{"id":"https://openalex.org/W4296070391","doi":"https://doi.org/10.21437/interspeech.2022-11074","title":"Shallow Fusion of Weighted Finite-State Transducer and Language Model for Text Normalization","display_name":"Shallow Fusion of Weighted Finite-State Transducer and Language Model for Text Normalization","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296070391","doi":"https://doi.org/10.21437/interspeech.2022-11074"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11074","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11074","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-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/A5066445347","display_name":"Evelina Bakhturina","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Evelina Bakhturina","raw_affiliation_strings":["NVIDIA, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354569","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0001-6777-3487"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["NVIDIA, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032957280","display_name":"Boris Ginsburg","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boris Ginsburg","raw_affiliation_strings":["NVIDIA, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066445347"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":1.0388,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.78496014,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"491","last_page":"495"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8582000136375427,"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":0.8582000136375427,"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":0.8526999950408936,"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":0.8274000287055969,"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":0.8809719085693359},{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.6983649730682373},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6337618231773376},{"id":"https://openalex.org/keywords/finite-state","display_name":"Finite state","score":0.6299213171005249},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5218799710273743},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4617566764354706},{"id":"https://openalex.org/keywords/finite-state-machine","display_name":"Finite-state machine","score":0.4215832054615021},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3705258369445801},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3681616485118866},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34706389904022217},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3263446092605591},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3066825866699219},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.21010050177574158},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1544477343559265},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12708839774131775}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8809719085693359},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.6983649730682373},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6337618231773376},{"id":"https://openalex.org/C2983497884","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite state","level":3,"score":0.6299213171005249},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5218799710273743},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4617566764354706},{"id":"https://openalex.org/C167822520","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite-state machine","level":2,"score":0.4215832054615021},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3705258369445801},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3681616485118866},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34706389904022217},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3263446092605591},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3066825866699219},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.21010050177574158},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1544477343559265},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12708839774131775},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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:10.21437/interspeech.2022-11074","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11074","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1489087795","https://openalex.org/W1629199664","https://openalex.org/W1915251500","https://openalex.org/W2103085228","https://openalex.org/W2129914454","https://openalex.org/W2747175885","https://openalex.org/W2896457183","https://openalex.org/W2921312604","https://openalex.org/W2924677654","https://openalex.org/W2945656493","https://openalex.org/W2965373594","https://openalex.org/W3034775979","https://openalex.org/W3160789530","https://openalex.org/W3194932072","https://openalex.org/W4287231588","https://openalex.org/W4288089799"],"related_works":["https://openalex.org/W1532285316","https://openalex.org/W4281261571","https://openalex.org/W4387024110","https://openalex.org/W2535494882","https://openalex.org/W1566362083","https://openalex.org/W2500821785","https://openalex.org/W1571505340","https://openalex.org/W2103029213","https://openalex.org/W4387581576","https://openalex.org/W4254987752"],"abstract_inverted_index":{"Text":[0],"normalization":[1,31,47,73],"(TN)":[2],"systems":[3,15,32],"in":[4],"production":[5],"are":[6,50],"largely":[7],"rule-based":[8,64],"using":[9],"weighted":[10],"finite-state":[11],"transducers":[12],"(WFST).However,":[13],"WFST-based":[14],"struggle":[16],"with":[17],"ambiguous":[18],"input":[19],"when":[20],"the":[21,26,61,82,93,98],"normalized":[22],"form":[23],"is":[24,105,113],"context-dependent.On":[25],"other":[27],"hand,":[28],"neural":[29,66,78],"text":[30],"can":[33],"take":[34],"context":[35],"into":[36],"account":[37],"but":[38],"they":[39],"suffer":[40],"from":[41],"unrecoverable":[42,96],"errors":[43],"and":[44,65,75,109],"require":[45],"labeled":[46],"datasets,":[48],"which":[49],"hard":[51],"to":[52,86,107],"collect.We":[53],"propose":[54],"a":[55,68,77],"new":[56],"hybrid":[57],"approach":[58,104],"that":[59],"combines":[60],"benefits":[62],"of":[63],"systems.First,":[67],"non-deterministic":[69],"WFST":[70,94],"outputs":[71],"all":[72],"candidates,":[74],"then":[76],"language":[79,99],"model":[80,100],"picks":[81],"best":[83],"one":[84],"-similar":[85],"shallow":[87],"fusion":[88],"for":[89],"automatic":[90],"speech":[91],"recognition.While":[92],"prevents":[95],"errors,":[97],"resolves":[101],"contextual":[102],"ambiguity.The":[103],"easy":[106],"extend":[108],"we":[110],"show":[111],"it":[112],"effective.It":[114],"achieves":[115],"comparable":[116],"or":[117],"better":[118],"results":[119],"than":[120],"existing":[121],"state-of-theart":[122],"TN":[123],"models.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}