{"id":"https://openalex.org/W4390480998","doi":"https://doi.org/10.1109/taslp.2023.3348762","title":"Text-to-Speech for Low-Resource Agglutinative Language With Morphology-Aware Language Model Pre-Training","display_name":"Text-to-Speech for Low-Resource Agglutinative Language With Morphology-Aware Language Model Pre-Training","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4390480998","doi":"https://doi.org/10.1109/taslp.2023.3348762"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3348762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3348762","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/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":true,"raw_author_name":"Rui Liu","raw_affiliation_strings":["Department of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":"https://orcid.org/0000-0003-4524-7413","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100708728","display_name":"Yifan Hu","orcid":"https://orcid.org/0009-0004-9393-5004"},"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":["Department of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":"https://orcid.org/0009-0008-2276-1456","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008862741","display_name":"Haolin Zuo","orcid":"https://orcid.org/0009-0000-1412-2883"},"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":"Haolin Zuo","raw_affiliation_strings":["Department of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":"https://orcid.org/0009-0000-1412-2883","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077713342","display_name":"Zhaojie Luo","orcid":"https://orcid.org/0000-0002-4173-6319"},"institutions":[{"id":"https://openalex.org/I4210110027","display_name":"Sanken Electric (Japan)","ror":"https://ror.org/01v07hj96","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210110027"]},{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zhaojie Luo","raw_affiliation_strings":["SANKEN, Osaka University, Osaka, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4173-6319","affiliations":[{"raw_affiliation_string":"SANKEN, Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I4210110027","https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101745213","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-8094-6861"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-8094-6861","affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"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":["Department of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":"https://orcid.org/0009-0005-5513-1192","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5082746577"],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":10.9275,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.98653331,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"1075","last_page":"1087"},"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":0.9991999864578247,"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/naturalness","display_name":"Naturalness","score":0.8454207181930542},{"id":"https://openalex.org/keywords/agglutinative-language","display_name":"Agglutinative language","score":0.8331611156463623},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7256368398666382},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.596307098865509},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.591474175453186},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5564655065536499},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.487913578748703},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42445626854896545},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.38313519954681396},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3770052194595337},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.34757474064826965},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.07708677649497986}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8454207181930542},{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.8331611156463623},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7256368398666382},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.596307098865509},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.591474175453186},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5564655065536499},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.487913578748703},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42445626854896545},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.38313519954681396},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3770052194595337},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.34757474064826965},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.07708677649497986},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3348762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3348762","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.44999998807907104}],"awards":[{"id":"https://openalex.org/G101729752","display_name":null,"funder_award_id":"21300-231510","funder_id":"https://openalex.org/F4320322216","funder_display_name":"Inner Mongolia University"},{"id":"https://openalex.org/G4617505510","display_name":null,"funder_award_id":"62206136","funder_id":"https://openalex.org/F4320331088","funder_display_name":"Natural Science Foundation for Young Scientists of Shanxi Province"}],"funders":[{"id":"https://openalex.org/F4320322216","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496"},{"id":"https://openalex.org/F4320331088","display_name":"Natural Science Foundation for Young Scientists of Shanxi Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W51373460","https://openalex.org/W349236604","https://openalex.org/W1570629387","https://openalex.org/W2091653553","https://openalex.org/W2102003408","https://openalex.org/W2107860279","https://openalex.org/W2111284386","https://openalex.org/W2129142580","https://openalex.org/W2269051851","https://openalex.org/W2515943672","https://openalex.org/W2598638573","https://openalex.org/W2790783922","https://openalex.org/W2884236563","https://openalex.org/W2889026195","https://openalex.org/W2903739847","https://openalex.org/W2952370363","https://openalex.org/W2962784628","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2965373594","https://openalex.org/W2969658393","https://openalex.org/W2972881244","https://openalex.org/W2973034126","https://openalex.org/W2973217961","https://openalex.org/W2994396107","https://openalex.org/W3015922793","https://openalex.org/W3016137096","https://openalex.org/W3022876224","https://openalex.org/W3081416955","https://openalex.org/W3081488690","https://openalex.org/W3096303254","https://openalex.org/W3096656663","https://openalex.org/W3106690208","https://openalex.org/W3161492781","https://openalex.org/W3168542456","https://openalex.org/W3168997536","https://openalex.org/W3195171908","https://openalex.org/W3197287223","https://openalex.org/W3197324626","https://openalex.org/W3202191685","https://openalex.org/W4210690177","https://openalex.org/W4221166168","https://openalex.org/W4225943493","https://openalex.org/W4237871605","https://openalex.org/W4240592325","https://openalex.org/W4243859118","https://openalex.org/W4285182272","https://openalex.org/W4285189120","https://openalex.org/W4296068816","https://openalex.org/W4310608752","https://openalex.org/W4372267432","https://openalex.org/W4376456840","https://openalex.org/W6739901393","https://openalex.org/W6748409065","https://openalex.org/W6749489859","https://openalex.org/W6753212667","https://openalex.org/W6755207826","https://openalex.org/W6755257315","https://openalex.org/W6763832098","https://openalex.org/W6766673545","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W2108985546","https://openalex.org/W2433276473","https://openalex.org/W1531783358","https://openalex.org/W2077992636","https://openalex.org/W1537411440","https://openalex.org/W2535215250","https://openalex.org/W290673751","https://openalex.org/W2017702615"],"abstract_inverted_index":{"Text-to-Speech":[0],"(TTS)":[1],"aims":[2],"to":[3,8,79,88,102,128,141,157],"convert":[4],"the":[5,13,39,45,49,58,61,90,93,124,134,138,143,146,160,172,194,202,208],"input":[6,135],"text":[7,46,86,114,136],"a":[9,111,178],"human-like":[10],"voice.":[11],"With":[12],"development":[14],"of":[15,27,44,54,60,92,137,145,196,201,210],"deep":[16,130],"learning,":[17],"encoder-decoder":[18],"based":[19,181,187],"TTS":[20,53,139,191],"models":[21,192],"perform":[22],"superior":[23],"performance,":[24],"in":[25,29,155,164,213],"terms":[26],"naturalness,":[28],"mainstream":[30],"languages":[31],"such":[32],"as":[33],"Chinese,":[34],"English,":[35],"etc.":[36],"Note":[37],"that":[38,100,154],"linguistic":[40,82,131,162],"information":[41,83,132,163,170],"learning":[42],"capability":[43],"encoder":[47],"is":[48,75,96],"key.":[50],"However,":[51],"for":[52,116,133],"low-resource":[55,214],"agglutinative":[56,165],"languages,":[57,166],"scale":[59],"<inline-formula":[62,69],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[63,70],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[64,71],"notation=\"LaTeX\">$&lt;":[65],"$</tex-math></inline-formula>":[66],"text,":[67],"speech":[68],"notation=\"LaTeX\">$&gt;$</tex-math></inline-formula>":[72],"paired":[73],"data":[74,87,115,204],"limited.":[76],"Therefore,":[77],"how":[78],"extract":[80,129],"rich":[81],"from":[84],"small-scale":[85],"enhance":[89],"naturalness":[91,144],"synthesized":[94,148],"speech,":[95],"an":[97],"urgent":[98],"issue":[99],"needs":[101],"be":[103,152],"addressed.":[104],"In":[105],"this":[106],"paper,":[107],"we":[108,167],"first":[109],"collect":[110],"large":[112],"unsupervised":[113],"BERT-like":[117],"language":[118,126,173],"model":[119,127,140,174,183],"pre-training,":[120],"and":[121,176],"then":[122],"adopt":[123],"trained":[125],"improve":[142],"final":[147],"speech.":[149],"It":[150],"should":[151],"emphasized":[153],"order":[156],"fully":[158],"exploit":[159],"prosody-related":[161],"incorporated":[168],"morphological":[169],"into":[171],"training":[175],"constructed":[177],"morphology-aware":[179],"masking":[180],"BERT":[182],"(MAM-BERT).":[184],"Experimental":[185],"results":[186],"on":[188],"various":[189,203],"advanced":[190],"validate":[193],"effectiveness":[195,209],"our":[197,211],"approach.":[198],"Further":[199],"comparison":[200],"scales":[205],"also":[206],"validates":[207],"approach":[212],"scenarios.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}