{"id":"https://openalex.org/W4372259757","doi":"https://doi.org/10.1109/icassp49357.2023.10094808","title":"Robust Acoustic And Semantic Contextual Biasing In Neural Transducers For Speech Recognition","display_name":"Robust Acoustic And Semantic Contextual Biasing In Neural Transducers For Speech Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372259757","doi":"https://doi.org/10.1109/icassp49357.2023.10094808"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094808","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/A5055157490","display_name":"Xuandi Fu","orcid":"https://orcid.org/0000-0002-9922-6856"},"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":"Xuandi Fu","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084035667","display_name":"Kanthashree Mysore Sathyendra","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":"Kanthashree Mysore Sathyendra","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","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 P. Strimel","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040080962","display_name":"Ross McGowan","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":"Ross McGowan","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029573067","display_name":"Athanasios Mouchtaris","orcid":"https://orcid.org/0000-0001-7583-0189"},"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":"Athanasios Mouchtaris","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"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":1.0,"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":1.0,"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":0.9986000061035156,"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":0.9976999759674072,"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/utterance","display_name":"Utterance","score":0.7399048805236816},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7283037304878235},{"id":"https://openalex.org/keywords/biasing","display_name":"Biasing","score":0.6823899745941162},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6023526191711426},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5916073322296143},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.5032007098197937},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.47237327694892883},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3738606572151184},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1471489667892456},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08666926622390747},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06846106052398682}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7399048805236816},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7283037304878235},{"id":"https://openalex.org/C20254490","wikidata":"https://www.wikidata.org/wiki/Q719550","display_name":"Biasing","level":3,"score":0.6823899745941162},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6023526191711426},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5916073322296143},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5032007098197937},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.47237327694892883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3738606572151184},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1471489667892456},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08666926622390747},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06846106052398682},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"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},{"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/icassp49357.2023.10094808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094808","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","id":"https://metadata.un.org/sdg/4","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W2327501763","https://openalex.org/W2477293991","https://openalex.org/W2886319145","https://openalex.org/W2937402758","https://openalex.org/W2962760690","https://openalex.org/W2963250244","https://openalex.org/W2963979492","https://openalex.org/W2964107261","https://openalex.org/W2972625221","https://openalex.org/W2973172693","https://openalex.org/W3015686596","https://openalex.org/W3097777922","https://openalex.org/W3097794466","https://openalex.org/W3140235797","https://openalex.org/W3163462603","https://openalex.org/W3197688480","https://openalex.org/W3198004110","https://openalex.org/W3202725408","https://openalex.org/W4224918838","https://openalex.org/W4225289150","https://openalex.org/W4225985539","https://openalex.org/W4298422451","https://openalex.org/W6623517193","https://openalex.org/W6638749077","https://openalex.org/W6727099177"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2529301793","https://openalex.org/W2350724007","https://openalex.org/W2384121599","https://openalex.org/W2355751417","https://openalex.org/W2000075989","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2038083449","https://openalex.org/W4307784074"],"abstract_inverted_index":{"Attention-based":[0],"contextual":[1,37,95,106,129,169],"biasing":[2,73,96,133,163,178],"approaches":[3,28,46],"have":[4],"shown":[5],"significant":[6],"improvements":[7,200,211],"in":[8,16],"the":[9,33,43,54,102,105,123,136,150,167,199],"recognition":[10],"of":[11],"generic":[12],"and/or":[13],"personal":[14],"rare-words":[15],"End-to-End":[17],"Automatic":[18],"Speech":[19],"Recognition":[20],"(E2E":[21],"ASR)":[22],"systems":[23],"like":[24],"neural":[25,115],"transducers.":[26],"These":[27],"employ":[29],"crossattention":[30],"to":[31,42,64,83,88,93,121,131,192],"bias":[32,55],"model":[34,117,148,170],"towards":[35],"specific":[36],"entities":[38,107,130],"injected":[39],"as":[40],"bias-phrases":[41],"model.":[44,195],"Prior":[45],"typically":[47],"relied":[48],"on":[49,75,149,161,212],"subword":[50,58],"encoders":[51,120],"for":[52,72],"encoding":[53],"phrases.":[56],"However,":[57],"tokenizations":[59],"are":[60,201],"coarse":[61],"and":[62,104,176,207,216],"fail":[63],"capture":[65],"granular":[66],"pronunciation":[67,91],"information":[68],"which":[69],"is":[70],"crucial":[71],"based":[74,119],"acoustic":[76,99,109,175],"similarity.":[77],"In":[78],"this":[79],"work,":[80],"we":[81,185],"propose":[82],"use":[84],"lightweight":[85],"character":[86],"representations":[87],"encode":[89,122],"fine-grained":[90],"features":[92],"improve":[94],"guided":[97],"by":[98,135],"similarity":[100],"between":[101],"audio":[103],"(termed":[108,140],"biasing).":[110,142],"We":[111],"further":[112],"integrate":[113],"pretrained":[114],"language":[116],"(NLM)":[118],"utterance's":[124],"semantic":[125,138,141,177],"context":[126,139],"along":[127],"with":[128,205],"perform":[132],"informed":[134],"utterance\u2019s":[137],"Experiments":[143],"using":[144],"a":[145,154,181],"Conformer":[146],"Transducer":[147],"Librispeech":[151,213],"dataset":[152],"show":[153],"4.62%":[155],"-":[156],"9.26%":[157],"relative":[158,188,209],"WER":[159,189,210],"improvement":[160,190],"different":[162],"list":[164],"sizes":[165],"over":[166],"baseline":[168,194],"when":[171],"incorporating":[172],"our":[173,193],"proposed":[174],"approach.":[179],"On":[180,196],"large-scale":[182],"in-house":[183,218],"dataset,":[184],"observe":[186],"7.91%":[187],"compared":[191],"tail":[197],"utterances,":[198],"even":[202],"more":[203],"pronounced":[204],"36.80%":[206],"23.40%":[208],"rare":[214],"words":[215],"an":[217],"testset":[219],"respectively.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}