{"id":"https://openalex.org/W4392904569","doi":"https://doi.org/10.1109/icassp48485.2024.10446748","title":"Promptformer: Prompted Conformer Transducer for ASR","display_name":"Promptformer: Prompted Conformer Transducer for ASR","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904569","doi":"https://doi.org/10.1109/icassp48485.2024.10446748"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446748","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446748","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/A5093734223","display_name":"Sergio Duarte-Torres","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Sergio Duarte-Torres","raw_affiliation_strings":["Amazon AGI,Aachen,Germany","Amazon AGI, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Amazon AGI,Aachen,Germany","institution_ids":["https://openalex.org/I4210089985"]},{"raw_affiliation_string":"Amazon AGI, Aachen, Germany","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026220576","display_name":"Arunasish Sen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123934","display_name":"Amazon (United Kingdom)","ror":"https://ror.org/02xey9634","country_code":"GB","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210123934"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Arunasish Sen","raw_affiliation_strings":["Amazon AGI,Cambridge,UK","Amazon AGI, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Amazon AGI,Cambridge,UK","institution_ids":["https://openalex.org/I4210123934"]},{"raw_affiliation_string":"Amazon AGI, Cambridge, UK","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081680780","display_name":"Aman Rana","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Aman Rana","raw_affiliation_strings":["Amazon AGI,Aachen,Germany","Amazon AGI, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Amazon AGI,Aachen,Germany","institution_ids":["https://openalex.org/I4210089985"]},{"raw_affiliation_string":"Amazon AGI, Aachen, Germany","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011191228","display_name":"Lukas Drude","orcid":"https://orcid.org/0000-0003-3683-5432"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lukas Drude","raw_affiliation_strings":["Amazon AGI,Aachen,Germany","Amazon AGI, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Amazon AGI,Aachen,Germany","institution_ids":["https://openalex.org/I4210089985"]},{"raw_affiliation_string":"Amazon AGI, Aachen, Germany","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045966889","display_name":"Alejandro Gomez-Alanis","orcid":"https://orcid.org/0000-0002-9797-8974"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alejandro Gomez-Alanis","raw_affiliation_strings":["Amazon AGI,Aachen,Germany","Amazon AGI, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Amazon AGI,Aachen,Germany","institution_ids":["https://openalex.org/I4210089985"]},{"raw_affiliation_string":"Amazon AGI, Aachen, Germany","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056885986","display_name":"Andreas Schwarz","orcid":"https://orcid.org/0000-0002-3883-4989"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Schwarz","raw_affiliation_strings":["Amazon AGI,Aachen,Germany","Amazon AGI, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Amazon AGI,Aachen,Germany","institution_ids":["https://openalex.org/I4210089985"]},{"raw_affiliation_string":"Amazon AGI, Aachen, Germany","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108093538","display_name":"L. R\u00e4del","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Leif R\u00e4del","raw_affiliation_strings":["Amazon AGI,Aachen,Germany","Amazon AGI, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Amazon AGI,Aachen,Germany","institution_ids":["https://openalex.org/I4210089985"]},{"raw_affiliation_string":"Amazon AGI, Aachen, Germany","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034723709","display_name":"Volker Leutnant","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Volker Leutnant","raw_affiliation_strings":["Amazon AGI,Aachen,Germany","Amazon AGI, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Amazon AGI,Aachen,Germany","institution_ids":["https://openalex.org/I4210089985"]},{"raw_affiliation_string":"Amazon AGI, Aachen, Germany","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5093734223"],"corresponding_institution_ids":["https://openalex.org/I4210089985"],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61734233,"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":"11821","last_page":"11825"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9987000226974487,"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":0.9983000159263611,"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":0.8197602033615112},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7115263938903809},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6494394540786743},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5908098816871643},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.580545961856842},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5703771114349365},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5693153738975525},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5423246026039124},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5180078148841858},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.5063260793685913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5008876323699951},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.5005292892456055},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.4838598966598511},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.42487239837646484},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34289419651031494},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07149696350097656},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07078537344932556}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8197602033615112},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7115263938903809},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6494394540786743},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5908098816871643},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.580545961856842},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5703771114349365},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5693153738975525},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5423246026039124},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5180078148841858},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.5063260793685913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5008876323699951},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.5005292892456055},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.4838598966598511},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.42487239837646484},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34289419651031494},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07149696350097656},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07078537344932556},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446748","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446748","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":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2886319145","https://openalex.org/W2896457183","https://openalex.org/W2936774411","https://openalex.org/W3093579165","https://openalex.org/W3097777922","https://openalex.org/W3097794466","https://openalex.org/W3105816068","https://openalex.org/W3163463193","https://openalex.org/W3197898596","https://openalex.org/W4224918838","https://openalex.org/W4225985539","https://openalex.org/W4226315417","https://openalex.org/W4226420874","https://openalex.org/W4283812287","https://openalex.org/W4283826357","https://openalex.org/W4285247752","https://openalex.org/W4308521139","https://openalex.org/W4372269222","https://openalex.org/W4372348570","https://openalex.org/W4372349774","https://openalex.org/W4375869066","https://openalex.org/W6631190155","https://openalex.org/W6638749077","https://openalex.org/W6755207826","https://openalex.org/W6784614252","https://openalex.org/W6809993782"],"related_works":["https://openalex.org/W3000097931","https://openalex.org/W2354322770","https://openalex.org/W4237547500","https://openalex.org/W1570848052","https://openalex.org/W2373192430","https://openalex.org/W4239268388","https://openalex.org/W1537496349","https://openalex.org/W4243305035","https://openalex.org/W2379407973","https://openalex.org/W2125195795"],"abstract_inverted_index":{"Context":[0],"cues":[1],"carry":[2],"information":[3],"which":[4],"can":[5,99],"improve":[6],"multi-turn":[7,43],"interactions":[8,44],"in":[9,33,69],"automatic":[10],"speech":[11],"recognition":[12],"(ASR)":[13],"systems.":[14],"In":[15],"this":[16],"paper,":[17],"we":[18],"introduce":[19],"a":[20,39,58,91],"novel":[21],"mechanism":[22],"inspired":[23],"by":[24],"hyper-prompting":[25],"to":[26,76],"fuse":[27],"textual":[28],"context":[29,73,96],"with":[30,42],"acoustic":[31],"representations":[32],"the":[34,70,80],"attention":[35],"mechanism.":[36],"Results":[37],"on":[38],"test":[40],"set":[41],"show":[45,62,88],"that":[46,63,89],"our":[47,64],"method":[48,65],"achieves":[49],"5.9%":[50],"relative":[51],"word":[52],"error":[53],"rate":[54],"reduction":[55],"(rWERR)":[56],"over":[57],"strong":[59],"baseline.":[60],"We":[61,86],"does":[66],"not":[67],"degrade":[68],"absence":[71],"of":[72],"and":[74],"leads":[75],"improvements":[77],"even":[78],"if":[79],"model":[81,94],"is":[82],"trained":[83],"without":[84],"context.":[85],"further":[87],"leveraging":[90],"pre-trained":[92],"sentence-piece":[93],"for":[95],"embedding":[97],"generation":[98],"outperform":[100],"an":[101],"external":[102],"BERT":[103],"model.":[104]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}