{"id":"https://openalex.org/W4400123644","doi":"https://doi.org/10.1145/3675397","title":"Optimizing Uyghur Speech Synthesis by Combining Pretrained Cross-Lingual Model","display_name":"Optimizing Uyghur Speech Synthesis by Combining Pretrained Cross-Lingual Model","publication_year":2024,"publication_date":"2024-06-28","ids":{"openalex":"https://openalex.org/W4400123644","doi":"https://doi.org/10.1145/3675397"},"language":"en","primary_location":{"id":"doi:10.1145/3675397","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3675397","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3675397","source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3675397","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088334916","display_name":"Kexin Lu","orcid":"https://orcid.org/0009-0004-8154-4882"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kexin Lu","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0009-0004-8154-4882","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033367964","display_name":"Zhihua Huang","orcid":"https://orcid.org/0009-0001-0973-4401"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihua Huang","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang University, Urumqi, China and Key Laboratory of Signal Detection and Processing in Xinjiang, Xinjiang University, Wulumuqi, China","School of Computer Science and Technology, Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0009-0001-0973-4401","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, Urumqi, China and Key Laboratory of Signal Detection and Processing in Xinjiang, Xinjiang University, Wulumuqi, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083541861","display_name":"Mingming Yin","orcid":"https://orcid.org/0009-0000-4518-6257"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingming Yin","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0009-0000-4518-6257","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115598124","display_name":"Ke Chen","orcid":"https://orcid.org/0009-0005-3069-9769"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Chen","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0009-0005-3069-9769","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":0.8335,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7641359,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"23","issue":"9","first_page":"1","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":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":0.9991000294685364,"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":0.9921000003814697,"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":0.8305302858352661},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6702647805213928},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6676815748214722},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6611857414245605},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5584852695465088},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5238009691238403},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.5140236616134644},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5009841918945312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48806631565093994},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4803161025047302},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.45226991176605225},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41871270537376404},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.10917127132415771},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10669693350791931}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8305302858352661},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6702647805213928},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6676815748214722},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6611857414245605},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5584852695465088},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5238009691238403},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.5140236616134644},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5009841918945312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48806631565093994},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4803161025047302},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.45226991176605225},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41871270537376404},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10917127132415771},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10669693350791931},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3675397","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3675397","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3675397","source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3675397","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3675397","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3675397","source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3510065837","display_name":null,"funder_award_id":"2018YFC0823402","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4400123644.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2107860279","https://openalex.org/W2608207374","https://openalex.org/W2761478804","https://openalex.org/W2889028433","https://openalex.org/W2914120296","https://openalex.org/W2938099940","https://openalex.org/W2964243274","https://openalex.org/W2972772214","https://openalex.org/W2973217961","https://openalex.org/W2990138404","https://openalex.org/W3025165719","https://openalex.org/W3047866127","https://openalex.org/W3150572638","https://openalex.org/W3163793923","https://openalex.org/W3174758275","https://openalex.org/W4200300291","https://openalex.org/W4287368090","https://openalex.org/W4288028050","https://openalex.org/W4289677850","https://openalex.org/W4382202681","https://openalex.org/W4385245566","https://openalex.org/W4395961059","https://openalex.org/W6739901393"],"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/W2535215250","https://openalex.org/W1813881148","https://openalex.org/W1537411440"],"abstract_inverted_index":{"End-to-end":[0],"speech":[1,45],"synthesis":[2],"methodologies":[3],"have":[4],"exhibited":[5],"considerable":[6],"advancements":[7],"for":[8,22],"languages":[9,23],"with":[10,147],"abundant":[11],"corpus":[12],"resources.":[13],"Nevertheless,":[14],"such":[15],"achievements":[16],"are":[17,105],"yet":[18],"to":[19,39,60,70,83,113,130,168],"be":[20],"realized":[21],"constrained":[24],"by":[25,89,153,186],"limited":[26],"corpora.":[27],"This":[28],"manuscript":[29],"delineates":[30],"a":[31,127,156],"novel":[32],"strategy":[33],"that":[34,144],"leverages":[35],"contextual":[36,62],"encoding":[37],"information":[38],"augment":[40],"the":[41,44,56,71,79,85,109,137,148,169,176,182],"naturalness":[42],"of":[43,74,121],"synthesized":[46,164],"through":[47],"FastSpeech2,":[48],"particularly":[49],"under":[50],"resource-scarce":[51],"conditions.":[52],"Initially,":[53],"we":[54,77,125],"harness":[55],"cross-linguistic":[57],"model":[58],"XLM-RoBERTa":[59],"extract":[61],"features,":[63],"which":[64],"serve":[65],"as":[66],"an":[67],"auxiliary":[68],"input":[69],"mel-spectrum":[72,80],"decoder":[73,112],"FastSpeech2.":[75],"Subsequently,":[76],"refine":[78],"prediction":[81],"module":[82],"mitigate":[84],"overfitting":[86],"dilemma":[87],"encountered":[88],"FastSpeech2":[90],"amidst":[91],"scant":[92],"training":[93],"datasets.":[94],"To":[95],"this":[96],"end,":[97],"Conformer":[98],"blocks,":[99,104],"rather":[100],"than":[101],"traditional":[102],"Transformer":[103],"employed":[106],"within":[107],"both":[108],"encoder":[110],"and":[111,119,133,180],"concentrate":[114],"intensively":[115],"on":[116],"varying":[117],"levels":[118],"granularities":[120],"feature":[122],"information.":[123],"Additionally,":[124],"introduce":[126],"token-average":[128],"mechanism":[129],"equalize":[131],"pitch":[132],"energy":[134],"attributes":[135],"at":[136],"frame":[138],"level.":[139],"The":[140],"empirical":[141],"outcomes":[142],"indicate":[143],"our":[145,172],"pre-training":[146],"LJ":[149],"Speech":[150],"dataset,":[151],"followed":[152],"fine-tuning":[154],"using":[155],"modest":[157],"10-minute":[158],"paired":[159],"Uyghur":[160,165],"corpus,":[161],"yields":[162],"satisfactory":[163],"speech.":[166],"Relative":[167],"baseline":[170],"framework,":[171],"proposed":[173],"technique":[174],"halves":[175],"character":[177],"error":[178],"rate":[179],"enhances":[181],"mean":[183],"opinion":[184],"score":[185],"over":[187],"0.6.":[188],"Similar":[189],"results":[190],"were":[191],"observed":[192],"in":[193],"Mandarin":[194],"Chinese":[195],"experimental":[196],"evaluations.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}