{"id":"https://openalex.org/W2944622002","doi":"https://doi.org/10.1109/iscslp.2018.8706263","title":"End-to-End Mongolian Text-to-Speech System","display_name":"End-to-End Mongolian Text-to-Speech System","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2944622002","doi":"https://doi.org/10.1109/iscslp.2018.8706263","mag":"2944622002"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2018.8706263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706263","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5100642253","display_name":"Jingdong Li","orcid":"https://orcid.org/0000-0003-2335-6280"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingdong Li","raw_affiliation_strings":["Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, College of Computer Science, Inner Mongolia University, China"],"affiliations":[{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323546","display_name":"Hui Zhang","orcid":"https://orcid.org/0000-0003-2569-1824"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Zhang","raw_affiliation_strings":["Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, College of Computer Science, Inner Mongolia University, China"],"affiliations":[{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082746577","display_name":"Rui Liu","orcid":"https://orcid.org/0000-0003-4524-7413"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Liu","raw_affiliation_strings":["Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, College of Computer Science, Inner Mongolia University, China"],"affiliations":[{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693230","display_name":"Xueliang Zhang","orcid":"https://orcid.org/0000-0002-0406-1105"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueliang Zhang","raw_affiliation_strings":["Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, College of Computer Science, Inner Mongolia University, China"],"affiliations":[{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014372166","display_name":"Feilong Bao","orcid":"https://orcid.org/0000-0001-7312-1629"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feilong Bao","raw_affiliation_strings":["Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, College of Computer Science, Inner Mongolia University, China"],"affiliations":[{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100642253"],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":0.8144,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.80668691,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"41","issue":null,"first_page":"483","last_page":"487"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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":0.9986000061035156,"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/annotation","display_name":"Annotation","score":0.8151067495346069},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7968117594718933},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7730674743652344},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7643463015556335},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6535971164703369},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6279380321502686},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6218553781509399},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.53208988904953},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5136269927024841},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.48443034291267395},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4815369248390198},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.4780226945877075},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.4588435888290405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4555356502532959},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.10029813647270203},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08208948373794556},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.07977387309074402}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8151067495346069},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7968117594718933},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7730674743652344},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7643463015556335},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6535971164703369},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6279380321502686},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6218553781509399},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.53208988904953},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5136269927024841},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.48443034291267395},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4815369248390198},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.4780226945877075},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.4588435888290405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4555356502532959},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.10029813647270203},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08208948373794556},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07977387309074402},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2018.8706263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706263","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1539777262","https://openalex.org/W1600722501","https://openalex.org/W2001173748","https://openalex.org/W2102003408","https://openalex.org/W2102113734","https://openalex.org/W2129142580","https://openalex.org/W2139207223","https://openalex.org/W2150658333","https://openalex.org/W2340944142","https://openalex.org/W2342840547","https://openalex.org/W2358326393","https://openalex.org/W2471520273","https://openalex.org/W2515943672","https://openalex.org/W2519091744","https://openalex.org/W2584505851","https://openalex.org/W2763079791","https://openalex.org/W2766557690","https://openalex.org/W2790783922","https://openalex.org/W2901997113","https://openalex.org/W2949382160","https://openalex.org/W2962902328","https://openalex.org/W2963211739","https://openalex.org/W2963609956","https://openalex.org/W2963797754","https://openalex.org/W2964243274","https://openalex.org/W4285719527","https://openalex.org/W4298857617","https://openalex.org/W6632319019","https://openalex.org/W6675365184","https://openalex.org/W6697154816","https://openalex.org/W6736996214","https://openalex.org/W6746700228","https://openalex.org/W6749025659","https://openalex.org/W6792025129","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W2338806053","https://openalex.org/W4200068392","https://openalex.org/W2184371793","https://openalex.org/W39235475","https://openalex.org/W2537969829","https://openalex.org/W2969905756","https://openalex.org/W2565668967","https://openalex.org/W3184592700","https://openalex.org/W2909367404","https://openalex.org/W2157536499"],"abstract_inverted_index":{"Speech":[0],"synthesis,":[1],"or":[2],"text-to-speech":[3],"(TTS),":[4],"generates":[5],"a":[6,15,19,106,116],"speech":[7,22,47,87],"waveform":[8],"of":[9,56,64,109],"the":[10,27,30,39,54,62,73,79,92,96,131,138],"given":[11],"text.":[12],"To":[13],"build":[14],"satisfactory":[16],"TTS":[17,65,81,100,141],"system,":[18,101],"large":[20],"natural":[21],"corpus":[23,31],"is":[24,41,103,125,130],"requested.":[25],"In":[26],"traditional":[28],"approach,":[29],"should":[32],"be":[33,144],"accompanied":[34],"with":[35,115],"precise":[36],"annotations.":[37],"However,":[38],"annotation":[40],"difficult":[42],"and":[43,69],"costly.":[44],"Recently,":[45],"end-to-end":[46,59,75],"synthesis":[48],"methods":[49,60],"are":[50],"proposed,":[51],"which":[52,102,129],"eliminated":[53],"requirement":[55],"annotation.":[57],"The":[58,119,134],"make":[61],"development":[63],"system":[66,94,136,142],"less":[67],"costly":[68],"easier.":[70],"We":[71],"used":[72],"state-of-the-art":[74],"Tacotron":[76],"model":[77],"in":[78,146],"Mongolian":[80,99,140],"task.":[82],"With":[83],"much":[84],"more":[85],"unannotated":[86],"data":[88,111],"(about":[89,112],"17":[90],"hours),":[91,114],"new":[93,120],"beats":[95],"old":[97,132],"best":[98],"trained":[104],"on":[105],"small":[107],"amount":[108],"annotated":[110],"5":[113],"big":[117],"margin.":[118],"mean":[121],"opinion":[122],"score":[123],"(MOS)":[124],"3.65":[126],"vs":[127],"2.08":[128],"one.":[133],"proposed":[135],"becomes":[137],"first":[139],"can":[143],"utilized":[145],"real":[147],"applications.":[148]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}