{"id":"https://openalex.org/W4319862232","doi":"https://doi.org/10.1109/slt54892.2023.10023323","title":"NAM+: Towards Scalable End-to-End Contextual Biasing for Adaptive ASR","display_name":"NAM+: Towards Scalable End-to-End Contextual Biasing for Adaptive ASR","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862232","doi":"https://doi.org/10.1109/slt54892.2023.10023323"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023323","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5062473985","display_name":"Tsendsuren Munkhdalai","orcid":"https://orcid.org/0000-0002-8783-4993"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tsendsuren Munkhdalai","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035558261","display_name":"Zelin Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zelin Wu","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051090720","display_name":"Golan Pundak","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Golan Pundak","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032798707","display_name":"Khe Chai Sim","orcid":"https://orcid.org/0000-0002-0866-2223"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khe Chai Sim","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100769534","display_name":"Jiayang Li","orcid":"https://orcid.org/0009-0009-4267-6897"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiayang Li","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066360541","display_name":"Pat Rondon","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pat Rondon","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tara N. Sainath","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5062473985"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.5412,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.84020619,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"190","last_page":"196"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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/T10662","display_name":"Ultrasonics and Acoustic Wave Propagation","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7506316900253296},{"id":"https://openalex.org/keywords/biasing","display_name":"Biasing","score":0.7236881256103516},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7102774977684021},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6339694261550903},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6081534624099731},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5126485228538513},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46102389693260193},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4599425494670868},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4479469954967499},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3798432946205139},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3125232458114624},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.21358245611190796},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12225550413131714},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.10434994101524353},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10354945063591003},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08547794818878174},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.06863126158714294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7506316900253296},{"id":"https://openalex.org/C20254490","wikidata":"https://www.wikidata.org/wiki/Q719550","display_name":"Biasing","level":3,"score":0.7236881256103516},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7102774977684021},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6339694261550903},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6081534624099731},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5126485228538513},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46102389693260193},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4599425494670868},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4479469954967499},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3798432946205139},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3125232458114624},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.21358245611190796},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12225550413131714},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.10434994101524353},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10354945063591003},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08547794818878174},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.06863126158714294},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/slt54892.2023.10023323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023323","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":28,"referenced_works":["https://openalex.org/W2133564696","https://openalex.org/W2293829681","https://openalex.org/W2403440562","https://openalex.org/W2617258110","https://openalex.org/W2886319145","https://openalex.org/W2889012072","https://openalex.org/W2928941594","https://openalex.org/W2953212265","https://openalex.org/W2963122170","https://openalex.org/W2971840980","https://openalex.org/W2972625221","https://openalex.org/W3016010032","https://openalex.org/W3097777922","https://openalex.org/W3097794466","https://openalex.org/W3163203022","https://openalex.org/W3197976839","https://openalex.org/W3201225328","https://openalex.org/W3202725408","https://openalex.org/W4225289150","https://openalex.org/W4225307083","https://openalex.org/W4225985539","https://openalex.org/W4226292626","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6638749077","https://openalex.org/W6679434410","https://openalex.org/W6760633627","https://openalex.org/W6843673214"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2146343568","https://openalex.org/W2013643406","https://openalex.org/W2157978810","https://openalex.org/W2111089054","https://openalex.org/W2097707447"],"abstract_inverted_index":{"Attention-based":[0],"biasing":[1,36,61,79],"techniques":[2],"for":[3],"end-to-end":[4],"ASR":[5],"systems":[6],"are":[7],"able":[8],"to":[9,24,31,37,105,117,130],"achieve":[10],"large":[11],"accuracy":[12],"gains":[13,92],"without":[14],"requiring":[15],"the":[16,106,112,131,134],"inference":[17,67],"algorithm":[18],"adjustments":[19],"and":[20,51,100],"parameter":[21],"tuning":[22],"common":[23],"fusion":[25],"approaches.":[26],"However,":[27],"it":[28],"is":[29,138],"challenging":[30],"simultaneously":[32],"scale":[33],"up":[34,116],"attention-based":[35,60],"realistic":[38],"numbers":[39],"of":[40,96,126],"biased":[41],"phrases;":[42],"maintain":[43],"in-domain":[44,113],"WER":[45,114,124,136],"gains,":[46],"while":[47,120],"minimizing":[48],"out-of-domain":[49,123,135],"losses;":[50],"run":[52,76],"in":[53],"real":[54],"time.":[55],"We":[56],"present":[57],"NAM+,":[58],"an":[59,122],"approach":[62],"which":[63],"achieves":[64,89],"a":[65,84,94],"16X":[66],"speedup":[68],"per":[69],"acoustic":[70],"frame":[71],"over":[72],"prior":[73],"work":[74],"when":[75],"with":[77],"3,000":[78],"entities,":[80],"as":[81],"measured":[82],"on":[83],"typical":[85],"mobile":[86],"CPU.":[87],"NAM+":[88,109],"these":[90],"run-time":[91],"through":[93],"combination":[95],"Two-Pass":[97],"Hierarchical":[98],"Attention":[99],"Dilated":[101],"Context":[102],"Update.":[103],"Compared":[104,129],"adapted":[107],"baseline,":[108,133],"further":[110],"decreases":[111],"by":[115],"12.6%":[118],"relative,":[119],"incurring":[121],"regression":[125,137],"20%":[127],"relative.":[128,141],"non-adapted":[132],"7.1":[139],"%":[140]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":8}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}