{"id":"https://openalex.org/W3127594010","doi":"https://doi.org/10.1145/3443279.3443295","title":"Myanmar Text-to-Speech Synthesis Using End-to-End Model","display_name":"Myanmar Text-to-Speech Synthesis Using End-to-End Model","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3127594010","doi":"https://doi.org/10.1145/3443279.3443295","mag":"3127594010"},"language":"en","primary_location":{"id":"doi:10.1145/3443279.3443295","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3443279.3443295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Natural Language Processing and Information Retrieval","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/A5049510238","display_name":"Qinglai Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qinglai Qin","raw_affiliation_strings":["Yunnan University Kunming, Yunnan Province, China"],"affiliations":[{"raw_affiliation_string":"Yunnan University Kunming, Yunnan Province, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101758436","display_name":"Jian Yang","orcid":"https://orcid.org/0000-0001-6135-6420"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["Yunnan University Kunming, Yunnan Province, China"],"affiliations":[{"raw_affiliation_string":"Yunnan University Kunming, Yunnan Province, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101578575","display_name":"Peiying Li","orcid":"https://orcid.org/0000-0001-8047-3817"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiying Li","raw_affiliation_strings":["Yunnan University Kunming, Yunnan Province, China"],"affiliations":[{"raw_affiliation_string":"Yunnan University Kunming, Yunnan Province, China","institution_ids":["https://openalex.org/I189210763"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049510238"],"corresponding_institution_ids":["https://openalex.org/I189210763"],"apc_list":null,"apc_paid":null,"fwci":0.1326,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57959079,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1702","issue":null,"first_page":"6","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9966999888420105,"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":0.9945999979972839,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7981256246566772},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.7693488597869873},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7659435272216797},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6955654621124268},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6406165361404419},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.577416718006134},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5726618766784668},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5584803223609924},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5198243856430054},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4726758599281311},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3828893005847931},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3360797166824341}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7981256246566772},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7693488597869873},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7659435272216797},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6955654621124268},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6406165361404419},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.577416718006134},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5726618766784668},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5584803223609924},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5198243856430054},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4726758599281311},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3828893005847931},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3360797166824341},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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:10.1145/3443279.3443295","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3443279.3443295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1975163393","https://openalex.org/W2057964681","https://openalex.org/W2064675550","https://openalex.org/W2102003408","https://openalex.org/W2129142580","https://openalex.org/W2591927543","https://openalex.org/W2604184139","https://openalex.org/W2612690371","https://openalex.org/W2896457183","https://openalex.org/W2936103087","https://openalex.org/W2963300588","https://openalex.org/W2964002616","https://openalex.org/W2964243274","https://openalex.org/W2972802841","https://openalex.org/W2973043900","https://openalex.org/W6695553435","https://openalex.org/W6734815144","https://openalex.org/W6736356763","https://openalex.org/W6756197946"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W1537411440","https://openalex.org/W1984347656","https://openalex.org/W596245619"],"abstract_inverted_index":{"In":[0,64],"this":[1,103],"paper,":[2],"we":[3,34,66],"propose":[4],"a":[5,40,53],"Myanmar":[6,20,61,99],"speech":[7,55,100,113],"synthesis":[8,101],"system":[9],"based":[10],"on":[11,29,84],"an":[12],"End-to-End":[13,26],"neural":[14],"network":[15,43,57,89],"model,":[16],"which":[17,79],"integrates":[18],"the":[19,24,30,68,75,81,85,92,107],"phone":[21,45,76,86],"model":[22,32],"into":[23],"Tacotron2":[25],"model.":[27],"Based":[28],"Seq2seq":[31],"architecture,":[33],"use":[35],"phone-level":[36],"embedding":[37],"to":[38,47,58,73],"form":[39],"feature":[41,77,87,94],"prediction":[42],"from":[44],"sequences":[46],"Mel":[48],"spectrum,":[49],"and":[50,90,109],"combine":[51],"with":[52,97],"semi-supervised":[54],"generation":[56],"generate":[59],"high-quality":[60],"synthesized":[62,112],"speech.":[63],"addition,":[65],"introduced":[67],"BERT":[69],"pre-training":[70],"decoder":[71],"module":[72],"assist":[74],"extraction,":[78],"reduces":[80],"system's":[82],"dependence":[83],"extraction":[88],"improve":[91],"text":[93],"richness.":[95],"Compared":[96],"other":[98],"systems,":[102],"method":[104],"effectively":[105],"improves":[106],"naturalness":[108],"accuracy":[110],"of":[111],"under":[114],"low":[115],"resource":[116],"conditions.":[117]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
