{"id":"https://openalex.org/W4308245331","doi":"https://doi.org/10.48550/arxiv.2211.01948","title":"Efficiently Trained Low-Resource Mongolian Text-to-Speech System Based On FullConv-TTS","display_name":"Efficiently Trained Low-Resource Mongolian Text-to-Speech System Based On FullConv-TTS","publication_year":2022,"publication_date":"2022-10-24","ids":{"openalex":"https://openalex.org/W4308245331","doi":"https://doi.org/10.48550/arxiv.2211.01948"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2211.01948","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.01948","pdf_url":"https://arxiv.org/pdf/2211.01948","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2211.01948","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076355208","display_name":"ZiQi Liang","orcid":null,"observed_orcids":[]},"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":true,"raw_author_name":"Liang, Ziqi","raw_affiliation_strings":["University of Science and Technology of China , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China , China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5076355208"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T10860","display_name":"Speech and Audio Processing","score":9.999999747378752e-05,"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"}},{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.9229999780654907},{"id":"https://openalex.org/keywords/mongolian-language","display_name":"Mongolian language","score":0.8669999837875366},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.8379999995231628},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.8840000033378601},{"id":"https://openalex.org/keywords/training-efficiency","display_name":"training efficiency","score":0.6470000147819519},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.9580000042915344},{"id":"https://openalex.org/keywords/time-warping","display_name":"time warping","score":0.9470000267028809},{"id":"https://openalex.org/keywords/frequency-masking","display_name":"frequency masking","score":0.9269999861717224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8410776853561401},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6799924969673157},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6527011394500732},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6392213106155396},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.5787243843078613},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5119701623916626},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.475579172372818},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45086345076560974},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.42254793643951416},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4161857068538666},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4158831238746643},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3070296049118042},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2211.01948","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.01948","pdf_url":"https://arxiv.org/pdf/2211.01948","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2211.01948","doi":"https://doi.org/10.48550/arxiv.2211.01948","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2211.01948","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2211.01948","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.01948","pdf_url":"https://arxiv.org/pdf/2211.01948","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2045049461","https://openalex.org/W1978893398","https://openalex.org/W2201908702","https://openalex.org/W4381094582","https://openalex.org/W2369625323","https://openalex.org/W2364579609","https://openalex.org/W1977906818","https://openalex.org/W1522139108","https://openalex.org/W2353528968","https://openalex.org/W2032776242"],"abstract_inverted_index":{"Recurrent":[0],"Neural":[1],"Networks":[2],"(RNNs)":[3],"have":[4,45],"become":[5],"the":[6,92,97,126,131,136,141,150,153],"standard":[7],"modeling":[8],"technique":[9],"for":[10,34],"sequence":[11,49],"data,":[12],"and":[13,37,99,117],"are":[14],"used":[15],"in":[16,57],"a":[17,25,39,62,72,105],"number":[18],"of":[19,101,107,152],"novel":[20],"text-to-speech":[21,58,74],"models.":[22],"However,":[23],"training":[24,55,137],"TTS":[26,127,143],"model":[27,103,128],"including":[28],"RNN":[29,87],"components":[30,88],"has":[31],"certain":[32,63],"requirements":[33],"GPU":[35],"performance":[36,64],"takes":[38],"long":[40],"time.":[41],"In":[42],"contrast,":[43],"studies":[44],"shown":[46],"that":[47,82,125],"CNN-based":[48],"synthesis":[50],"technology":[51],"can":[52,134],"greatly":[53],"reduce":[54,135],"time":[56,138],"models":[59,144],"while":[60,148],"ensuring":[61,149],"due":[65],"to":[66,140],"its":[67],"high":[68],"parallelism.":[69],"We":[70],"propose":[71],"new":[73],"system":[75],"based":[76],"on":[77],"deep":[78],"convolutional":[79],"neural":[80],"networks":[81],"does":[83],"not":[84],"employ":[85],"any":[86],"(recurrent":[89],"units).":[90],"At":[91],"same":[93],"time,":[94],"we":[95],"improve":[96],"generality":[98],"robustness":[100],"our":[102],"through":[104],"series":[106],"data":[108],"augmentation":[109],"methods":[110],"such":[111,145],"as":[112,146],"Time":[113,118],"Warping,":[114],"Frequency":[115],"Mask,":[116],"Mask.":[119],"The":[120],"final":[121],"experimental":[122],"results":[123],"show":[124],"using":[129],"only":[130],"CNN":[132],"component":[133],"compared":[139],"classic":[142],"Tacotron":[147],"quality":[151],"synthesized":[154],"speech.":[155]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2025-10-10T00:00:00"}