{"id":"https://openalex.org/W7148427047","doi":"https://doi.org/10.1109/asru65441.2025.11434809","title":"Lightweight Prompt Biasing for Contextualized End-to-End ASR Systems","display_name":"Lightweight Prompt Biasing for Contextualized End-to-End ASR Systems","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148427047","doi":"https://doi.org/10.1109/asru65441.2025.11434809"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434809","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","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/A5132796838","display_name":"Bo Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Bo Ren","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,USA","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132802260","display_name":"Yu Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Yu Shi","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,USA","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100364802","display_name":"Jin Li","orcid":"https://orcid.org/0000-0002-6131-456X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft, One Microsoft Way,Redmond,USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way,Redmond,USA","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5132796838"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":2.1819,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92937014,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9059000015258789,"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":0.9059000015258789,"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":0.012400000356137753,"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":0.010099999606609344,"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/leverage","display_name":"Leverage (statistics)","score":0.739300012588501},{"id":"https://openalex.org/keywords/biasing","display_name":"Biasing","score":0.5824000239372253},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5645999908447266},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4731999933719635},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.453000009059906},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.414000004529953},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.3653999865055084},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.33980000019073486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7628999948501587},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.739300012588501},{"id":"https://openalex.org/C20254490","wikidata":"https://www.wikidata.org/wiki/Q719550","display_name":"Biasing","level":3,"score":0.5824000239372253},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5645999908447266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5238999724388123},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48330000042915344},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4731999933719635},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.453000009059906},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.353300005197525},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3059000074863434},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2685000002384186},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434809","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":31,"referenced_works":["https://openalex.org/W2327501763","https://openalex.org/W2750499125","https://openalex.org/W2766219058","https://openalex.org/W2886319145","https://openalex.org/W2889012072","https://openalex.org/W2892009249","https://openalex.org/W2937402758","https://openalex.org/W2962760690","https://openalex.org/W2962824709","https://openalex.org/W2972625221","https://openalex.org/W2973172693","https://openalex.org/W3015194534","https://openalex.org/W3016010032","https://openalex.org/W3094667432","https://openalex.org/W3095311338","https://openalex.org/W3097777922","https://openalex.org/W3097794466","https://openalex.org/W3140235797","https://openalex.org/W3161873870","https://openalex.org/W3198004110","https://openalex.org/W3211278025","https://openalex.org/W4224918838","https://openalex.org/W4225985539","https://openalex.org/W4226462878","https://openalex.org/W4385245566","https://openalex.org/W4385822953","https://openalex.org/W4388017359","https://openalex.org/W4392902925","https://openalex.org/W4392903288","https://openalex.org/W4402111365","https://openalex.org/W4406461293"],"related_works":[],"abstract_inverted_index":{"End-to-End":[0],"Automatic":[1],"Speech":[2],"Recognition":[3],"(ASR)":[4],"has":[5],"advanced":[6],"significantly":[7,74],"yet":[8,21],"still":[9],"struggles":[10],"with":[11,99,106],"rare":[12],"and":[13,61,85,108,123,132],"domain-specific":[14],"entities.":[15,71],"This":[16],"paper":[17],"introduces":[18],"a":[19,34,45,62,81],"simple":[20],"efficient":[22],"prompt-based":[23],"biasing":[24,47],"technique":[25],"for":[26],"contextualized":[27],"ASR,":[28],"enhancing":[29],"recognition":[30],"accuracy":[31,77],"by":[32],"leverage":[33],"unified":[35],"multi-task":[36],"learning":[37],"framework.":[38],"The":[39,113],"approach":[40],"comprises":[41],"two":[42],"key":[43],"components:":[44],"prompt":[46],"model":[48,98],"which":[49,66],"is":[50],"trained":[51],"to":[52,55,95],"determine":[53],"when":[54],"focus":[56],"on":[57,78,102],"entities":[58],"in":[59,89,120],"prompt,":[60],"entity":[63,110],"filtering":[64],"mechanism":[65],"efficiently":[67],"filters":[68],"out":[69],"irrelevant":[70],"Our":[72],"method":[73,118],"enhances":[75],"ASR":[76],"entities,":[79],"achieving":[80],"relative":[82],"$30.7":[83],"\\%$":[84,87],"$18.0":[86],"reduction":[88],"Entity":[90],"Word":[91],"Error":[92],"Rate":[93],"compared":[94],"the":[96],"baseline":[97],"shallow":[100],"fusion":[101],"in-house":[103],"domain":[104],"dataset":[105],"small":[107],"large":[109],"lists,":[111],"respectively.":[112],"primary":[114],"advantage":[115],"of":[116],"this":[117],"lies":[119],"its":[121],"efficiency":[122],"simplicity":[124],"without":[125],"any":[126],"structure":[127],"change,":[128],"making":[129],"it":[130],"lightweight":[131],"highly":[133],"efficient.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2026-04-03T00:00:00"}