{"id":"https://openalex.org/W4281760581","doi":"https://doi.org/10.21437/interspeech.2022-10140","title":"Pronunciation Dictionary-Free Multilingual Speech Synthesis by Combining Unsupervised and Supervised Phonetic Representations","display_name":"Pronunciation Dictionary-Free Multilingual Speech Synthesis by Combining Unsupervised and Supervised Phonetic Representations","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4281760581","doi":"https://doi.org/10.21437/interspeech.2022-10140"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10140","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10140","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5101983531","display_name":"Chang Liu","orcid":"https://orcid.org/0009-0003-1661-1113"},"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":["NERC-SLIP, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"NERC-SLIP, University of Science and Technology of China, Hefei, 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":["NERC-SLIP, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"NERC-SLIP, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101593418","display_name":"Ling-Hui Chen","orcid":"https://orcid.org/0009-0009-4247-4128"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ling-Hui Chen","raw_affiliation_strings":["iFLYTEK Research, Hefei, China"],"affiliations":[{"raw_affiliation_string":"iFLYTEK Research, Hefei, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101983531"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.2086,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.39035506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4282","last_page":"4286"},"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":0.9983999729156494,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9934999942779541,"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/pronunciation","display_name":"Pronunciation","score":0.7980468273162842},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7921833992004395},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6892841458320618},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6299048662185669},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6273371577262878},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5518001317977905},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18776017427444458}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7980468273162842},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7921833992004395},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6892841458320618},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6299048662185669},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6273371577262878},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5518001317977905},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18776017427444458},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10140","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10140","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G8663906801","display_name":null,"funder_award_id":"61871358","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":20,"referenced_works":["https://openalex.org/W2316803017","https://openalex.org/W2514457011","https://openalex.org/W2747874407","https://openalex.org/W2884873108","https://openalex.org/W2903739847","https://openalex.org/W2933138175","https://openalex.org/W2946200149","https://openalex.org/W2963609956","https://openalex.org/W2963799213","https://openalex.org/W2964243274","https://openalex.org/W3033411150","https://openalex.org/W3036601975","https://openalex.org/W3092028330","https://openalex.org/W3140429000","https://openalex.org/W3174758275","https://openalex.org/W4200300291","https://openalex.org/W4286905904","https://openalex.org/W4287173589","https://openalex.org/W4297808394","https://openalex.org/W4302213377"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2000075989","https://openalex.org/W4220683390","https://openalex.org/W2776838583","https://openalex.org/W3204019825","https://openalex.org/W127416991"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,31,42,52],"multilingual":[4],"speech":[5,45],"synthesis":[6],"method":[7,105],"which":[8,74],"combines":[9,85],"unsupervised":[10],"phonetic":[11,16],"representations":[12,17],"(UPR)":[13],"and":[14,41,78,83,89,118],"supervised":[15],"(SPR)":[18],"to":[19,38,58,91],"avoid":[20],"reliance":[21],"on":[22,98],"the":[23,63,86,103,107,119],"pronunciation":[24],"dictionaries":[25],"of":[26,66,95],"target":[27,67],"languages.In":[28],"this":[29],"method,":[30],"pretrained":[32],"wav2vec":[33],"2.0":[34],"model":[35,48,71],"is":[36,49,72],"adopted":[37],"extract":[39,59],"UPRs":[40,77,88,125],"language-independent":[43],"automatic":[44],"recognition":[46],"(LI-ASR)":[47],"built":[50],"with":[51],"connectionist":[53],"temporal":[54],"classification":[55],"(CTC)":[56],"loss":[57],"segment-level":[60],"SPRs":[61,79,90],"from":[62,80,113],"audio":[64],"data":[65],"languages.Then,":[68],"an":[69],"acoustic":[70],"designed,":[73],"first":[75],"predicts":[76],"texts":[81],"separately":[82],"then":[84],"predicted":[87,111],"generate":[92],"mel-spectrograms.The":[93],"results":[94],"our":[96],"experiments":[97],"six":[99],"languages":[100],"show":[101],"that":[102,109,122],"proposed":[104],"outperformed":[106],"methods":[108],"directly":[110],"mel-spectrograms":[112],"character":[114],"or":[115,126],"phoneme":[116],"sequences":[117],"ablated":[120],"models":[121],"utilized":[123],"only":[124],"SPRs.":[127]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}