{"id":"https://openalex.org/W4400111169","doi":"https://doi.org/10.1109/taslp.2024.3407509","title":"Zero-Shot Text Normalization via Cross-Lingual Knowledge Distillation","display_name":"Zero-Shot Text Normalization via Cross-Lingual Knowledge Distillation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4400111169","doi":"https://doi.org/10.1109/taslp.2024.3407509"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3407509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3407509","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/A5102915267","display_name":"Linqin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linqin Wang","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"],"raw_orcid":"https://orcid.org/0009-0000-0700-5152","affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106405317","display_name":"Xiang Huang","orcid":"https://orcid.org/0000-0003-3425-5629"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Huang","raw_affiliation_strings":["School of Cyber Science and Technology, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3425-5629","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100619287","display_name":"Zhengtao Yu","orcid":"https://orcid.org/0000-0002-4012-461X"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengtao Yu","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"],"raw_orcid":"https://orcid.org/0000-0002-4012-461X","affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100740622","display_name":"Hao Peng","orcid":"https://orcid.org/0000-0003-0458-5977"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Peng","raw_affiliation_strings":["School of Cyber Science and Technology, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0458-5977","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017471172","display_name":"Shengxiang Gao","orcid":"https://orcid.org/0000-0002-2980-8420"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengxiang Gao","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"],"raw_orcid":"https://orcid.org/0000-0002-2980-8420","affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016947527","display_name":"Cunli Mao","orcid":"https://orcid.org/0000-0002-8289-6036"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cunli Mao","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"],"raw_orcid":"https://orcid.org/0000-0002-8289-6036","affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102000307","display_name":"Yuxin Huang","orcid":"https://orcid.org/0000-0003-1277-6212"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Huang","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"],"raw_orcid":"https://orcid.org/0000-0003-1277-6212","affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068973438","display_name":"Ling Dong","orcid":"https://orcid.org/0000-0003-1612-6671"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling Dong","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036357902","display_name":"Philip S. Yu","orcid":"https://orcid.org/0000-0002-3491-5968"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip S. Yu","raw_affiliation_strings":["Department of Computer Science, University of Illinois, Chicago, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-3491-5968","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois, Chicago, IL, USA","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6671,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.85909462,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"32","issue":null,"first_page":"4631","last_page":"4646"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9279000163078308,"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":0.9279000163078308,"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":0.9136999845504761,"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/normalization","display_name":"Normalization (sociology)","score":0.7476087808609009},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5731710195541382},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5380364060401917},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.45683830976486206},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.43185538053512573},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.39571669697761536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37157320976257324},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3499090373516083},{"id":"https://openalex.org/keywords/engineering-drawing","display_name":"Engineering drawing","score":0.3409014046192169},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.3259708881378174},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.23798593878746033},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.20668411254882812},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.16508269309997559},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1370951533317566},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12756291031837463},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.1050642728805542}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7476087808609009},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5731710195541382},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5380364060401917},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.45683830976486206},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43185538053512573},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.39571669697761536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37157320976257324},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3499090373516083},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.3409014046192169},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.3259708881378174},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.23798593878746033},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.20668411254882812},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.16508269309997559},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1370951533317566},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12756291031837463},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.1050642728805542},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3407509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3407509","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1629199664","https://openalex.org/W2103085228","https://openalex.org/W2747175885","https://openalex.org/W2766585573","https://openalex.org/W2806253224","https://openalex.org/W2895605766","https://openalex.org/W2896457183","https://openalex.org/W2924677654","https://openalex.org/W2945656493","https://openalex.org/W2962902328","https://openalex.org/W2997124358","https://openalex.org/W3002226419","https://openalex.org/W3021663125","https://openalex.org/W3034368386","https://openalex.org/W3034528892","https://openalex.org/W3154516348","https://openalex.org/W3161730088","https://openalex.org/W3169035567","https://openalex.org/W3187295906","https://openalex.org/W3198739096","https://openalex.org/W4224914527","https://openalex.org/W4285298768","https://openalex.org/W4290065441","https://openalex.org/W4296070391","https://openalex.org/W4307959803","https://openalex.org/W4385245566","https://openalex.org/W4389518652","https://openalex.org/W4391620705","https://openalex.org/W6631190155","https://openalex.org/W6682082992","https://openalex.org/W6684316753","https://openalex.org/W6760837195","https://openalex.org/W6766673545","https://openalex.org/W6773695642","https://openalex.org/W6800762109","https://openalex.org/W6852909395"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2591697403"],"abstract_inverted_index":{"Text":[0],"normalization":[1,237],"(TN)":[2],"is":[3,86,160,174,212],"a":[4,45,64,106,147,153,163,234],"crucial":[5],"preprocessing":[6],"step":[7],"in":[8,33,55,80,166,198,239,253,263,278],"text-to-speech":[9],"synthesis,":[10],"which":[11,51,116],"pertains":[12],"to":[13,120,131,214],"the":[14,22,83,89,122,133,167,171,179,186,199,207,220,225,257,267,274,281],"accurate":[15],"pronunciation":[16],"of":[17,48,206],"numbers":[18],"and":[19,41,128,182,228,260],"symbols":[20],"within":[21],"text.":[23],"Existing":[24],"neural":[25,93,150,208],"network-based":[26],"TN":[27,72,94,109,154,248],"methods":[28,38,95],"have":[29],"shown":[30],"significant":[31],"success":[32],"rich-resource":[34,126],"languages.":[35,241],"However,":[36],"these":[37],"are":[39,52,63],"data-driven":[40],"highly":[42],"rely":[43],"on":[44,112,125,136,250],"large":[46],"number":[47],"labeled":[49,284],"datasets,":[50],"not":[53],"practical":[54],"zero-resource":[56,137,216],"settings.":[57],"Rule-based":[58],"weighted":[59],"finite-state":[60],"transducers":[61],"(WFST)":[62],"common":[65],"measure":[66],"for":[67,224,256,266,283],"zero-shot":[68,108,235,247,261],"TN,":[69],"but":[70],"WFST-based":[71],"approaches":[73],"encounter":[74],"challenges":[75],"with":[76,156,245],"ambiguous":[77],"input,":[78],"particularly":[79],"cases":[81],"where":[82],"normalized":[84],"form":[85],"context-dependent.":[87],"On":[88],"other":[90],"hand,":[91],"conventional":[92],"suffer":[96],"from":[97,144,178,185],"unrecoverable":[98,204],"errors.":[99],"In":[100],"this":[101],"paper,":[102],"we":[103,194],"propose":[104],"ZSTN,":[105],"novel":[107],"framework":[110],"based":[111],"cross-lingual":[113,191],"knowledge":[114,143,148,192],"distillation,":[115,193],"utilizes":[117],"annotated":[118],"data":[119,130],"train":[121,132],"teacher":[123,164,180,226,258],"model":[124,135,155,165,173,181,227,259],"language":[127],"unlabelled":[129],"student":[134,172,268],"language.":[138,169,188],"Furthermore,":[139],"it":[140],"incorporates":[141],"expert":[142],"WFST":[145,157,183,202,229],"into":[146],"distillation":[149],"network.":[151],"Concretely,":[152],"pseudo-labels":[158,184],"augmentation":[159],"trained":[161],"as":[162],"source":[168],"Subsequently,":[170],"supervised":[175],"by":[176,218],"soft-labels":[177],"target":[187],"By":[189],"leveraging":[190],"address":[195],"contextual":[196],"ambiguity":[197],"text,":[200],"while":[201],"mitigates":[203],"errors":[205],"model.":[209,269],"Additionally,":[210],"ZSTN":[211,244,276],"adaptable":[213],"different":[215],"languages":[217,255,265],"using":[219],"joint":[221],"loss":[222],"function":[223],"constraints.":[230],"We":[231,242],"also":[232],"release":[233],"text":[236],"dataset":[238],"five":[240,264],"compare":[243],"seven":[246],"benchmarks":[249],"public":[251],"datasets":[252,262],"four":[254],"The":[270],"results":[271],"demonstrate":[272],"that":[273],"proposed":[275],"excels":[277],"performance":[279],"without":[280],"need":[282],"data.":[285]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
