{"id":"https://openalex.org/W4392903019","doi":"https://doi.org/10.1109/icassp48485.2024.10447782","title":"Contextualized Automatic Speech Recognition With Attention-Based Bias Phrase Boosted Beam Search","display_name":"Contextualized Automatic Speech Recognition With Attention-Based Bias Phrase Boosted Beam Search","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903019","doi":"https://doi.org/10.1109/icassp48485.2024.10447782"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5091425252","display_name":"Yui Sudo","orcid":"https://orcid.org/0000-0003-2094-6701"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yui Sudo","raw_affiliation_strings":["Honda Research Institute Japan Co., Ltd.,Saitama,Japan","Honda Research Institute Japan Co., Ltd., Saitama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Co., Ltd.,Saitama,Japan","institution_ids":["https://openalex.org/I1283473643"]},{"raw_affiliation_string":"Honda Research Institute Japan Co., Ltd., Saitama, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100568412","display_name":"Muhammad Shakeel","orcid":null},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Muhammad Shakeel","raw_affiliation_strings":["Honda Research Institute Japan Co., Ltd.,Saitama,Japan","Honda Research Institute Japan Co., Ltd., Saitama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Co., Ltd.,Saitama,Japan","institution_ids":["https://openalex.org/I1283473643"]},{"raw_affiliation_string":"Honda Research Institute Japan Co., Ltd., Saitama, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108536736","display_name":"Y. Fukumoto","orcid":null},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yosuke Fukumoto","raw_affiliation_strings":["Honda Research Institute Japan Co., Ltd.,Saitama,Japan","Honda Research Institute Japan Co., Ltd., Saitama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Co., Ltd.,Saitama,Japan","institution_ids":["https://openalex.org/I1283473643"]},{"raw_affiliation_string":"Honda Research Institute Japan Co., Ltd., Saitama, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033862822","display_name":"Yifan Peng","orcid":"https://orcid.org/0000-0002-8581-8674"},"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":"Yifan Peng","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA,USA","Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, 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,Pittsburgh,PA,USA","Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.6228,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.95844769,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10896","last_page":"10900"},"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":0.998199999332428,"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/T11309","display_name":"Music and Audio Processing","score":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.8134551048278809},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.7896980047225952},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6418455839157104},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6169982552528381},{"id":"https://openalex.org/keywords/contextualization","display_name":"Contextualization","score":0.5649999380111694},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5512300133705139},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5488172769546509},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5369019508361816},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4861738085746765},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4124157726764679},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09909611940383911},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.08607789874076843}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8134551048278809},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7896980047225952},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6418455839157104},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6169982552528381},{"id":"https://openalex.org/C2780712339","wikidata":"https://www.wikidata.org/wiki/Q5165204","display_name":"Contextualization","level":3,"score":0.5649999380111694},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5512300133705139},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5488172769546509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5369019508361816},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4861738085746765},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4124157726764679},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09909611940383911},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.08607789874076843},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1965255698","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2766219058","https://openalex.org/W2886319145","https://openalex.org/W2888779557","https://openalex.org/W2889012072","https://openalex.org/W2936774411","https://openalex.org/W2937402758","https://openalex.org/W2962780374","https://openalex.org/W2963240019","https://openalex.org/W2973122799","https://openalex.org/W3097239815","https://openalex.org/W3097777922","https://openalex.org/W3097794466","https://openalex.org/W3198004110","https://openalex.org/W3211278025","https://openalex.org/W4206006345","https://openalex.org/W4221165942","https://openalex.org/W4225289150","https://openalex.org/W4226292626","https://openalex.org/W4319862261","https://openalex.org/W4385822246","https://openalex.org/W4385823173","https://openalex.org/W4385823316","https://openalex.org/W4388017359","https://openalex.org/W4402671877","https://openalex.org/W6623517193","https://openalex.org/W6638749077","https://openalex.org/W6779469704","https://openalex.org/W6852710422"],"related_works":["https://openalex.org/W1687432146","https://openalex.org/W1591874556","https://openalex.org/W2185608106","https://openalex.org/W3046258185","https://openalex.org/W1548083239","https://openalex.org/W3216994056","https://openalex.org/W2268232908","https://openalex.org/W205610463","https://openalex.org/W4296050054","https://openalex.org/W2944691285"],"abstract_inverted_index":{"End-to-end":[0],"(E2E)":[1],"automatic":[2],"speech":[3,106],"recognition":[4],"(ASR)":[5],"methods":[6,16,29,48],"exhibit":[7],"remarkable":[8],"performance.":[9],"However,":[10],"since":[11],"the":[12,21,25,54,100,104,112,130,139,144,149,154,158,163],"performance":[13,114],"of":[14,153],"such":[15],"is":[17],"intrinsically":[18],"linked":[19],"to":[20,76,98,110],"context":[22],"present":[23],"in":[24,103,157],"training":[26],"data,":[27],"E2E-ASR":[28,47],"do":[30],"not":[31],"perform":[32],"as":[33,77],"desired":[34],"for":[35],"unseen":[36],"user":[37,55],"contexts":[38],"(e.g.,":[39],"technical":[40],"terms,":[41],"personal":[42],"names,":[43],"and":[44,95,148,166],"playlists).":[45],"Thus,":[46],"must":[49],"be":[50,68,85],"easily":[51],"contextualized":[52],"by":[53,88],"or":[56],"developer.":[57],"This":[58],"paper":[59],"proposes":[60],"an":[61,71],"attention-based":[62],"contextual":[63],"biasing":[64],"method":[65,83,141],"that":[66,138],"can":[67,84],"customized":[69],"using":[70],"editable":[72],"phrase":[73,92,122,132],"list":[74,160],"(referred":[75],"a":[78,90,120],"bias":[79,91,101,121,131,159],"list).":[80],"The":[81],"proposed":[82,140],"trained":[86],"effectively":[87],"combining":[89],"index":[93,133],"loss":[94],"special":[96],"tokens":[97],"detect":[99],"phrases":[102,156],"input":[105],"data.":[107],"In":[108],"addition,":[109],"improve":[111],"contextualization":[113],"during":[115],"inference":[116],"further,":[117],"we":[118],"propose":[119],"boosted":[123],"(BPB)":[124],"beam":[125],"search":[126],"algorithm":[127],"based":[128],"on":[129,161],"probability.":[134],"Experimental":[135],"results":[136],"demonstrate":[137],"consistently":[142],"improves":[143],"word":[145],"error":[146,151],"rate":[147,152],"character":[150],"target":[155],"both":[162],"Librispeech-960":[164],"(English)":[165],"our":[167],"in-house":[168],"(Japanese)":[169],"dataset,":[170],"respectively.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}