{"id":"https://openalex.org/W4401806189","doi":"https://doi.org/10.1109/taslp.2024.3449148","title":"PE-Wav2vec: A Prosody-Enhanced Speech Model for Self-Supervised Prosody Learning in TTS","display_name":"PE-Wav2vec: A Prosody-Enhanced Speech Model for Self-Supervised Prosody Learning in TTS","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401806189","doi":"https://doi.org/10.1109/taslp.2024.3449148"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3449148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3449148","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language 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/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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao-Ci Liu","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0007-0102-6527","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430194","display_name":"Liping Chen","orcid":"https://orcid.org/0000-0002-9421-1049"},"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":"Liping Chen","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-9421-1049","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059516164","display_name":"Ya-Jun Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya-Jun Hu","raw_affiliation_strings":["iFLYTEK Research, iFLYTEK Company Ltd., Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research, iFLYTEK Company Ltd., Hefei, China","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"middle","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 Laboratory 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 Laboratory 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/A5101924451","display_name":"Jia Pan","orcid":"https://orcid.org/0000-0002-7073-1744"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Pan","raw_affiliation_strings":["iFLYTEK Research, iFLYTEK Company Ltd., Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-7073-1744","affiliations":[{"raw_affiliation_string":"iFLYTEK Research, iFLYTEK Company Ltd., Hefei, China","institution_ids":["https://openalex.org/I173632517"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3892,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.83995434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"32","issue":null,"first_page":"4199","last_page":"4210"},"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/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":0.9696061611175537},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.48345503211021423},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44831210374832153},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.40715155005455017},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3600257337093353}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9696061611175537},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.48345503211021423},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44831210374832153},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40715155005455017},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3600257337093353}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3449148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3449148","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"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":44,"referenced_works":["https://openalex.org/W1604034532","https://openalex.org/W2006689085","https://openalex.org/W2034139177","https://openalex.org/W2049686551","https://openalex.org/W2109189270","https://openalex.org/W2110358797","https://openalex.org/W2124509324","https://openalex.org/W2157225271","https://openalex.org/W2519091744","https://openalex.org/W2903739847","https://openalex.org/W2904459034","https://openalex.org/W2933138175","https://openalex.org/W2963091184","https://openalex.org/W2964243274","https://openalex.org/W3097003111","https://openalex.org/W3097892637","https://openalex.org/W3150572638","https://openalex.org/W3161113899","https://openalex.org/W3162948689","https://openalex.org/W3170320568","https://openalex.org/W3197216873","https://openalex.org/W3197304925","https://openalex.org/W3197324626","https://openalex.org/W3202510435","https://openalex.org/W3209059054","https://openalex.org/W3216941316","https://openalex.org/W4200047557","https://openalex.org/W4221159457","https://openalex.org/W4226380987","https://openalex.org/W4297841650","https://openalex.org/W4297841714","https://openalex.org/W4375868859","https://openalex.org/W4385329631","https://openalex.org/W4385822381","https://openalex.org/W4385895691","https://openalex.org/W4390926497","https://openalex.org/W4395959004","https://openalex.org/W6750489868","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6805710207","https://openalex.org/W6810007534"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2355553914","https://openalex.org/W149862513","https://openalex.org/W2347684782","https://openalex.org/W187117048","https://openalex.org/W4320472397","https://openalex.org/W2401269021","https://openalex.org/W2145654520"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"leveraging":[3],"large-scale":[4],"untranscribed":[5],"speech":[6,26,93,141,169],"data":[7],"to":[8],"enhance":[9],"the":[10,21,24,50,60,65,74,79,88,97,121,131,143,150,159,164],"prosody":[11,39,42,138],"modelling":[12],"capability":[13],"of":[14,23,78,123,140,167],"<italic":[15,30,51,106],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[16,31,52,107],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">text-to-speech</i>":[17],"(TTS)":[18],"models.":[19,173],"On":[20],"basis":[22,122],"self-supervised":[25],"model":[27,81,104,110,134,147,152],"wav2vec":[28,66,145],"2.0,":[29],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Prosody-Enhanced":[32],"wav2vec</i>":[33],"(PE-wav2vec)":[34],"is":[35,44,118],"proposed":[36,132],"by":[37,46],"introducing":[38],"learning.":[40],"Specifically,":[41],"learning":[43],"achieved":[45],"applying":[47],"supervision":[48],"from":[49],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">linear":[53],"predictive":[54],"coding</i>":[55],"(LPC)":[56],"residual":[57],"signals":[58],"on":[59,112,120],"initial":[61,75],"Transformer":[62,76],"blocks":[63,77],"in":[64,91,100],"2.0":[67,146],"architecture.":[68],"The":[69,126],"embedding":[70],"vectors":[71],"extracted":[72],"with":[73,171],"PE-wav2vec":[80,98,133,154],"are":[82],"utilised":[83],"as":[84],"prosodic":[85],"representations":[86,99,155],"for":[87],"corresponding":[89],"frames":[90],"a":[92],"utterance.":[94],"To":[95],"apply":[96],"TTS,":[101],"an":[102],"acoustic":[103],"named":[105],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Speech":[108],"Synthesis":[109],"conditioned":[111],"Self-Supervisedly":[113],"Learned":[114],"Prosodic":[115],"Representations</i>":[116],"(S4LPR)":[117],"designed":[119],"FastSpeech":[124],"2.":[125],"experimental":[127],"results":[128],"demonstrate":[129],"that":[130],"can":[135,156],"provide":[136],"richer":[137],"descriptions":[139],"than":[142],"vanilla":[144],"can.":[148],"Furthermore,":[149],"S4LPR":[151],"using":[153],"effectively":[157],"improve":[158],"subjective":[160],"naturalness":[161],"and":[162],"reduce":[163],"objective":[165],"distortions":[166],"synthetic":[168],"compared":[170],"baseline":[172]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}