{"id":"https://openalex.org/W4283031490","doi":"https://doi.org/10.21437/interspeech.2022-10557","title":"Residual Language Model for End-to-end Speech Recognition","display_name":"Residual Language Model for End-to-end Speech Recognition","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283031490","doi":"https://doi.org/10.21437/interspeech.2022-10557"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10557","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10557","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/A5011937407","display_name":"Emiru Tsunoo","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Emiru Tsunoo","raw_affiliation_strings":["Sony Group Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109644502","display_name":"Yosuke Kashiwagi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yosuke Kashiwagi","raw_affiliation_strings":["Sony Group Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015372147","display_name":"Chaitanya Narisetty","orcid":"https://orcid.org/0000-0002-9239-5534"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chaitanya Prasad Narisetty","raw_affiliation_strings":["Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5011937407"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3495,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.82902746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3899","last_page":"3903"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9957000017166138,"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/T11309","display_name":"Music and Audio Processing","score":0.9753999710083008,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7770813703536987},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7072844505310059},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5526059865951538},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5428550243377686},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5326544642448425},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29813045263290405},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08248457312583923}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7770813703536987},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7072844505310059},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5526059865951538},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5428550243377686},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5326544642448425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29813045263290405},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08248457312583923}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10557","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10557","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1821462560","https://openalex.org/W1915251500","https://openalex.org/W1922655562","https://openalex.org/W2087006792","https://openalex.org/W2143612262","https://openalex.org/W2183341477","https://openalex.org/W2193413348","https://openalex.org/W2327501763","https://openalex.org/W2397725648","https://openalex.org/W2766219058","https://openalex.org/W2888779557","https://openalex.org/W2936774411","https://openalex.org/W2939111082","https://openalex.org/W2963211739","https://openalex.org/W2963240019","https://openalex.org/W2963242190","https://openalex.org/W2963288281","https://openalex.org/W2972818416","https://openalex.org/W3007433671","https://openalex.org/W3008037978","https://openalex.org/W3016010032","https://openalex.org/W3097777922","https://openalex.org/W3101648800","https://openalex.org/W3152221657","https://openalex.org/W3161669994","https://openalex.org/W3163560333","https://openalex.org/W3197507772","https://openalex.org/W3197674197","https://openalex.org/W3198439131","https://openalex.org/W4224917166"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W3196421258","https://openalex.org/W2560215812","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2916997151","https://openalex.org/W2949174760"],"abstract_inverted_index":{"End-to-end":[0],"automatic":[1],"speech":[2,11],"recognition":[3],"suffers":[4],"from":[5,48],"adaptation":[6],"to":[7,39],"unknown":[8],"target":[9,41,148],"domain":[10,88,149],"despite":[12],"being":[13],"trained":[14],"with":[15,55,129],"a":[16,25,81,130],"large":[17],"amount":[18],"of":[19,28,68,104,132,142,167],"paired":[20],"audio-text":[21],"data.Recent":[22],"studies":[23],"estimate":[24],"linguistic":[26],"bias":[27],"the":[29,32,40,43,49,63,66,69,92,101,105,111,116,122,139,143,147,154,161,168],"model":[30,35,100],"as":[31],"internal":[33,44,70,93,108,124,144,162],"language":[34],"(LM).To":[36],"effectively":[37],"adapt":[38],"domain,":[42],"LM":[45,71,84,94,125,145,157,163],"is":[46],"subtracted":[47],"posterior":[50],"during":[51],"inference":[52,64],"and":[53,65,107,126,134,170],"fused":[54],"an":[56],"external":[57,83,106],"target-domain":[58],"LM.However,":[59],"this":[60,77],"fusion":[61,85],"complicates":[62],"estimation":[67,95,164],"may":[72],"not":[73],"always":[74],"be":[75],"accurate.In":[76],"paper,":[78],"we":[79,119],"propose":[80,120],"simple":[82],"method":[86],"for":[87],"adaptation,":[89],"which":[90,137],"considers":[91],"in":[96,146,165],"its":[97],"training.We":[98],"directly":[99],"residual":[102,112,117,156],"factor":[103],"LMs,":[109],"namely":[110],"LM.To":[113],"stably":[114],"train":[115],"LM,":[118],"smoothing":[121],"estimated":[123],"optimizing":[127],"it":[128],"combination":[131],"cross-entropy":[133],"mean-squared-error":[135],"losses,":[136],"consider":[138],"statistical":[140],"behaviors":[141],"data.We":[150],"experimentally":[151],"confirmed":[152],"that":[153],"proposed":[155],"performs":[158],"better":[159],"than":[160],"most":[166],"cross-domain":[169],"intra-domain":[171],"scenarios.":[172]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}