{"id":"https://openalex.org/W4392904338","doi":"https://doi.org/10.1109/icassp48485.2024.10448320","title":"Hot-Fixing Wake Word Recognition for End-to-End ASR Via Neural Model Reprogramming","display_name":"Hot-Fixing Wake Word Recognition for End-to-End ASR Via Neural Model Reprogramming","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904338","doi":"https://doi.org/10.1109/icassp48485.2024.10448320"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448320","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":"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/A5092048123","display_name":"Pin-Jui Ku","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"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":true,"raw_author_name":"Pin-Jui Ku","raw_affiliation_strings":["Georgia Institute of Technology,USA","Amazon, USA","Georgia Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046605612","display_name":"I\u2010Ming Chen","orcid":"https://orcid.org/0000-0002-4831-3781"},"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":"I-Fan Chen","raw_affiliation_strings":["Amazon,USA","Amazon, USA"],"affiliations":[{"raw_affiliation_string":"Amazon,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020376803","display_name":"Chao-Han Huck Yang","orcid":"https://orcid.org/0000-0003-2879-8811"},"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":"Chao-Han Huck Yang","raw_affiliation_strings":["Amazon,USA","Amazon, USA"],"affiliations":[{"raw_affiliation_string":"Amazon,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon, 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,USA","Amazon, USA"],"affiliations":[{"raw_affiliation_string":"Amazon,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076504502","display_name":"Pranav Dheram","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":"Pranav Dheram","raw_affiliation_strings":["Amazon,USA","Amazon, USA"],"affiliations":[{"raw_affiliation_string":"Amazon,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029777844","display_name":"Pegah Ghahremani","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":"Pegah Ghahremani","raw_affiliation_strings":["Amazon,USA","Amazon, USA"],"affiliations":[{"raw_affiliation_string":"Amazon,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027102522","display_name":"Brian King","orcid":"https://orcid.org/0000-0002-5300-5564"},"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":"Brian King","raw_affiliation_strings":["Amazon,USA","Amazon, USA"],"affiliations":[{"raw_affiliation_string":"Amazon,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375136","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0003-4690-1886"},"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":"Jing Liu","raw_affiliation_strings":["Amazon,USA","Amazon, USA"],"affiliations":[{"raw_affiliation_string":"Amazon,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076628167","display_name":"Roger Ren","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":"Roger Ren","raw_affiliation_strings":["Amazon,USA","Amazon, USA"],"affiliations":[{"raw_affiliation_string":"Amazon,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005758272","display_name":"Phani Sankar Nidadavolu","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Phani Sankar Nidadavolu","raw_affiliation_strings":["Georgia Institute of Technology,USA","Georgia Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5092048123"],"corresponding_institution_ids":["https://openalex.org/I130701444","https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61729328,"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":"10816","last_page":"10820"},"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":0.9962000250816345,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9950000047683716,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7627758979797363},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7005093693733215},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6670318245887756},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6597989201545715},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6561347246170044},{"id":"https://openalex.org/keywords/wake","display_name":"Wake","score":0.5292204022407532},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5127424001693726},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4859384298324585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4817928671836853},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.46778950095176697},{"id":"https://openalex.org/keywords/word-recognition","display_name":"Word recognition","score":0.46168890595436096},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4479319155216217},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42750269174575806},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.41971254348754883},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08030211925506592},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07670813798904419}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7627758979797363},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7005093693733215},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6670318245887756},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6597989201545715},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6561347246170044},{"id":"https://openalex.org/C48939323","wikidata":"https://www.wikidata.org/wiki/Q294879","display_name":"Wake","level":2,"score":0.5292204022407532},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5127424001693726},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4859384298324585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4817928671836853},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.46778950095176697},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.46168890595436096},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4479319155216217},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42750269174575806},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.41971254348754883},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08030211925506592},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07670813798904419},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448320","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":27,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2972359262","https://openalex.org/W2972625221","https://openalex.org/W3015927303","https://openalex.org/W3016160783","https://openalex.org/W3016256870","https://openalex.org/W3093383631","https://openalex.org/W3097239815","https://openalex.org/W3097794466","https://openalex.org/W3100460087","https://openalex.org/W3162665866","https://openalex.org/W3174784402","https://openalex.org/W3209059054","https://openalex.org/W4205991051","https://openalex.org/W4224918838","https://openalex.org/W4225985539","https://openalex.org/W4226162428","https://openalex.org/W4285247752","https://openalex.org/W4297841687","https://openalex.org/W4319862674","https://openalex.org/W4322825254","https://openalex.org/W4372260195","https://openalex.org/W4372346241","https://openalex.org/W6752946794","https://openalex.org/W6796456916","https://openalex.org/W6796581206","https://openalex.org/W6850477478"],"related_works":["https://openalex.org/W2916997151","https://openalex.org/W2495256954","https://openalex.org/W2259317772","https://openalex.org/W2949174760","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W4290708361","https://openalex.org/W2129812225"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"two":[3],"novel":[4],"variants":[5],"of":[6,37,67,117],"neural":[7],"reprogramming":[8],"to":[9,42,76,124,135],"enhance":[10],"wake":[11,40,50,86,95,137],"word":[12,41,51,87,138],"recognition":[13,139],"in":[14,70,141],"streaming":[15],"end-to-end":[16],"ASR":[17,44,144],"models":[18,145],"without":[19,146],"updating":[20],"model":[21,82,150],"weights.":[22],"The":[23,53],"first,":[24],"\"trigger-frame":[25],"reprogramming\",":[26],"prepends":[27],"the":[28,34,38,59,68,71,97,118,147],"input":[29],"speech":[30],"feature":[31],"sequence":[32],"with":[33,83,107],"learned":[35],"trigger-frames":[36],"target":[39],"adjust":[43],"model\u2019s":[45],"hidden":[46,65],"states":[47],"for":[48,149],"improved":[49],"recognition.":[52],"second,":[54],"\"predictor-state":[55],"initialization\",":[56],"trains":[57],"only":[58],"initial":[60],"state":[61],"vectors":[62],"(cell":[63],"and":[64,102],"states)":[66],"LSTMs":[69],"prediction":[72],"network.":[73],"When":[74],"applying":[75],"a":[77,84],"baseline":[78],"LibriSpeech":[79],"Emformer":[80],"RNN-T":[81],"98%":[85],"verification":[88],"false":[89,111],"rejection":[90],"rate":[91],"(FRR)":[92],"on":[93,110],"unseen":[94],"words,":[96],"proposed":[98,119],"approaches":[99,120,129],"achieve":[100],"76%":[101],"97%":[103],"relative":[104],"FRR":[105],"reductions":[106],"no":[108],"increase":[109],"acceptance":[112],"rate.":[113],"In-depth":[114],"characteristic":[115],"analyses":[116],"are":[121],"also":[122],"conducted":[123],"provide":[125],"deeper":[126],"insights.":[127],"These":[128],"offer":[130],"an":[131],"effective":[132],"hot-fixing":[133],"methods":[134],"improve":[136],"performance":[140],"deployed":[142],"production":[143],"need":[148],"updates.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}