{"id":"https://openalex.org/W4310608752","doi":"https://doi.org/10.1109/ialp57159.2022.9961271","title":"MnTTS: An Open-Source Mongolian Text-to-Speech Synthesis Dataset and Accompanied Baseline","display_name":"MnTTS: An Open-Source Mongolian Text-to-Speech Synthesis Dataset and Accompanied Baseline","publication_year":2022,"publication_date":"2022-10-27","ids":{"openalex":"https://openalex.org/W4310608752","doi":"https://doi.org/10.1109/ialp57159.2022.9961271"},"language":"en","primary_location":{"id":"doi:10.1109/ialp57159.2022.9961271","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp57159.2022.9961271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100708728","display_name":"Yifan Hu","orcid":"https://orcid.org/0009-0008-2276-1456"},"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":"Yifan Hu","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University,Hohhot,China","Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China","National & Local Joint Engineering Research Center of Mongolian Intelligent Information Processing, Hohhot, China","College of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China","institution_ids":[]},{"raw_affiliation_string":"National & Local Joint Engineering Research Center of Mongolian Intelligent Information Processing, Hohhot, China","institution_ids":[]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072602270","display_name":"Pengkai Yin","orcid":null},"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":"Pengkai Yin","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University,Hohhot,China","National & Local Joint Engineering Research Center of Mongolian Intelligent Information Processing, Hohhot, China","College of Computer Science, Inner Mongolia University, Hohhot, China","Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"National & Local Joint Engineering Research Center of Mongolian Intelligent Information Processing, Hohhot, China","institution_ids":[]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China","institution_ids":[]}]},{"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":["College of Computer Science, Inner Mongolia University,Hohhot,China","College of Computer Science, Inner Mongolia University, Hohhot, China","Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China","National & Local Joint Engineering Research Center of Mongolian Intelligent Information Processing, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China","institution_ids":[]},{"raw_affiliation_string":"National & Local Joint Engineering Research Center of Mongolian Intelligent Information Processing, Hohhot, China","institution_ids":[]}]},{"author_position":"middle","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":["College of Computer Science, Inner Mongolia University,Hohhot,China","College of Computer Science, Inner Mongolia University, Hohhot, China","Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China","National & Local Joint Engineering Research Center of Mongolian Intelligent Information Processing, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China","institution_ids":[]},{"raw_affiliation_string":"National & Local Joint Engineering Research Center of Mongolian Intelligent Information Processing, Hohhot, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"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":"Guanglai Gao","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University,Hohhot,China","National & Local Joint Engineering Research Center of Mongolian Intelligent Information Processing, Hohhot, China","College of Computer Science, Inner Mongolia University, Hohhot, China","Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"National & Local Joint Engineering Research Center of Mongolian Intelligent Information Processing, Hohhot, China","institution_ids":[]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"184","last_page":"189"},"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":0.9988999962806702,"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":0.9933000206947327,"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/baseline","display_name":"Baseline (sea)","score":0.7363643050193787},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.665244460105896},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5411211252212524},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5262621641159058},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5178309082984924},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.48111218214035034},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.43533551692962646},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42918121814727783},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4173696041107178},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.41520634293556213},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33608075976371765},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10673537850379944},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07615914940834045}],"concepts":[{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.7363643050193787},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.665244460105896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5411211252212524},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5262621641159058},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5178309082984924},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.48111218214035034},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.43533551692962646},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42918121814727783},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4173696041107178},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.41520634293556213},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33608075976371765},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10673537850379944},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07615914940834045},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"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/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp57159.2022.9961271","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp57159.2022.9961271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5435010561","display_name":null,"funder_award_id":"2018YFE0122900","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G600008135","display_name":null,"funder_award_id":"62206136","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"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1570629387","https://openalex.org/W1701606884","https://openalex.org/W1975163393","https://openalex.org/W2006267643","https://openalex.org/W2152859600","https://openalex.org/W2591927543","https://openalex.org/W2795109282","https://openalex.org/W2884236563","https://openalex.org/W2889028433","https://openalex.org/W2901997113","https://openalex.org/W2903739847","https://openalex.org/W2944622002","https://openalex.org/W2946200149","https://openalex.org/W2952711665","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2972359262","https://openalex.org/W2973034126","https://openalex.org/W2994396107","https://openalex.org/W3015278429","https://openalex.org/W3033411150","https://openalex.org/W3092028330","https://openalex.org/W3094002217","https://openalex.org/W3106690208","https://openalex.org/W3126473426","https://openalex.org/W3174758275","https://openalex.org/W4205087900","https://openalex.org/W4295731579","https://openalex.org/W6734815144","https://openalex.org/W6761297928","https://openalex.org/W6762242920","https://openalex.org/W6763832098","https://openalex.org/W6767111847","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6785090365","https://openalex.org/W6796730497"],"related_works":["https://openalex.org/W2031768607","https://openalex.org/W3164858600","https://openalex.org/W3109498233","https://openalex.org/W127416991","https://openalex.org/W2151415191","https://openalex.org/W4200068392","https://openalex.org/W4297798732","https://openalex.org/W2151664070","https://openalex.org/W4205278983","https://openalex.org/W4298324454"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,12,37,86],"high-quality":[4],"open-source":[5],"text-to-speech":[6],"(TTS)":[7],"synthesis":[8],"dataset":[9,49,71,125],"for":[10,142],"Mongolian,":[11],"low-resource":[13],"language":[14],"spoken":[15,35],"by":[16,36,68],"over":[17],"10":[18],"million":[19],"people":[20],"worldwide.":[21],"The":[22,145],"dataset,":[23,83,146],"named":[24],"MnTTS,":[25],"consists":[26],"of":[27,31,81],"about":[28,132],"8":[29],"hours":[30],"transcribed":[32],"audio":[33],"recordings":[34],"22-year-old":[38],"professional":[39],"female":[40],"Mongolian":[41,53],"announcer.":[42],"It":[43],"is":[44],"the":[45,70,79,102,118],"first":[46],"publicly":[47],"available":[48,155],"developed":[50],"to":[51],"promote":[52],"TTS":[54,151],"applications":[55],"in":[56],"both":[57],"academia":[58],"and":[59,74,95,98,108,130,149],"industry.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64,84],"share":[65],"our":[66,82,124],"experience":[67],"describing":[69],"development":[72],"procedures":[73],"faced":[75],"challenges.":[76],"To":[77],"demonstrate":[78],"reliability":[80],"built":[85],"powerful":[87,119],"non-autoregressive":[88],"baseline":[89,120],"system":[90,121],"based":[91],"on":[92,123],"FastSpeech2":[93],"model":[94],"HiFi-GAN":[96],"vocoder,":[97],"evaluated":[99],"it":[100,140],"using":[101],"subjective":[103],"mean":[104],"opinion":[105],"score":[106],"(MOS)":[107],"real":[109],"time":[110],"factor":[111],"(RTF)":[112],"metrics.":[113],"Evaluation":[114],"results":[115],"show":[116],"that":[117],"trained":[122],"achieves":[126],"MOS":[127],"above":[128],"4":[129],"RTF":[131],"3.30\u00d710":[133],"<sup":[134,156,159],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[135,157,160],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">\u22121</sup>":[136],",":[137],"which":[138],"makes":[139],"applicable":[141],"practical":[143],"use.":[144],"training":[147],"recipe,":[148],"pretrained":[150],"models":[152],"are":[153],"freely":[154],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[158,161],"https://github.com/walker-hyf/MnTTS.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}