{"id":"https://openalex.org/W2981762175","doi":"https://doi.org/10.1109/icassp40776.2020.9053051","title":"Correction of Automatic Speech Recognition with Transformer Sequence-To-Sequence Model","display_name":"Correction of Automatic Speech Recognition with Transformer Sequence-To-Sequence Model","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2981762175","doi":"https://doi.org/10.1109/icassp40776.2020.9053051","mag":"2981762175"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053051","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/1910.10697","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088392468","display_name":"Oleksii Hrinchuk","orcid":null},"institutions":[{"id":"https://openalex.org/I153845743","display_name":"Moscow Institute of Physics and Technology","ror":"https://ror.org/00v0z9322","country_code":"RU","type":"education","lineage":["https://openalex.org/I153845743"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Oleksii Hrinchuk","raw_affiliation_strings":["Moscow Institute of Physics and Technology,Moscow,Russia","Moscow Institute of Physics and Technology"],"affiliations":[{"raw_affiliation_string":"Moscow Institute of Physics and Technology,Moscow,Russia","institution_ids":["https://openalex.org/I153845743"]},{"raw_affiliation_string":"Moscow Institute of Physics and Technology","institution_ids":["https://openalex.org/I153845743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112439881","display_name":"Mariya Popova","orcid":"https://orcid.org/0009-0007-2921-5338"},"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":"Mariya Popova","raw_affiliation_strings":["NVIDIA,Santa Clara,CA,USA","[NVidia, Santa Clara, CA, USA]"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,CA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"[NVidia, Santa Clara, CA, 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,CA,USA","[NVidia, Santa Clara, CA, USA]"],"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,CA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"[NVidia, Santa Clara, CA, USA]","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088392468"],"corresponding_institution_ids":["https://openalex.org/I153845743"],"apc_list":null,"apc_paid":null,"fwci":0.2743,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61931404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9998000264167786,"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":0.9993000030517578,"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":0.7836264371871948},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7550805807113647},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7505289912223816},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6437589526176453},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.607987105846405},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5725666284561157},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5666921138763428},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5640182495117188},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.47720345854759216},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43636754155158997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4172079563140869},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13971108198165894},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09073039889335632},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07799586653709412}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7836264371871948},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7550805807113647},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7505289912223816},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6437589526176453},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.607987105846405},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5725666284561157},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5666921138763428},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5640182495117188},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.47720345854759216},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43636754155158997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4172079563140869},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13971108198165894},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09073039889335632},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07799586653709412},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053051","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.10697","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.10697","pdf_url":"https://arxiv.org/pdf/1910.10697","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2981762175","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1910.10697","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.1910.10697","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.10697","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/98ep-4p48","is_oa":true,"landing_page_url":"https://doi.org/10.17023/98ep-4p48","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:1910.10697","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.10697","pdf_url":"https://arxiv.org/pdf/1910.10697","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2981762175.pdf","grobid_xml":"https://content.openalex.org/works/W2981762175.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2130942839","https://openalex.org/W2134800885","https://openalex.org/W2157331557","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2327501763","https://openalex.org/W2501000458","https://openalex.org/W2525778437","https://openalex.org/W2530876040","https://openalex.org/W2746314669","https://openalex.org/W2797303992","https://openalex.org/W2889326796","https://openalex.org/W2911109671","https://openalex.org/W2916997151","https://openalex.org/W2936774411","https://openalex.org/W2945697643","https://openalex.org/W2962826786","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963446712","https://openalex.org/W2963631907","https://openalex.org/W2964110616","https://openalex.org/W2964308564","https://openalex.org/W2964345285","https://openalex.org/W2973215447","https://openalex.org/W2974231335","https://openalex.org/W6629717138","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6679855610","https://openalex.org/W6739901393","https://openalex.org/W6743428213","https://openalex.org/W6754905691","https://openalex.org/W6755207826","https://openalex.org/W6762625080","https://openalex.org/W6767671539"],"related_works":["https://openalex.org/W3200151955","https://openalex.org/W3016053077","https://openalex.org/W2949174760","https://openalex.org/W2262506559","https://openalex.org/W1904457459","https://openalex.org/W3160523328","https://openalex.org/W3003809177","https://openalex.org/W2899439440","https://openalex.org/W2537374808","https://openalex.org/W2978571467","https://openalex.org/W3202576380","https://openalex.org/W3197681820","https://openalex.org/W2626638964","https://openalex.org/W3034497445","https://openalex.org/W2936078256","https://openalex.org/W2027079089","https://openalex.org/W2963747784","https://openalex.org/W2388234732","https://openalex.org/W2395971734","https://openalex.org/W1959963859"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"introduce":[4],"a":[5],"simple":[6],"yet":[7],"efficient":[8],"post-processing":[9],"model":[10,16,24,41,77,94,101],"for":[11,36],"automatic":[12],"speech":[13],"recognition.":[14],"Our":[15,93],"has":[17],"Transformer-based":[18],"encoder-decoder":[19],"architecture":[20],"which":[21],"\"translates\"":[22],"acoustic":[23,76],"output":[25],"into":[26],"grammatically":[27],"and":[28,38,42,48,86,103],"semantically":[29],"correct":[30],"text.":[31],"We":[32],"investigate":[33],"different":[34],"strategies":[35],"regularizing":[37],"optimizing":[39],"the":[40,49,61,74,90,105],"show":[43],"that":[44],"extensive":[45],"data":[46],"augmentation":[47],"initialization":[50],"with":[51,78,98,109],"pretrained":[52],"weights":[53],"are":[54],"required":[55],"to":[56],"achieve":[57],"good":[58],"performance.":[59],"On":[60],"LibriSpeech":[62],"benchmark,":[63],"our":[64],"method":[65],"demonstrates":[66],"significant":[67],"improvement":[68],"in":[69],"word":[70],"error":[71],"rate":[72],"over":[73],"baseline":[75,97],"greedy":[79],"decoding,":[80],"especially":[81],"on":[82],"much":[83],"noisier":[84],"dev-other":[85],"test-other":[87],"portions":[88],"of":[89,107],"evaluation":[91],"dataset.":[92],"also":[95],"outperforms":[96],"6-gram":[99],"language":[100,112],"re-scoring":[102,108],"approaches":[104],"performance":[106],"Transformer-XL":[110],"neural":[111],"model.":[113]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}