{"id":"https://openalex.org/W3193959417","doi":"https://doi.org/10.21437/interspeech.2021-379","title":"A Light-Weight Contextual Spelling Correction Model for Customizing Transducer-Based Speech Recognition Systems","display_name":"A Light-Weight Contextual Spelling Correction Model for Customizing Transducer-Based Speech Recognition Systems","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3193959417","doi":"https://doi.org/10.21437/interspeech.2021-379","mag":"3193959417"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-379","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5100626793","display_name":"Xiaoqiang Wang","orcid":"https://orcid.org/0000-0001-6096-8011"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoqiang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100360935","display_name":"Yanqing Liu","orcid":"https://orcid.org/0000-0003-0412-8805"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanqing Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329353","display_name":"Sheng Zhao","orcid":"https://orcid.org/0000-0002-9624-5381"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sheng Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3993,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85030317,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1982","last_page":"1986"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T12031","display_name":"Speech and dialogue systems","score":0.9923999905586243,"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":0.9869999885559082,"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":0.8272050619125366},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7742905020713806},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7401263117790222},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.7339141368865967},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6645139455795288},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5837538242340088},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.5618912577629089},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5340219140052795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5208645462989807},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5189406871795654},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5106080174446106},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3910750150680542},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06524357199668884},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06308257579803467}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8272050619125366},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7742905020713806},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7401263117790222},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.7339141368865967},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6645139455795288},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5837538242340088},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.5618912577629089},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5340219140052795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5208645462989807},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5189406871795654},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5106080174446106},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3910750150680542},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06524357199668884},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06308257579803467},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-379","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W26527944","https://openalex.org/W2523799048","https://openalex.org/W2155620340","https://openalex.org/W2944691285"],"abstract_inverted_index":{"It's":[0],"challenging":[1],"to":[2,32,61],"customize":[3],"transducer-based":[4,38],"automatic":[5],"speech":[6],"recognition":[7,35],"(ASR)":[8],"system":[9],"with":[10,51,76],"context":[11,44,54,64],"information":[12,45],"which":[13,84],"is":[14],"dynamic":[15],"and":[16,56],"unavailable":[17],"during":[18,107],"model":[19,31,50,70,74,97],"training.":[20,108],"In":[21],"this":[22],"work,":[23],"we":[24],"introduce":[25],"a":[26,52,58],"light-weight":[27],"contextual":[28,93],"spelling":[29,48],"correction":[30,49],"correct":[33],"context-related":[34],"errors":[36],"in":[37],"ASR":[39,73],"systems.":[40],"We":[41],"incorporate":[42],"the":[43,47,69,88],"into":[46],"shared":[53],"encoder":[55],"use":[57],"filtering":[59],"algorithm":[60],"handle":[62],"large-size":[63],"lists.":[65],"Experiments":[66],"show":[67],"that":[68],"improves":[71],"baseline":[72,89],"performance":[75,101],"about":[77],"50%":[78],"relative":[79],"word":[80],"error":[81],"rate":[82],"reduction,":[83],"also":[85,98],"significantly":[86],"outperforms":[87],"method":[90],"such":[91],"as":[92],"LM":[94],"biasing.":[95],"The":[96],"shows":[99],"excellent":[100],"for":[102],"out-of-vocabulary":[103],"terms":[104],"not":[105],"seen":[106]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}