{"id":"https://openalex.org/W197865384","doi":"https://doi.org/10.21437/interspeech.2008-570","title":"A language-modeling approach to inverse text normalization and data cleanup for multimodal voice search applications","display_name":"A language-modeling approach to inverse text normalization and data cleanup for multimodal voice search applications","publication_year":2008,"publication_date":"2008-09-22","ids":{"openalex":"https://openalex.org/W197865384","doi":"https://doi.org/10.21437/interspeech.2008-570","mag":"197865384"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2008-570","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"},"type":"conference-paper","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/A5108388457","display_name":"Yun\u2010Cheng Ju","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun-Cheng Ju","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108501599","display_name":"J. J. Odell","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Julian Odell","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7554,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.65928404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2179","last_page":"2182"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.8480287790298462},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.8271953463554382},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7203136682510376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5816748738288879},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5579779744148254},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3783191442489624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8480287790298462},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8271953463554382},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7203136682510376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5816748738288879},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5579779744148254},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3783191442489624},{"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":2,"locations":[{"id":"doi:10.21437/interspeech.2008-570","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.725.6496","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.725.6496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cslu.ogi.edu/%7Esproatr/Courses/TextNorm/Papers/IS080913.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W179719456","https://openalex.org/W1522352264","https://openalex.org/W1559453099","https://openalex.org/W2024490156","https://openalex.org/W2040681044","https://openalex.org/W2099832642","https://openalex.org/W2142278517","https://openalex.org/W2145378002","https://openalex.org/W2166799778","https://openalex.org/W2169434751"],"related_works":["https://openalex.org/W2591697403","https://openalex.org/W2953716828","https://openalex.org/W2904857019","https://openalex.org/W2944728705","https://openalex.org/W3011538607","https://openalex.org/W2904022177","https://openalex.org/W2359348847","https://openalex.org/W4321441197","https://openalex.org/W4294432981","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"address":[4],"two":[5],"related":[6],"challenges":[7],"in":[8,99],"multimodal":[9],"local":[10],"search":[11],"applications":[12],"on":[13,50],"mobile":[14],"devices:":[15],"first,":[16],"correctly":[17],"displaying":[18],"the":[19,36,43,51,65],"business":[20],"names,":[21],"and":[22,42],"second,":[23],"harvesting":[24],"language":[25,46,60,82,88,108],"model":[26,47,61,83,89],"training":[27,48,84],"data":[28],"from":[29],"an":[30],"inconsistently":[31],"labeled":[32],"corpus.":[33],"We":[34,56],"investigate":[35],"impact":[37],"of":[38,45,53],"common":[39],"text":[40,70,103,106],"normalization":[41],"quality":[44],"corpus":[49],"accuracy":[52],"displayed":[54],"results.":[55],"propose":[57],"a":[58],"new":[59,87],"framework":[62,74],"that":[63],"eliminates":[64],"need":[66],"for":[67],"explicit":[68],"inverse":[69,105],"normalization.":[71],"The":[72],"same":[73],"can":[75],"be":[76],"applied":[77],"to":[78],"sift":[79],"through":[80],"corrupted":[81],"data.":[85],"Our":[86],"is":[90],"25":[91,96],"%":[92,97],"more":[93],"accurate":[94],"while":[95],"smaller":[98],"size.":[100],"Index":[101],"Terms:":[102],"normalization,":[104,107],"model,":[109],"multimodal,":[110],"voice":[111],"search,":[112],"transduction,":[113]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}