{"id":"https://openalex.org/W4285817889","doi":"https://doi.org/10.1109/lsp.2022.3192199","title":"Spelling-Aware Word-Based End-to-End ASR","display_name":"Spelling-Aware Word-Based End-to-End ASR","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285817889","doi":"https://doi.org/10.1109/lsp.2022.3192199"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2022.3192199","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2022.3192199","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5103183851","display_name":"Ekaterina Egorova","orcid":"https://orcid.org/0000-0001-5398-4371"},"institutions":[{"id":"https://openalex.org/I4210093365","display_name":"Edip (Czechia)","ror":"https://ror.org/00m6vcy72","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210093365"]},{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ekaterina Egorova","raw_affiliation_strings":["Faculty of Information Technology, Speech@FIT, Brno University of Technology, Brno-střed, Czech Republic","ed, Czechia"],"raw_orcid":"https://orcid.org/0000-0001-5398-4371","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Brno-střed, Czech Republic","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"ed, Czechia","institution_ids":["https://openalex.org/I4210093365"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014351336","display_name":"Hari Krishna Vydana","orcid":"https://orcid.org/0000-0001-5192-5888"},"institutions":[{"id":"https://openalex.org/I4210093365","display_name":"Edip (Czechia)","ror":"https://ror.org/00m6vcy72","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210093365"]},{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Hari Krishna Vydana","raw_affiliation_strings":["Faculty of Information Technology, Speech@FIT, Brno University of Technology, Brno-střed, Czech Republic","ed, Czechia"],"raw_orcid":"https://orcid.org/0000-0001-5192-5888","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Brno-střed, Czech Republic","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"ed, Czechia","institution_ids":["https://openalex.org/I4210093365"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I4210093365","display_name":"Edip (Czechia)","ror":"https://ror.org/00m6vcy72","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210093365"]},{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lukas Burget","raw_affiliation_strings":["Faculty of Information Technology, Speech@FIT, Brno University of Technology, Brno-střed, Czech Republic","ed, Czechia"],"raw_orcid":"https://orcid.org/0000-0002-4951-5908","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Brno-střed, Czech Republic","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"ed, Czechia","institution_ids":["https://openalex.org/I4210093365"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"institutions":[{"id":"https://openalex.org/I4210093365","display_name":"Edip (Czechia)","ror":"https://ror.org/00m6vcy72","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210093365"]},{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Honza Cernocky","raw_affiliation_strings":["Faculty of Information Technology, Speech@FIT, Brno University of Technology, Brno-střed, Czech Republic","ed, Czechia"],"raw_orcid":"https://orcid.org/0000-0002-8800-0210","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Brno-střed, Czech Republic","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"ed, Czechia","institution_ids":["https://openalex.org/I4210093365"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3936,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66032243,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"29","issue":null,"first_page":"1729","last_page":"1733"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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":0.9988999962806702,"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":0.830704927444458},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7798538208007812},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7234770059585571},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.683907687664032},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.6331079006195068},{"id":"https://openalex.org/keywords/spell","display_name":"Spell","score":0.5906316041946411},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5817382335662842},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5572035312652588},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5169381499290466},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5109214186668396},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48972824215888977},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14314982295036316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.830704927444458},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7798538208007812},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7234770059585571},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.683907687664032},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.6331079006195068},{"id":"https://openalex.org/C2780957641","wikidata":"https://www.wikidata.org/wiki/Q1999796","display_name":"Spell","level":2,"score":0.5906316041946411},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5817382335662842},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5572035312652588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5169381499290466},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5109214186668396},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48972824215888977},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14314982295036316},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2022.3192199","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2022.3192199","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1895481600","https://openalex.org/W2166221226","https://openalex.org/W2166850712","https://openalex.org/W2327501763","https://openalex.org/W2545177271","https://openalex.org/W2597757402","https://openalex.org/W2622263826","https://openalex.org/W2766219058","https://openalex.org/W2799800213","https://openalex.org/W2962784628","https://openalex.org/W2963250244","https://openalex.org/W2963357986","https://openalex.org/W2963483399","https://openalex.org/W2963970535","https://openalex.org/W3097777922","https://openalex.org/W3139918052","https://openalex.org/W4226033575","https://openalex.org/W6600052307","https://openalex.org/W6621543089","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6729239390","https://openalex.org/W6739622702","https://openalex.org/W6791904447"],"related_works":["https://openalex.org/W4255929276","https://openalex.org/W2789394886","https://openalex.org/W2184839352","https://openalex.org/W2083657536","https://openalex.org/W2042822003","https://openalex.org/W2103233694","https://openalex.org/W2034944613","https://openalex.org/W2044923869","https://openalex.org/W2097478624","https://openalex.org/W3002191324"],"abstract_inverted_index":{"We":[0,56],"propose":[1],"a":[2,68],"new":[3],"end-to-end":[4],"architecture":[5],"for":[6],"automatic":[7],"speech":[8],"recognition":[9],"that":[10,58],"expands":[11],"the":[12,20,29,43,53,63],"“listen,":[13],"attend":[14],"and":[15,71,81],"spell”":[16],"(LAS)":[17],"paradigm.":[18],"While":[19],"main":[21,44],"word-predicting":[22],"network":[23,45],"is":[24,33],"trained":[25],"to":[26,35],"predict":[27,36],"words,":[28],"secondary,":[30],"speller":[31],"network,":[32],"optimized":[34],"word":[37,47,64,79],"spellings":[38],"from":[39,52],"inner":[40],"representations":[41],"of":[42,67,91,93],"(e.g.":[46],"embeddings":[48],"or":[49],"context":[50],"vectors":[51],"attention":[54],"module).":[55],"show":[57],"this":[59],"joint":[60],"training":[61],"improves":[62],"error":[65],"rate":[66],"word-based":[69],"system":[70],"enables":[72],"solving":[73],"additional":[74],"tasks,":[75],"such":[76],"as":[77],"out-of-vocabulary":[78],"detection":[80],"recovery.":[82],"The":[83],"tests":[84],"are":[85],"conducted":[86],"on":[87],"LibriSpeech":[88],"dataset":[89],"consisting":[90],"1000 h":[92],"read":[94],"speech.":[95]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}