{"id":"https://openalex.org/W4400490143","doi":"https://doi.org/10.1109/cscwd61410.2024.10580278","title":"EM-TTS: Efficiently Trained Low-Resource Mongolian Lightweight Text-to-Speech","display_name":"EM-TTS: Efficiently Trained Low-Resource Mongolian Lightweight Text-to-Speech","publication_year":2024,"publication_date":"2024-05-08","ids":{"openalex":"https://openalex.org/W4400490143","doi":"https://doi.org/10.1109/cscwd61410.2024.10580278"},"language":"en","primary_location":{"id":"doi:10.1109/cscwd61410.2024.10580278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cscwd61410.2024.10580278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","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/A5101332887","display_name":"Ziqi Liang","orcid":"https://orcid.org/0009-0002-8003-7681"},"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":"Ziqi Liang","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020364411","display_name":"Haoxiang Shi","orcid":"https://orcid.org/0009-0002-9204-0351"},"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":"Haoxiang Shi","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032557170","display_name":"Jiawei Wang","orcid":"https://orcid.org/0000-0002-0606-5214"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Wang","raw_affiliation_strings":["Hefei University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045007834","display_name":"Keda Lu","orcid":"https://orcid.org/0009-0006-8974-3813"},"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":"Keda Lu","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1134","last_page":"1139"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962999820709229,"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":0.98089998960495,"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":0.7867596745491028},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6509928703308105},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5699842572212219},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5017211437225342},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4475753605365753},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4319138824939728},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.05856215953826904}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7867596745491028},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6509928703308105},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5699842572212219},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5017211437225342},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4475753605365753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4319138824939728},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.05856215953826904}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cscwd61410.2024.10580278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cscwd61410.2024.10580278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W1576227399","https://openalex.org/W2102661631","https://openalex.org/W2120605154","https://openalex.org/W2294797155","https://openalex.org/W2519091744","https://openalex.org/W2560674852","https://openalex.org/W2747329762","https://openalex.org/W2790783922","https://openalex.org/W2937870435","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W3015338123","https://openalex.org/W4280561221","https://openalex.org/W4312564489","https://openalex.org/W4313679638","https://openalex.org/W4361858590","https://openalex.org/W4390075359","https://openalex.org/W6748409065","https://openalex.org/W6763832098","https://openalex.org/W6767111847","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6792476516","https://openalex.org/W6795261426","https://openalex.org/W6796464841","https://openalex.org/W6805710207","https://openalex.org/W6838721020","https://openalex.org/W6840257003","https://openalex.org/W6848735303"],"related_works":["https://openalex.org/W2216757598","https://openalex.org/W4387496629","https://openalex.org/W3013209356","https://openalex.org/W2489800615","https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W3204019825","https://openalex.org/W127416991"],"abstract_inverted_index":{"Recently,":[0],"deep":[1,95],"learning-based":[2],"Text-to-Speech":[3],"(TTS)":[4],"systems":[5,26],"have":[6,15],"achieved":[7],"high-quality":[8],"speech":[9,203],"synthesis":[10,53],"results.":[11],"Recurrent":[12],"neural":[13,97],"networks":[14],"become":[16],"a":[17,33,46,64,69,89,101,131,159,225],"standard":[18],"modeling":[19],"technique":[20],"for":[21,175,216],"sequential":[22],"data":[23,162],"in":[24],"TTS":[25,34,65,91,105,208],"and":[27,44,60,107,121,135,172,192,198],"are":[28],"widely":[29],"used.":[30],"However,":[31],"training":[32,61,103,190,221],"model":[35,66,106,115,157,186],"which":[36,77,99,218],"includes":[37],"RNN":[38],"components":[39],"requires":[40],"powerful":[41],"GPU":[42],"performance":[43,71],"takes":[45],"long":[47],"time.":[48],"In":[49,84],"contrast,":[50],"CNN-based":[51],"sequence":[52],"techniques":[54],"can":[55,187],"significantly":[56,219],"reduce":[57,188],"the":[58,136,142,146,153,177,189,196,201],"parameters":[59,193],"time":[62,168,173,191,222],"of":[63,82,117,155,161,200],"while":[67,194,223],"guaranteeing":[68],"certain":[70,226],"due":[72],"to":[73,127,140,205],"their":[74],"high":[75],"parallelism,":[76],"alleviate":[78],"these":[79],"economic":[80],"costs":[81],"training.":[83],"this":[85],"paper,":[86],"we":[87,151],"propose":[88],"lightweight":[90],"system":[92],"based":[93],"on":[94],"convolutional":[96],"networks,":[98],"is":[100,125,138],"two-stage":[102],"end-to-end":[104],"does":[108],"not":[109],"employ":[110],"any":[111],"recurrent":[112],"units.":[113],"Our":[114,210],"consists":[116],"two":[118],"stages:":[119],"Text2Spectrum":[120],"SSRN.":[122],"The":[123],"former":[124],"used":[126,139],"encode":[128],"phonemes":[129],"into":[130],"coarse":[132,147],"mel":[133,148],"spectrogram":[134],"latter":[137],"synthesize":[141],"complete":[143],"spectrum":[144],"from":[145],"spectrogram.":[149],"Meanwhile,":[150],"improve":[152],"robustness":[154],"our":[156,185],"by":[158],"series":[160],"augmentations,":[163],"such":[164],"as":[165],"noise":[166],"suppression,":[167],"warping,":[169],"frequency":[170],"masking":[171],"masking,":[174],"solving":[176],"low":[178],"resource":[179],"mongolian":[180],"problem.":[181],"Experiments":[182],"show":[183],"that":[184],"ensuring":[195],"quality":[197],"naturalness":[199],"synthesized":[202],"compared":[204],"using":[206],"mainstream":[207],"models.":[209],"method":[211],"uses":[212],"NCMMSC2022-MTTSC":[213],"Challenge":[214],"dataset":[215],"validation,":[217],"reduces":[220],"maintaining":[224],"accuracy.":[227]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}