{"id":"https://openalex.org/W4392254146","doi":"https://doi.org/10.1145/3639479.3639516","title":"Watch Your English Language: Text Normalization from Written Expressions to Spoken Forms","display_name":"Watch Your English Language: Text Normalization from Written Expressions to Spoken Forms","publication_year":2023,"publication_date":"2023-12-27","ids":{"openalex":"https://openalex.org/W4392254146","doi":"https://doi.org/10.1145/3639479.3639516"},"language":"en","primary_location":{"id":"doi:10.1145/3639479.3639516","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639479.3639516","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639479.3639516","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 6th International Conference on Machine Learning and Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3639479.3639516","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101538277","display_name":"Yufeng Jiang","orcid":"https://orcid.org/0009-0009-1159-1102"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yufeng Jiang","raw_affiliation_strings":["Xidian University, Xidian University, China"],"raw_orcid":"https://orcid.org/0009-0009-1159-1102","affiliations":[{"raw_affiliation_string":"Xidian University, Xidian University, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101538277"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24809956,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"177","last_page":"181"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.38280001282691956,"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":0.38280001282691956,"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":0.7869589328765869},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.774999737739563},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6745489835739136},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.6076656579971313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5327798128128052},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4298766851425171},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39551854133605957},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.04937624931335449}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7869589328765869},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.774999737739563},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6745489835739136},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6076656579971313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5327798128128052},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4298766851425171},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39551854133605957},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.04937624931335449},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3639479.3639516","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639479.3639516","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639479.3639516","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 6th International Conference on Machine Learning and Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3639479.3639516","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639479.3639516","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639479.3639516","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 6th International Conference on Machine Learning and Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392254146.pdf","grobid_xml":"https://content.openalex.org/works/W4392254146.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2591697403","https://openalex.org/W2944728705","https://openalex.org/W2904022177","https://openalex.org/W2359348847","https://openalex.org/W3011538607","https://openalex.org/W4294432981","https://openalex.org/W4321441197","https://openalex.org/W2953716828","https://openalex.org/W2469820710","https://openalex.org/W633922780"],"abstract_inverted_index":{"Based":[0],"on":[1,11,25],"the":[2,20,42,46,73,76,90,93,98,103,110,115,155,175,182,212,222],"existing":[3],"research":[4],"results":[5,223],"for":[6],"speech-to-text":[7],"and":[8,49,66,83,162,169,194,217,240],"methods":[9],"based":[10,24],"statistical":[12],"modelling,":[13],"machine":[14,26],"learning,":[15],"etc.,":[16],"this":[17],"paper":[18],"applied":[19],"feature":[21,183],"engineering":[22,184],"method":[23],"learning":[27],"to":[28,128,171],"speech-totext,":[29],"converting":[30],"English":[31],"text":[32,85],"from":[33],"written":[34],"expressions":[35],"into":[36],"spoken":[37],"forms.":[38],"First,":[39],"I":[40,59,71,79,123,153,180,199,220],"preprocessed":[41],"data,":[43,229],"including":[44,211],"calculating":[45],"file":[47],"structure":[48],"contenthad,":[50],"missing":[51],"values":[52],"as":[53,55,107,109,159,164,166],"well":[54,108,165],"reformating":[56],"features.":[57],"Next":[58],"had":[60],"a":[61,125,133,197,202,206,231],"look":[62],"at":[63],"normalized":[64,167],"sentences":[65],"overview":[67,138],"visualizations.":[68],"And":[69],"then":[70],"researched":[72,80],"impact":[74],"of":[75,89,119,148,177,186,208,236],"normalization.":[77],"Moreover,":[78],"token":[81,136,190],"classes":[82],"their":[84],"normalization,":[86,243],"which":[87],"compose":[88],"\"PLAIN\"":[91],"(modifications),":[92],"\"PUNCT\"":[94],"(punctuation),":[95],"numerical":[96],"classes,":[97,163],"\"LETTERS\"":[99],"(acronyms":[100],"anhd":[101],"initials),":[102],"\"VERBATIM\"":[104],"(special":[105],"symbols)":[106],"\"ELECTRONIC\"":[111],"(websites)":[112],"class,":[113],"with":[114,224],"most":[116],"frequent":[117],"transformations":[118],"each":[120],"class.":[121],"Meanwhile,":[122],"did":[124,181,201],"next-neighbour":[126],"analysis":[127],"prove":[129],"that":[130],"context":[131],"matters":[132],"lot,":[134],"inlcuding":[135],"class":[137,213],"-":[139,205],"previous":[140],"vs":[141],"next,":[142],"treemap":[143],"overviews":[144],"relative":[145],"percentages,":[146],"exploration":[147],"all":[149],"neighbour":[150],"relations.":[151],"Then,":[152],"analysed":[154],"transformation":[156],"statistics,":[157],"such":[158],"sentence":[160],"length":[161],"tokens":[168,193],"where":[170],"found":[172],"them.":[173],"On":[174],"basis":[176],"these":[178],"foundings,":[179],"composing":[185],"string":[187],"length,":[188],"class-specific":[189],"distance,":[191],"numeric":[192],"what\u2019s":[195],"in":[196],"name.":[198],"also":[200],"case":[203],"study":[204],"tale":[207],"four":[209],"twos,":[210],"\"CARDINAL\",":[214],"\"ORDINAL\",":[215],"\"LETTERS\",":[216],"\"PLAIN\".":[218],"Ultimately,":[219],"evaluated":[221],"11.11":[225],"MB":[226],"size":[227],"test":[228],"getting":[230],"extremely":[232],"high":[233],"accuracy":[234],"score":[235],"99.776Additional":[237],"Key":[238],"Words":[239],"Phrases:":[241],"Text":[242],"Text-to-speechFeature":[244],"engineering,":[245],"Tok":[246]},"counts_by_year":[],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}