{"id":"https://openalex.org/W3130965709","doi":"https://doi.org/10.1109/icassp39728.2021.9414912","title":"Neural Inverse Text Normalization","display_name":"Neural Inverse Text Normalization","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3130965709","doi":"https://doi.org/10.1109/icassp39728.2021.9414912","mag":"3130965709"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.06380","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014130267","display_name":"Monica Sunkara","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Monica Sunkara","raw_affiliation_strings":["Amazon AWS AI","[Amazon AWS AI]"],"affiliations":[{"raw_affiliation_string":"Amazon AWS AI","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"[Amazon AWS AI]","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076250439","display_name":"Chaitanya Shivade","orcid":"https://orcid.org/0000-0001-6604-1129"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chaitanya Shivade","raw_affiliation_strings":["Amazon AWS AI","[Amazon AWS AI]"],"affiliations":[{"raw_affiliation_string":"Amazon AWS AI","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"[Amazon AWS AI]","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050552820","display_name":"Sravan Bodapati","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sravan Bodapati","raw_affiliation_strings":["Amazon AWS AI","[Amazon AWS AI]"],"affiliations":[{"raw_affiliation_string":"Amazon AWS AI","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"[Amazon AWS AI]","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050325468","display_name":"Katrin Kirchhoff","orcid":"https://orcid.org/0000-0002-6645-6030"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katrin Kirchhoff","raw_affiliation_strings":["Amazon AWS AI","[Amazon AWS AI]"],"affiliations":[{"raw_affiliation_string":"Amazon AWS AI","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"[Amazon AWS AI]","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014130267"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.42331073,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66774496,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7573","last_page":"7577"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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":0.9977999925613403,"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":0.8024803996086121},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7134405374526978},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6501445174217224},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6205331087112427},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.5065609216690063},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4834774136543274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4501854181289673},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42096102237701416},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3694803714752197},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.340457558631897},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1161927878856659},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.10313603281974792},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.07506859302520752},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07404708862304688}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8024803996086121},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7134405374526978},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6501445174217224},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6205331087112427},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5065609216690063},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4834774136543274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4501854181289673},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42096102237701416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3694803714752197},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.340457558631897},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1161927878856659},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.10313603281974792},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.07506859302520752},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07404708862304688},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.06380","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.06380","pdf_url":"https://arxiv.org/pdf/2102.06380","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"mag:3130965709","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2102.06380.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2102.06380","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.06380","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/c3yq-hs86","is_oa":true,"landing_page_url":"https://doi.org/10.17023/c3yq-hs86","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.06380","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.06380","pdf_url":"https://arxiv.org/pdf/2102.06380","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3130965709.pdf","grobid_xml":"https://content.openalex.org/works/W3130965709.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W145178388","https://openalex.org/W1704572586","https://openalex.org/W2546744831","https://openalex.org/W2550821151","https://openalex.org/W2606974598","https://openalex.org/W2749051922","https://openalex.org/W2807022326","https://openalex.org/W2916997151","https://openalex.org/W2945656493","https://openalex.org/W2945700568","https://openalex.org/W2952913664","https://openalex.org/W2962739339","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2964308564","https://openalex.org/W2965373594","https://openalex.org/W2970076840","https://openalex.org/W2972880214","https://openalex.org/W2982399380","https://openalex.org/W3006381853","https://openalex.org/W3015722595","https://openalex.org/W3015752032","https://openalex.org/W3016252185","https://openalex.org/W6605854414","https://openalex.org/W6679434410","https://openalex.org/W6729005282","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6762471609","https://openalex.org/W6766673545","https://openalex.org/W6769311223","https://openalex.org/W6771713106","https://openalex.org/W6775945549"],"related_works":["https://openalex.org/W3160789530","https://openalex.org/W3166601111","https://openalex.org/W3102726551","https://openalex.org/W3165075898","https://openalex.org/W2974111094","https://openalex.org/W2626769175","https://openalex.org/W3132772989","https://openalex.org/W2971694752","https://openalex.org/W3129976344","https://openalex.org/W3175011263","https://openalex.org/W3084368726","https://openalex.org/W3093667565","https://openalex.org/W3080683114","https://openalex.org/W2949541269","https://openalex.org/W2914277910","https://openalex.org/W3089390372","https://openalex.org/W3027803578","https://openalex.org/W3037308981","https://openalex.org/W2616526340","https://openalex.org/W2061064548"],"abstract_inverted_index":{"While":[0],"there":[1],"have":[2],"been":[3],"several":[4,154],"contributions":[5],"exploring":[6],"state":[7,31],"of":[8,17,138],"the":[9,15,82,118],"art":[10],"techniques":[11,66],"for":[12,55,67,84,98],"text":[13,19,64],"normalization,":[14],"problem":[16],"inverse":[18],"normalization":[20,65],"(ITN)":[21],"remains":[22],"relatively":[23],"unexplored.":[24],"The":[25],"best":[26],"known":[27],"approaches":[28],"leverage":[29],"finite":[30],"transducer":[32],"(FST)":[33],"based":[34,59,143],"models":[35,61],"which":[36],"rely":[37],"on":[38,136,162],"manually":[39,89],"curated":[40],"rules":[41],"and":[42,51,62,126,131,156,166],"are":[43],"hence":[44],"not":[45],"scalable.":[46],"We":[47,70,92],"propose":[48],"an":[49,103],"efficient":[50],"robust":[52],"neural":[53],"solution":[54,120],"ITN":[56,101],"leveraging":[57],"transformer":[58,142],"seq2seq":[60],"FST-based":[63],"data":[68],"preparation.":[69],"show":[71,116],"that":[72,117],"this":[73],"can":[74],"be":[75],"easily":[76],"extended":[77],"to":[78,88,105,128,159],"other":[79],"languages":[80],"without":[81],"need":[83],"a":[85,95,150],"linguistic":[86],"expert":[87],"curate":[90],"them.":[91],"then":[93],"present":[94],"hybrid":[96],"framework":[97],"integrating":[99],"Neural":[100],"with":[102,146],"FST":[104],"overcome":[106],"common":[107],"recoverable":[108],"errors":[109],"in":[110],"production":[111],"environments.":[112],"Our":[113],"empirical":[114],"evaluations":[115],"proposed":[119],"minimizes":[121],"incorrect":[122],"perturbations":[123],"(insertions,":[124],"deletions":[125],"substitutions)":[127],"ASR":[129],"output":[130],"maintains":[132],"high":[133],"quality":[134],"even":[135],"out":[137],"domain":[139],"data.":[140],"A":[141],"model":[144],"infused":[145],"pretraining":[147],"consistently":[148],"achieves":[149],"lower":[151],"WER":[152],"across":[153],"datasets":[155],"is":[157],"able":[158],"outperform":[160],"baselines":[161],"English,":[163],"Spanish,":[164],"German":[165],"Italian":[167],"datasets.":[168]},"counts_by_year":[{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}