{"id":"https://openalex.org/W4223954171","doi":"https://doi.org/10.21437/interspeech.2022-10660","title":"Improving Rare Word Recognition with LM-aware MWER Training","display_name":"Improving Rare Word Recognition with LM-aware MWER Training","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4223954171","doi":"https://doi.org/10.21437/interspeech.2022-10660"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10660","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10660","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":"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/A5101432591","display_name":"Weiran Wang","orcid":"https://orcid.org/0009-0000-0843-707X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang Weiran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027631053","display_name":"Tongzhou Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tongzhou Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tara Sainath","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040131037","display_name":"Ehsan Variani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ehsan Variani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032640894","display_name":"Rohit Prabhavalkar","orcid":"https://orcid.org/0000-0001-5331-6058"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohit Prabhavalkar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101399361","display_name":"Wei Huang","orcid":"https://orcid.org/0000-0002-4817-8858"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"W. Ronny Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016601028","display_name":"Neeraj Gaur","orcid":"https://orcid.org/0000-0002-5926-9966"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Neeraj Gaur","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060420622","display_name":"Sepand Mavandadi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sepand Mavandadi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037066965","display_name":"Cal Peyser","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cal Peyser","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032931723","display_name":"Trevor Strohman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Trevor Strohman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101153566","display_name":"Yanzhang He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanzhang He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050133412","display_name":"David Rybach","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Rybach","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1031","last_page":"1035"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9976999759674072,"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":0.9926999807357788,"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":0.7837080955505371},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5787044167518616},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5757191777229309},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5022103786468506},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4446926414966583},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4417009949684143},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14517924189567566}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7837080955505371},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5787044167518616},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5757191777229309},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5022103786468506},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4446926414966583},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4417009949684143},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14517924189567566},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10660","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10660","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":"Reduced inequalities","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W1530808388","https://openalex.org/W3192589309","https://openalex.org/W2970166416"],"abstract_inverted_index":{"Language":[0],"models":[1,11,43],"(LMs)":[2],"significantly":[3],"improve":[4],"the":[5,22,26,36,45,51,57,62,77,86,101,122,132],"recognition":[6],"accuracy":[7],"of":[8,38,59],"end-to-end":[9],"(E2E)":[10],"on":[12,92],"words":[13],"rarely":[14],"seen":[15],"during":[16,69],"training,":[17],"when":[18],"used":[19],"in":[20,35,44,115],"either":[21],"shallow":[23,63],"fusion":[24,64,113,136],"or":[25],"rescoring":[27,102,124],"setups.":[28],"In":[29],"this":[30],"work,":[31],"we":[32,66,104],"introduce":[33],"LMs":[34,68],"learning":[37],"hybrid":[39],"autoregressive":[40],"transducer":[41],"(HAT)":[42],"discriminative":[46],"training":[47,52],"framework,":[48],"to":[49,110],"mitigate":[50],"versus":[53],"inference":[54],"gap":[55],"regarding":[56],"use":[58,67],"LMs.":[60],"For":[61,100],"setup,":[65,103],"both":[70],"hypotheses":[71],"generation":[72],"and":[73,76],"loss":[74],"computation,":[75],"LM-aware":[78],"MWER-trained":[79,128],"model":[80,87,120],"achieves":[81,121],"10\\%":[82],"relative":[83],"improvement":[84],"over":[85],"trained":[88],"with":[89],"standard":[90],"MWER":[91],"voice":[93],"search":[94],"test":[95],"sets":[96],"containing":[97],"rare":[98],"words.":[99],"learn":[105],"a":[106,116],"small":[107],"neural":[108],"module":[109],"generate":[111],"per-token":[112],"weights":[114],"data-dependent":[117],"manner.":[118],"This":[119],"same":[123],"WER":[125],"as":[126],"regular":[127],"model,":[129],"but":[130],"without":[131],"need":[133],"for":[134],"sweeping":[135],"weights.":[137]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}