{"id":"https://openalex.org/W4392903078","doi":"https://doi.org/10.1109/icassp48485.2024.10447438","title":"Improving ASR Contextual Biasing with Guided Attention","display_name":"Improving ASR Contextual Biasing with Guided Attention","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903078","doi":"https://doi.org/10.1109/icassp48485.2024.10447438"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447438","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/A5101730616","display_name":"Jiyang Tang","orcid":"https://orcid.org/0009-0008-3229-7976"},"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":"Jiyang Tang","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":"middle","author":{"id":"https://openalex.org/A5052377938","display_name":"Kwangyoun Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kwangyoun Kim","raw_affiliation_strings":["ASAPP Inc.,New York,NY,USA","ASAPP Inc., New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP Inc.,New York,NY,USA","institution_ids":["https://openalex.org/I1283576576"]},{"raw_affiliation_string":"ASAPP Inc., New York, NY, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020263683","display_name":"Suwon Shon","orcid":null},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suwon Shon","raw_affiliation_strings":["ASAPP Inc.,New York,NY,USA","ASAPP Inc., New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP Inc.,New York,NY,USA","institution_ids":["https://openalex.org/I1283576576"]},{"raw_affiliation_string":"ASAPP Inc., New York, NY, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113099538","display_name":"Felix F. Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Felix Wu","raw_affiliation_strings":["ASAPP Inc.,New York,NY,USA","ASAPP Inc., New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP Inc.,New York,NY,USA","institution_ids":["https://openalex.org/I1283576576"]},{"raw_affiliation_string":"ASAPP Inc., New York, NY, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006917911","display_name":"Prashant Sridhar","orcid":null},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prashant Sridhar","raw_affiliation_strings":["ASAPP Inc.,New York,NY,USA","ASAPP Inc., New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASAPP Inc.,New York,NY,USA","institution_ids":["https://openalex.org/I1283576576"]},{"raw_affiliation_string":"ASAPP Inc., New York, NY, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12096","last_page":"12100"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9958999752998352,"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":0.9902999997138977,"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/biasing","display_name":"Biasing","score":0.7216004729270935},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6439955234527588},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5514213442802429},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5003905296325684},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4254891276359558},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11068254709243774},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.10998114943504333},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08183819055557251}],"concepts":[{"id":"https://openalex.org/C20254490","wikidata":"https://www.wikidata.org/wiki/Q719550","display_name":"Biasing","level":3,"score":0.7216004729270935},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6439955234527588},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5514213442802429},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5003905296325684},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4254891276359558},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11068254709243774},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.10998114943504333},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08183819055557251},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447438","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2327501763","https://openalex.org/W2477293991","https://openalex.org/W2886319145","https://openalex.org/W2962780374","https://openalex.org/W2972625221","https://openalex.org/W3043783436","https://openalex.org/W3097239815","https://openalex.org/W3097777922","https://openalex.org/W3097794466","https://openalex.org/W3140235797","https://openalex.org/W3198004110","https://openalex.org/W3202725408","https://openalex.org/W4224903522","https://openalex.org/W4224918838","https://openalex.org/W4225985539","https://openalex.org/W4372259757","https://openalex.org/W4372260607","https://openalex.org/W4375869128","https://openalex.org/W4385822246","https://openalex.org/W4385822295","https://openalex.org/W4385822583","https://openalex.org/W4385822684","https://openalex.org/W4385823371","https://openalex.org/W4402671877","https://openalex.org/W6623517193","https://openalex.org/W6638749077","https://openalex.org/W6852710422"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W2405439032","https://openalex.org/W2547793174","https://openalex.org/W2132658536","https://openalex.org/W2070212102","https://openalex.org/W2544241817","https://openalex.org/W2158882055","https://openalex.org/W2914603036"],"abstract_inverted_index":{"In":[0],"this":[1,57],"paper,":[2],"we":[3,59,125],"propose":[4],"a":[5,61,135,178],"Guided":[6],"Attention":[7],"(GA)":[8],"auxiliary":[9],"training":[10,67],"loss,":[11],"which":[12],"improves":[13],"the":[14,37,49,70,80,100,106,128,144,151,155,168],"effectiveness":[15,142],"and":[16,110,172],"robustness":[17],"of":[18,51,146,157],"automatic":[19],"speech":[20],"recognition":[21],"(ASR)":[22],"contextual":[23,45,169],"biasing":[24,46,170],"without":[25],"introducing":[26],"additional":[27,66],"parameters.":[28],"A":[29],"common":[30],"challenge":[31],"in":[32],"previous":[33],"literature":[34],"is":[35,111],"that":[36,127],"word":[38],"error":[39],"rate":[40],"(WER)":[41],"reduction":[42],"brought":[43],"by":[44,160],"diminishes":[47],"as":[48,64,143],"number":[50,145],"bias":[52,86,147],"phrases":[53,87,148],"increases.":[54,149],"To":[55],"address":[56],"challenge,":[58],"employ":[60],"GA":[62,75,152],"loss":[63,76,102,153],"an":[65],"objective":[68],"besides":[69],"Transducer":[71,121],"loss.":[72],"The":[73],"proposed":[74,101,129],"aims":[77],"to":[78,84,95,113,134,162,167,174,177],"teach":[79],"cross":[81,107],"attention":[82,108],"how":[83],"align":[85],"with":[88,97,122],"text":[89],"tokens":[90],"or":[91],"audio":[92],"frames.":[93],"Compared":[94],"studies":[96],"similar":[98],"motivations,":[99],"operates":[103],"directly":[104],"on":[105,119,164],"weights":[109],"easier":[112],"implement.":[114],"Through":[115],"extensive":[116],"experiments":[117],"based":[118],"Conformer":[120],"Contextual":[123],"Adapter,":[124],"demonstrate":[126],"method":[130],"not":[131],"only":[132],"leads":[133],"lower":[136],"WER":[137,156],"but":[138],"also":[139],"retains":[140],"its":[141],"Specifically,":[150],"decreases":[154],"rare":[158],"vocabularies":[159],"up":[161,173],"19.2%":[163],"LibriSpeech":[165],"compared":[166,176],"baseline,":[171],"49.3%":[175],"vanilla":[179],"Transducer.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}