{"id":"https://openalex.org/W4406461761","doi":"https://doi.org/10.1109/slt61566.2024.10832341","title":"Language-Independent Prosody-Enhanced Speech Representations For Multilingual Speech Synthesis","display_name":"Language-Independent Prosody-Enhanced Speech Representations For Multilingual Speech Synthesis","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461761","doi":"https://doi.org/10.1109/slt61566.2024.10832341"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5100353288","display_name":"Chang Liu","orcid":"https://orcid.org/0000-0002-7292-6107"},"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":true,"raw_author_name":"Chang Liu","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069176378","display_name":"Zhen-Hua Ling","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":"Zhen-Hua Ling","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","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 Co., Ltd.,China"],"affiliations":[{"raw_affiliation_string":"iFLYTEK Co., Ltd.,China","institution_ids":["https://openalex.org/I173632517"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100353288"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23844237,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"482","last_page":"488"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9973999857902527,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9970999956130981,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.8170933723449707},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7590497732162476},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6862971782684326},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5812085866928101},{"id":"https://openalex.org/keywords/chinese-speech-synthesis","display_name":"Chinese speech synthesis","score":0.577446699142456},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5464850068092346},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5271496176719666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.399395227432251}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8170933723449707},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7590497732162476},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6862971782684326},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5812085866928101},{"id":"https://openalex.org/C73411735","wikidata":"https://www.wikidata.org/wiki/Q16369","display_name":"Chinese speech synthesis","level":4,"score":0.577446699142456},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5464850068092346},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5271496176719666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.399395227432251}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2127141656","https://openalex.org/W2933138175","https://openalex.org/W2964243274","https://openalex.org/W3036601975","https://openalex.org/W3092028330","https://openalex.org/W3181257032","https://openalex.org/W3198275944","https://openalex.org/W3198429080","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4226132755","https://openalex.org/W4226380987","https://openalex.org/W4281492411","https://openalex.org/W4283076240","https://openalex.org/W4287173589","https://openalex.org/W4287854494","https://openalex.org/W4297841714","https://openalex.org/W4319586625","https://openalex.org/W4319862652","https://openalex.org/W4375869005","https://openalex.org/W4385764360","https://openalex.org/W4385822337","https://openalex.org/W4385823368","https://openalex.org/W4386536196","https://openalex.org/W4391640577","https://openalex.org/W4392903365","https://openalex.org/W4402111672","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6795952400","https://openalex.org/W6796464841","https://openalex.org/W6798575157","https://openalex.org/W6810007534","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W3149582125","https://openalex.org/W2349468610","https://openalex.org/W2465421051","https://openalex.org/W2181715843","https://openalex.org/W652196294","https://openalex.org/W2395605663","https://openalex.org/W1984347656","https://openalex.org/W2772686614","https://openalex.org/W4200068392","https://openalex.org/W231741463"],"abstract_inverted_index":{"This":[0,72],"paper":[1,73],"proposes":[2],"language-independent":[3,100,139],"prosody-enhanced":[4,140,170],"speech":[5,12,41,141,171],"representations":[6,35,49,142,149,172,178],"to":[7,104,121],"improve":[8,105],"the":[9,15,34,60,69,75,80,106,131,138,155,174],"naturalness":[10],"of":[11,109,150],"synthesis":[13],"for":[14,27],"target":[16,164],"languages":[17,165],"that":[18,167],"lack":[19],"prosodic":[20,70,76,91,94,107,117],"labels.":[21,95],"To":[22],"build":[23],"text-to-speech":[24],"(TTS)":[25],"systems":[26],"low-resource":[28],"languages,":[29],"recent":[30],"studies":[31],"have":[32,55],"employed":[33],"extracted":[36,144],"from":[37],"self-supervised":[38],"learning":[39],"(SSL)":[40],"models,":[42],"such":[43],"as":[44,47,147],"wav2vec":[45,82,123,176],"2.0,":[46],"intermediate":[48,148],"in":[50,65,79,154],"TTS":[51,157],"models.":[52,111],"However,":[53],"they":[54],"generally":[56],"focused":[57],"only":[58],"on":[59,162],"linguistic":[61],"and":[62,93,145],"phonetic":[63],"information":[64,77],"SSL":[66,110],"representations,":[67],"disregarding":[68],"information.":[71],"investigates":[74],"contained":[78],"multilingual":[81,127],"2.0":[83,124,136,177],"model":[84,125,153],"through":[85],"layer-wise":[86],"probing":[87],"tests":[88],"utilizing":[89],"acoustic":[90,152],"features":[92],"Furthermore,":[96],"we":[97],"propose":[98],"a":[99,116],"prosody":[101],"enhancement":[102],"approach":[103],"properties":[108],"The":[112,159],"proposed":[113,169],"method":[114],"introduces":[115],"label":[118],"prediction":[119],"loss":[120],"fine-tune":[122],"with":[126],"prosody-annotated":[128],"corpora.":[129],"From":[130],"fine-tuned":[132],"wav":[133],"2":[134],"vec":[135],"model,":[137],"are":[143],"serve":[146],"our":[151,168],"downstream":[156],"task.":[158],"experimental":[160],"results":[161],"six":[163],"demonstrate":[166],"outperform":[173],"original":[175],"without":[179],"enhancement.":[180]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}