{"id":"https://openalex.org/W4387693344","doi":"https://doi.org/10.1145/3614008.3614019","title":"The Tacotron2-based IPA-to-Speech speech synthesis system","display_name":"The Tacotron2-based IPA-to-Speech speech synthesis system","publication_year":2023,"publication_date":"2023-07-14","ids":{"openalex":"https://openalex.org/W4387693344","doi":"https://doi.org/10.1145/3614008.3614019"},"language":"en","primary_location":{"id":"doi:10.1145/3614008.3614019","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3614008.3614019","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 6th International Conference on Signal Processing and Machine Learning (SPML)","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/A5090510182","display_name":"Jueting Liu","orcid":"https://orcid.org/0009-0004-2986-2605"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jueting Liu","raw_affiliation_strings":["China University of Mining and Technology, China"],"raw_orcid":"https://orcid.org/0009-0004-2986-2605","affiliations":[{"raw_affiliation_string":"China University of Mining and Technology, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101928096","display_name":"Yu Lei","orcid":"https://orcid.org/0009-0004-6047-9284"},"institutions":[{"id":"https://openalex.org/I4210096896","display_name":"Huaibei Mining (China)","ror":"https://ror.org/00tpvmh02","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210096896"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Lei","raw_affiliation_strings":["Huaibei Mining Group, China"],"raw_orcid":"https://orcid.org/0009-0004-6047-9284","affiliations":[{"raw_affiliation_string":"Huaibei Mining Group, China","institution_ids":["https://openalex.org/I4210096896"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088242008","display_name":"Minda Yao","orcid":"https://orcid.org/0000-0003-4820-5366"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minda Yao","raw_affiliation_strings":["China University of Mining and Technology, China"],"raw_orcid":"https://orcid.org/0000-0003-4820-5366","affiliations":[{"raw_affiliation_string":"China University of Mining and Technology, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zemeng Liu","orcid":"https://orcid.org/0009-0007-4649-9790"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zemeng Liu","raw_affiliation_strings":["Jiangsu Novolion Technology Company, China"],"raw_orcid":"https://orcid.org/0009-0007-4649-9790","affiliations":[{"raw_affiliation_string":"Jiangsu Novolion Technology Company, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093074693","display_name":"Guoyuan Lin","orcid":"https://orcid.org/0009-0000-5841-6365"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoyuan Lin","raw_affiliation_strings":["China University of Mining and Technology, China"],"raw_orcid":"https://orcid.org/0009-0000-5841-6365","affiliations":[{"raw_affiliation_string":"China University of Mining and Technology, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002576314","display_name":"Zehua Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zehua Wang","raw_affiliation_strings":["China University of Mining and Technology, China"],"raw_orcid":"https://orcid.org/0009-0003-2681-8230","affiliations":[{"raw_affiliation_string":"China University of Mining and Technology, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091632689","display_name":"Yingchun Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingchun Liu","raw_affiliation_strings":["China University of Mining and Technology, China"],"raw_orcid":"https://orcid.org/0009-0003-3072-072X","affiliations":[{"raw_affiliation_string":"China University of Mining and Technology, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100344481","display_name":"Wei Chen","orcid":"https://orcid.org/0000-0002-7663-278X"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Chen","raw_affiliation_strings":["China University of Mining and Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-7663-278X","affiliations":[{"raw_affiliation_string":"China University of Mining and Technology, China","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13229988,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"70","last_page":"75"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9955000281333923,"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/T10028","display_name":"Topic Modeling","score":0.9854000210762024,"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/computer-science","display_name":"Computer science","score":0.811371922492981},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7859165668487549},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7751632928848267},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6529395580291748},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5969396829605103},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5827769637107849},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5633103847503662},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5151418447494507},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4786432981491089},{"id":"https://openalex.org/keywords/chinese-speech-synthesis","display_name":"Chinese speech synthesis","score":0.4334821105003357},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4259389042854309},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.4259144067764282},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11902740597724915},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08254560828208923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.811371922492981},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7859165668487549},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7751632928848267},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6529395580291748},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5969396829605103},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5827769637107849},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5633103847503662},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5151418447494507},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4786432981491089},{"id":"https://openalex.org/C73411735","wikidata":"https://www.wikidata.org/wiki/Q16369","display_name":"Chinese speech synthesis","level":4,"score":0.4334821105003357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4259389042854309},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.4259144067764282},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11902740597724915},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08254560828208923},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3614008.3614019","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3614008.3614019","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 6th International Conference on Signal Processing and Machine Learning (SPML)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4529491380","display_name":null,"funder_award_id":"2023QN1079","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1593247906","https://openalex.org/W2090755665","https://openalex.org/W2093107730","https://openalex.org/W2115143544","https://openalex.org/W2946200149","https://openalex.org/W2963299674","https://openalex.org/W2972437137","https://openalex.org/W4285216467","https://openalex.org/W6607786901","https://openalex.org/W6736996214"],"related_works":["https://openalex.org/W2349468610","https://openalex.org/W2772686614","https://openalex.org/W2036933852","https://openalex.org/W4200068392","https://openalex.org/W231741463","https://openalex.org/W301864623","https://openalex.org/W2338806053","https://openalex.org/W2559880587","https://openalex.org/W2543721542","https://openalex.org/W4387693344"],"abstract_inverted_index":{"To":[0],"help":[1],"language":[2,31],"learners":[3],"better":[4],"understanding":[5],"the":[6,56,62,66,82,89,106,110,118,121,131,135,138,147],"pronunciation":[7],"of":[8,55,120],"one":[9],"language,":[10],"in":[11,32,40,69,137],"this":[12,79,125,144],"paper,":[13],"we":[14,141],"proposed":[15],"an":[16],"IPA-to-Speech":[17],"speech":[18,28,50,83,90,122],"synthesis":[19,51,84],"system":[20],"which":[21],"aims":[22],"to":[23,60,87,104,116,129],"generate":[24,88],"high":[25],"quality":[26],"human":[27],"from":[29,91],"written":[30],"IPA":[33,76,92,132],"format.":[34],"There":[35],"are":[36],"mainly":[37],"two":[38],"parts":[39],"our":[41],"system:":[42],"a":[43,48],"Transformer-based":[44],"G2P":[45,57,107],"converter":[46,58,108],"and":[47,81,98,109,150],"Tacotron2-based":[49],"system.":[52],"The":[53,94],"purpose":[54],"is":[59],"build":[61],"training":[63],"data,":[64],"all":[65],"English":[67],"sentences":[68],"LJSpeech":[70],"can":[71],"be":[72],"converted":[73],"into":[74],"their":[75],"formats":[77],"by":[78],"converter,":[80],"module":[85],"intend":[86],"sentences.":[93],"word":[95],"error":[96,100],"rate":[97,101],"phoneme":[99],"were":[102],"utilized":[103],"evaluate":[105,117],"mean":[111],"opinion":[112],"score":[113],"was":[114],"used":[115],"performance":[119],"synthesis.":[123],"Also,":[124],"work":[126],"inspired":[127],"us":[128],"use":[130],"format":[133],"represent":[134],"dialects,":[136],"future":[139],"work,":[140],"will":[142],"continue":[143],"research":[145],"on":[146],"dialect":[148],"recognition":[149],"generation.":[151]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}