{"id":"https://openalex.org/W4406401036","doi":"https://doi.org/10.1145/3711828","title":"PhonemeVec: A Phoneme-Level Contextual Prosody Representation For Speech Synthesis","display_name":"PhonemeVec: A Phoneme-Level Contextual Prosody Representation For Speech Synthesis","publication_year":2025,"publication_date":"2025-01-15","ids":{"openalex":"https://openalex.org/W4406401036","doi":"https://doi.org/10.1145/3711828"},"language":"en","primary_location":{"id":"doi:10.1145/3711828","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711828","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/A5091475468","display_name":"Shiming Wang","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":"Shiming Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0004-8004-937X","affiliations":[{"raw_affiliation_string":"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":"Li-Ping Chen","raw_affiliation_strings":["Dept. of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-9421-1049","affiliations":[{"raw_affiliation_string":"Dept. of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045907056","display_name":"Yang Ai","orcid":"https://orcid.org/0000-0001-6668-022X"},"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":"Yang Ai","raw_affiliation_strings":["Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-6668-022X","affiliations":[{"raw_affiliation_string":"Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010426665","display_name":"Yajun Hu","orcid":"https://orcid.org/0009-0007-9626-456X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yajun Hu","raw_affiliation_strings":["iFlytek Co Ltd, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0007-9626-456X","affiliations":[{"raw_affiliation_string":"iFlytek Co Ltd, Hefei, China","institution_ids":[]}]},{"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":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-7853-5273","affiliations":[{"raw_affiliation_string":"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":[],"apc_list":null,"apc_paid":null,"fwci":1.396,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.81999737,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"24","issue":"3","first_page":"1","last_page":"15"},"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":0.9972000122070312,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9969000220298767,"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":0.8673016428947449},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6285930871963501},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5172865390777588},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4877951443195343},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4726654291152954},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.43768996000289917},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.43402621150016785},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3222264051437378}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8673016428947449},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6285930871963501},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5172865390777588},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4877951443195343},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4726654291152954},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43768996000289917},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.43402621150016785},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3222264051437378},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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:10.1145/3711828","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711828","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":[],"awards":[{"id":"https://openalex.org/G889782296","display_name":null,"funder_award_id":"U23B2053 and 62301521","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2000633092","https://openalex.org/W2471520273","https://openalex.org/W2903739847","https://openalex.org/W2904459034","https://openalex.org/W2933138175","https://openalex.org/W2973049979","https://openalex.org/W3015338123","https://openalex.org/W3015440759","https://openalex.org/W3016021263","https://openalex.org/W3026874504","https://openalex.org/W3095491807","https://openalex.org/W3140429000","https://openalex.org/W3150572638","https://openalex.org/W3197324626","https://openalex.org/W3209059054","https://openalex.org/W3216941316","https://openalex.org/W4221145109","https://openalex.org/W4221159457","https://openalex.org/W4225303561","https://openalex.org/W4281492411","https://openalex.org/W4287119707","https://openalex.org/W4381786045","https://openalex.org/W4385572372","https://openalex.org/W4385822952","https://openalex.org/W4390075359","https://openalex.org/W4391020683","https://openalex.org/W4394862910","https://openalex.org/W4395959004","https://openalex.org/W4401806189"],"related_works":["https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3149582125","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W152045069","https://openalex.org/W652196294","https://openalex.org/W2368700418","https://openalex.org/W1965141925"],"abstract_inverted_index":{"Recently,":[0],"fine-grained":[1],"prosody":[2,27,38,50,81],"representations":[3,28],"have":[4],"emerged":[5],"and":[6,59,70,125,132],"attracted":[7],"growing":[8],"attention":[9],"to":[10,46,51],"address":[11],"the":[12,23,31,36,42,47,53,56,80,84,90,97,103,114,119,122],"one-to-many":[13],"problem":[14],"in":[15,102,128],"text-to-speech":[16],"(TTS).":[17],"In":[18],"this":[19],"article,":[20],"we":[21,40],"propose":[22],"PhonemeVec,":[24],"a":[25,62],"pre-trained":[26],"with":[29,67],"considering":[30],"contextual":[32,37],"information.":[33],"To":[34],"obtain":[35],"representations,":[39],"improve":[41],"data2vec":[43],"framework":[44],"according":[45],"characteristics":[48],"of":[49,83,99,105,116,130],"extract":[52],"PhonemeVec":[54,73,100,117],"from":[55],"low-band":[57],"mel-spectrogram,":[58],"pre-train":[60],"on":[61,89],"960":[63],"hours":[64],"Chinese":[65],"corpus":[66],"high":[68],"quality":[69],"diverse":[71],"pronunciation.":[72],"is":[74],"subsequently":[75],"integrated":[76],"into":[77],"FastSpeech2,":[78],"supervising":[79],"modeling":[82],"text":[85],"encoder.":[86],"Experiments":[87],"conducted":[88],"Blizzard":[91],"Challenge":[92],"2019":[93],"dataset":[94],"show":[95],"that":[96,113],"integration":[98],"results":[101],"synthesis":[104],"more":[106],"natural":[107],"speech.":[108],"Additionally,":[109],"objective":[110],"evaluations":[111],"confirm":[112],"application":[115],"reduces":[118],"distortions":[120],"between":[121],"generated":[123],"speech":[124],"original":[126],"recordings":[127],"terms":[129],"duration":[131],"F0.":[133],"Audio":[134],"samples":[135],"can":[136],"be":[137],"found":[138],"at":[139],"http://home.ustc.edu.cn/~wsmzzz/PhonemeVec/demo.html":[140],".":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
