[43],"are":[44,55],"extracted":[45],"by":[49],"combining":[50],"VAE":[51],"FastSpeech,":[53],"and":[54,99,106],"predicted":[56],"using":[57],"text":[59],"together":[61],"BERT":[63],"embeddings.":[64],"The":[65],"continuous":[66],"wavelet":[67],"transform":[68],"(CWT)":[69],"FastSpeech2":[71,102],"for":[72],"F0":[73],"representation":[74],"is":[75],"not":[76],"necessary":[77],"anymore.":[78],"Experimental":[79],"results":[80],"Chinese":[83],"audiobook":[84],"dataset":[85],"show":[86],"that":[87],"our":[88],"proposed":[89],"can":[91],"effectively":[92],"take":[93],"advantage":[94],"linguistic":[97],"information":[98],"has":[100],"outperformed":[101],"naturalness":[105],"expressiveness":[107],"synthetic":[109],"speech.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}