{"id":"https://openalex.org/W3197267207","doi":"https://doi.org/10.21437/interspeech.2021-587","title":"Reducing Exposure Bias in Training Recurrent Neural Network Transducers","display_name":"Reducing Exposure Bias in Training Recurrent Neural Network Transducers","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197267207","doi":"https://doi.org/10.21437/interspeech.2021-587","mag":"3197267207"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-587","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-587","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":"conference-paper","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/A5102014291","display_name":"Xiaodong Cui","orcid":"https://orcid.org/0000-0003-4865-1307"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaodong Cui","raw_affiliation_strings":["IBM Research AI IBM T. J. Watson Research Center, Yorktown Heights, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI IBM T. J. Watson Research Center, Yorktown Heights, New York, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM Research AI IBM T. J. Watson Research Center, Yorktown Heights, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI IBM T. J. Watson Research Center, Yorktown Heights, New York, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM Research AI IBM T. J. Watson Research Center, Yorktown Heights, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI IBM T. J. Watson Research Center, Yorktown Heights, New York, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049318367","display_name":"David Haws","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Haws","raw_affiliation_strings":["IBM Research AI IBM T. J. Watson Research Center, Yorktown Heights, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI IBM T. J. Watson Research Center, Yorktown Heights, New York, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047353872","display_name":"Zolt\u00e1n T\u00fcske","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zolt\u00e1n T\u00fcske","raw_affiliation_strings":["IBM Research AI IBM T. J. Watson Research Center, Yorktown Heights, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI IBM T. J. Watson Research Center, Yorktown Heights, New York, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1802","last_page":"1806"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9954000115394592,"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/security-token","display_name":"Security token","score":0.8365587592124939},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7757025361061096},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7222554087638855},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.6283677816390991},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5957311987876892},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5928726196289062},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5425288677215576},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48738938570022583},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3867553174495697},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3279787302017212},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09227856993675232}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.8365587592124939},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7757025361061096},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7222554087638855},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.6283677816390991},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5957311987876892},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5928726196289062},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5425288677215576},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48738938570022583},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3867553174495697},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3279787302017212},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09227856993675232},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-587","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-587","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":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W648786980","https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1553004968","https://openalex.org/W1828163288","https://openalex.org/W2079623482","https://openalex.org/W2109886035","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2150769028","https://openalex.org/W2166637769","https://openalex.org/W2184045248","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2759071281","https://openalex.org/W2888519496","https://openalex.org/W2908510526","https://openalex.org/W2936774411","https://openalex.org/W2937780860","https://openalex.org/W2962760690","https://openalex.org/W2962824709","https://openalex.org/W2963266252","https://openalex.org/W2973229104","https://openalex.org/W2985287635","https://openalex.org/W3007776460","https://openalex.org/W3008037978","https://openalex.org/W3015190365","https://openalex.org/W3163300396","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2997152889","https://openalex.org/W4387768015","https://openalex.org/W4285141722"],"abstract_inverted_index":{"When":[0],"recurrent":[1],"neural":[2],"network":[3,16,74],"transducers":[4],"(RNNTs)":[5],"are":[6,80],"trained":[7,18],"using":[8,82],"the":[9,14,36,58,72,96,104,114,127],"typical":[10],"maximum":[11],"likelihood":[12],"criterion,":[13],"prediction":[15,73],"is":[17,75],"only":[19],"on":[20,88,95,126],"ground":[21],"truth":[22],"label":[23,41],"sequences.This":[24],"leads":[25],"to":[26,50,56,71],"a":[27,117],"mismatch":[28],"during":[29],"inference,":[30],"known":[31],"as":[32],"exposure":[33,52,105],"bias,":[34,106],"when":[35],"model":[37,121],"must":[38],"deal":[39],"with":[40],"sequences":[42,79],"containing":[43],"errors.In":[44],"this":[45],"paper":[46],"we":[47,107,110],"investigate":[48],"approaches":[49],"reducing":[51,103],"bias":[53],"in":[54],"training":[55],"improve":[57,113],"generalization":[59],"of":[60,116],"RNNT":[61,119],"models":[62],"for":[63],"automatic":[64],"speech":[65],"recognition":[66],"(ASR).A":[67],"label-preserving":[68],"input":[69,77],"perturbation":[70],"introduced.The":[76],"token":[78,91],"perturbed":[81],"SwitchOut":[83],"and":[84,122],"scheduled":[85],"sampling":[86],"based":[87],"an":[89],"additional":[90],"language":[92],"model.Experiments":[93],"conducted":[94],"300-hour":[97,128],"Switchboard":[98,129],"dataset":[99],"demonstrate":[100],"their":[101],"effectiveness.By":[102],"show":[108],"that":[109],"can":[111],"further":[112],"accuracy":[115],"high-performance":[118],"ASR":[120],"obtain":[123],"state-of-the-art":[124],"results":[125],"dataset.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}