{"id":"https://openalex.org/W4372348570","doi":"https://doi.org/10.1109/icassp49357.2023.10096062","title":"Procter: Pronunciation-Aware Contextual Adapter For Personalized Speech Recognition In Neural Transducers","display_name":"Procter: Pronunciation-Aware Contextual Adapter For Personalized Speech Recognition In Neural Transducers","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372348570","doi":"https://doi.org/10.1109/icassp49357.2023.10096062"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096062","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":"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/A5020350278","display_name":"Rahul Pandey","orcid":"https://orcid.org/0000-0003-2748-0502"},"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"]},{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rahul Pandey","raw_affiliation_strings":["Amazon Alexa AI,USA","George Mason University, 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":"George Mason University, USA","institution_ids":["https://openalex.org/I162714631"]},{"raw_affiliation_string":"Amazon Alexa AI, 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 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/A5101831407","display_name":"Qi Luo","orcid":"https://orcid.org/0000-0002-4103-7112"},"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":"Qi Luo","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/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 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/A5110230355","display_name":"Ariya Rastrow","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":"Ariya Rastrow","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/A5014054572","display_name":"Ankur Gandhe","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":"Ankur Gandhe","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/A5017041805","display_name":"Denis Filimonov","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":"Denis Filimonov","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/A5023708721","display_name":"Grant P. Strimel","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":"Grant Strimel","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/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":"last","author":{"id":"https://openalex.org/A5109934165","display_name":"Ivan Bulyko","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":"Ivan Bulyko","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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9995999932289124,"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/pronunciation","display_name":"Pronunciation","score":0.854456901550293},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8359051942825317},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.7085689306259155},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.668326199054718},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.6579265594482422},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.567287802696228},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5651747584342957},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5486432313919067},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49073946475982666},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4885497987270355},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.45747140049934387},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.27747297286987305},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09638723731040955}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.854456901550293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8359051942825317},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.7085689306259155},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.668326199054718},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6579265594482422},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.567287802696228},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5651747584342957},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5486432313919067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49073946475982666},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4885497987270355},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.45747140049934387},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27747297286987305},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09638723731040955},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096062","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":[{"display_name":"Quality Education","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W2327501763","https://openalex.org/W2477293991","https://openalex.org/W2886319145","https://openalex.org/W2888779557","https://openalex.org/W2889213362","https://openalex.org/W2892009249","https://openalex.org/W2937402758","https://openalex.org/W2962760690","https://openalex.org/W2962784628","https://openalex.org/W2963240019","https://openalex.org/W2964012862","https://openalex.org/W2972625221","https://openalex.org/W2973172693","https://openalex.org/W3097794466","https://openalex.org/W3140235797","https://openalex.org/W3163462603","https://openalex.org/W3170360470","https://openalex.org/W3172443934","https://openalex.org/W3198004110","https://openalex.org/W4221160683","https://openalex.org/W4224918838","https://openalex.org/W4225985539","https://openalex.org/W4226316089","https://openalex.org/W4226380987","https://openalex.org/W4288088457","https://openalex.org/W4385245566","https://openalex.org/W6638749077","https://openalex.org/W6739901393","https://openalex.org/W6769806307","https://openalex.org/W6796456916"],"related_works":["https://openalex.org/W2160451571","https://openalex.org/W4321593827","https://openalex.org/W2495256954","https://openalex.org/W1566315437","https://openalex.org/W2259317772","https://openalex.org/W2594897229","https://openalex.org/W4221142855","https://openalex.org/W2151348424","https://openalex.org/W2050138804","https://openalex.org/W767271433"],"abstract_inverted_index":{"End-to-End":[0],"(E2E)":[1],"automatic":[2],"speech":[3],"recognition":[4],"(ASR)":[5],"systems":[6],"used":[7],"in":[8,33,38,124],"voice":[9],"assistants":[10],"often":[11,28],"have":[12,29],"difficulties":[13],"recognizing":[14],"infrequent":[15],"words":[16,27],"personalized":[17,102,105,130],"to":[18,128,142],"the":[19,39,79,84,90,111],"user,":[20],"such":[21,34],"as":[22,140],"names":[23],"and":[24,32,97,104],"places.":[25],"Rare":[26],"non-trivial":[30],"pronunciations,":[31],"cases,":[35],"human":[36],"knowledge":[37,59],"form":[40],"of":[41,115],"a":[42,50,66,71,125],"pronunciation":[43],"lexicon":[44,58],"can":[45],"be":[46],"useful.":[47],"We":[48],"propose":[49],"PROnunCiation-aware":[51],"conTextual":[52],"adaptER":[53],"(PROCTER)":[54],"that":[55,78],"dynamically":[56],"injects":[57],"into":[60],"an":[61],"RNN-T":[62,86],"model":[63,87,112],"by":[64,88,95,118],"adding":[65],"phonemic":[67],"embedding":[68],"along":[69],"with":[70,138,147],"textual":[72],"embedding.":[73],"The":[74],"experimental":[75],"results":[76],"show":[77],"proposed":[80],"PROCTER":[81],"architecture":[82],"outperforms":[83],"baseline":[85],"improving":[89],"word":[91],"error":[92],"rate":[93],"(WER)":[94],"44%":[96],"57%":[98],"when":[99,122],"measured":[100],"on":[101],"entities":[103],"rare":[106],"entities,":[107],"respectively,":[108],"while":[109],"increasing":[110],"size":[113],"(number":[114],"trainable":[116],"parameters)":[117],"only":[119,143],"1%.":[120],"Furthermore,":[121],"evaluated":[123],"zero-shot":[126],"setting":[127],"recognize":[129],"device":[131],"names,":[132],"we":[133],"observe":[134],"7%":[135],"WER":[136,145],"improvement":[137,146],"PROCTER,":[139],"compared":[141],"1%":[144],"text-only":[148],"contextual":[149],"attention.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
