{"id":"https://openalex.org/W4372260335","doi":"https://doi.org/10.1109/icassp49357.2023.10097142","title":"Adaptive Endpointing with Deep Contextual Multi-Armed Bandits","display_name":"Adaptive Endpointing with Deep Contextual Multi-Armed Bandits","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260335","doi":"https://doi.org/10.1109/icassp49357.2023.10097142"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097142","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10097142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5114138481","display_name":"Do June Min","orcid":"https://orcid.org/0000-0001-7830-5638"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Do June Min","raw_affiliation_strings":["University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109046112","display_name":"Anirudh Raju","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anirudh Raju","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082491203","display_name":"Colin Vaz","orcid":"https://orcid.org/0000-0002-5709-7953"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Colin Vaz","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017672130","display_name":"Di He","orcid":"https://orcid.org/0009-0008-5025-7062"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Di He","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060593241","display_name":"Venkatesh Ravichandran","orcid":"https://orcid.org/0009-0001-7214-2919"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Venkatesh Ravichandran","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085746637","display_name":"Viet Anh Trinh","orcid":"https://orcid.org/0000-0002-1660-6627"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Viet Anh Trinh","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5114138481"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":0.1905,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39294788,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9975000023841858,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9975000023841858,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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":0.839218258857727},{"id":"https://openalex.org/keywords/hyperparameter-optimization","display_name":"Hyperparameter optimization","score":0.7534793615341187},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.7456001043319702},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6084995269775391},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5722858309745789},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5474746823310852},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5070104598999023},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4827372431755066},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4495505094528198},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44010522961616516},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43904024362564087},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4337233304977417},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.42662858963012695},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.4126438796520233}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.839218258857727},{"id":"https://openalex.org/C10485038","wikidata":"https://www.wikidata.org/wiki/Q48996162","display_name":"Hyperparameter optimization","level":3,"score":0.7534793615341187},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.7456001043319702},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6084995269775391},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5722858309745789},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5474746823310852},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5070104598999023},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4827372431755066},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4495505094528198},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44010522961616516},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43904024362564087},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4337233304977417},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.42662858963012695},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.4126438796520233},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097142","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10097142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":27,"referenced_works":["https://openalex.org/W1533504578","https://openalex.org/W1903951673","https://openalex.org/W2147934395","https://openalex.org/W2406310406","https://openalex.org/W2745949735","https://openalex.org/W2746424190","https://openalex.org/W2748416658","https://openalex.org/W2748934350","https://openalex.org/W2891367150","https://openalex.org/W2963007936","https://openalex.org/W3094192145","https://openalex.org/W3143923103","https://openalex.org/W3158218109","https://openalex.org/W3161080229","https://openalex.org/W3202725408","https://openalex.org/W4221147513","https://openalex.org/W4223655162","https://openalex.org/W4224457787","https://openalex.org/W4224918838","https://openalex.org/W4289744488","https://openalex.org/W4297841778","https://openalex.org/W4389009570","https://openalex.org/W6684588631","https://openalex.org/W6743806954","https://openalex.org/W6747890380","https://openalex.org/W6753406286","https://openalex.org/W6784171646"],"related_works":["https://openalex.org/W2953665647","https://openalex.org/W4281646320","https://openalex.org/W4205712847","https://openalex.org/W3169687406","https://openalex.org/W1974336862","https://openalex.org/W4388119537","https://openalex.org/W3014750173","https://openalex.org/W3114025147","https://openalex.org/W4287818966","https://openalex.org/W3192751261"],"abstract_inverted_index":{"Current":[0],"endpointing":[1,40,53,63],"(EP)":[2],"solutions":[3],"learn":[4],"in":[5,20,69,134],"a":[6,49,96],"supervised":[7],"framework,":[8],"which":[9],"does":[10,79],"not":[11,80],"allow":[12],"the":[13,35,103,110],"model":[14],"to":[15,29,33,47,122],"incorporate":[16],"feedback":[17],"and":[18,85,125],"improve":[19],"an":[21,39,56,61,70],"online":[22,71,88],"setting.":[23],"Also,":[24],"it":[25],"is":[26],"common":[27],"practice":[28],"utilize":[30],"costly":[31],"grid-search":[32],"find":[34],"best":[36],"configuration":[37,64],"for":[38,51,59],"model.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45,94],"aim":[46],"provide":[48],"solution":[50],"adaptive":[52],"by":[54],"proposing":[55],"efficient":[57],"method":[58,78],"choosing":[60],"optimal":[62],"given":[65],"utterance-level":[66],"audio":[67],"features":[68],"setting,":[72],"while":[73,139],"avoiding":[74],"hyperparameter":[75],"grid-search.":[76],"Our":[77],"require":[81],"ground":[82],"truth":[83],"labels,":[84],"uses":[86],"only":[87],"learning":[89],"from":[90],"reward":[91],"signals.":[92],"Specifically,":[93],"propose":[95],"deep":[97,129],"contextual":[98],"multi-armed":[99],"bandit-based":[100],"approach,":[101],"combining":[102],"representational":[104],"power":[105],"of":[106,114],"neural":[107],"networks":[108],"with":[109],"action":[111],"exploration":[112],"behavior":[113],"Thomp-son":[115],"modeling":[116],"algorithms.":[117],"We":[118],"compare":[119],"our":[120,128],"approach":[121],"several":[123],"baselines,":[124],"show":[126],"that":[127],"bandit":[130],"models":[131],"also":[132],"succeed":[133],"reducing":[135],"early":[136],"cutoff":[137],"errors":[138],"maintaining":[140],"low":[141],"latency.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}