{"id":"https://openalex.org/W4408354385","doi":"https://doi.org/10.1109/icassp49660.2025.10890616","title":"Speech Recognition Rescoring with Large Speech-Text Foundation Models","display_name":"Speech Recognition Rescoring with Large Speech-Text Foundation Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354385","doi":"https://doi.org/10.1109/icassp49660.2025.10890616"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890616","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890616","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5088032905","display_name":"Prashanth Gurunath Shivakumar","orcid":"https://orcid.org/0000-0003-1632-3309"},"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":true,"raw_author_name":"Prashanth Gurunath Shivakumar","raw_affiliation_strings":["Amazon Science,Seattle,Washington,U.S.A"],"affiliations":[{"raw_affiliation_string":"Amazon Science,Seattle,Washington,U.S.A","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052467988","display_name":"Jari Kolehmainen","orcid":"https://orcid.org/0000-0002-4174-6277"},"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":"Jari Kolehmainen","raw_affiliation_strings":["Amazon Science,Seattle,Washington,U.S.A"],"affiliations":[{"raw_affiliation_string":"Amazon Science,Seattle,Washington,U.S.A","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050696303","display_name":"Aditya Gourav","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":"Aditya Gourav","raw_affiliation_strings":["Amazon Science,Seattle,Washington,U.S.A"],"affiliations":[{"raw_affiliation_string":"Amazon Science,Seattle,Washington,U.S.A","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014319412","display_name":"Yi Gu","orcid":"https://orcid.org/0000-0001-7962-9466"},"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":"Yi Gu","raw_affiliation_strings":["Amazon Science,Seattle,Washington,U.S.A"],"affiliations":[{"raw_affiliation_string":"Amazon Science,Seattle,Washington,U.S.A","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 Science,Seattle,Washington,U.S.A"],"affiliations":[{"raw_affiliation_string":"Amazon Science,Seattle,Washington,U.S.A","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 Science,Seattle,Washington,U.S.A"],"affiliations":[{"raw_affiliation_string":"Amazon Science,Seattle,Washington,U.S.A","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 Science,Seattle,Washington,U.S.A"],"affiliations":[{"raw_affiliation_string":"Amazon Science,Seattle,Washington,U.S.A","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5088032905"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02063303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.8996999859809875,"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":0.8996999859809875,"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":0.7607606649398804},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7048887014389038},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.6274818778038025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3979530334472656},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38364851474761963},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.07440528273582458}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7607606649398804},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7048887014389038},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.6274818778038025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3979530334472656},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38364851474761963},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.07440528273582458},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890616","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890616","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2024490156","https://openalex.org/W2125336414","https://openalex.org/W2799473636","https://openalex.org/W2973122799","https://openalex.org/W2995181338","https://openalex.org/W3011339933","https://openalex.org/W3016188195","https://openalex.org/W3024308166","https://openalex.org/W3095410713","https://openalex.org/W3196509775","https://openalex.org/W3198217962","https://openalex.org/W4210300569","https://openalex.org/W4221160683","https://openalex.org/W4287854499","https://openalex.org/W4297841367","https://openalex.org/W4307680525","https://openalex.org/W4385574033","https://openalex.org/W4385822355","https://openalex.org/W4385823001","https://openalex.org/W4385823154","https://openalex.org/W4389518827","https://openalex.org/W4389524500","https://openalex.org/W4391021131","https://openalex.org/W4392904805","https://openalex.org/W4392931626","https://openalex.org/W4404573785","https://openalex.org/W6769613987","https://openalex.org/W6770528390","https://openalex.org/W6771467084","https://openalex.org/W6790356757","https://openalex.org/W6799174933","https://openalex.org/W6811340617","https://openalex.org/W6847363464","https://openalex.org/W6850625674","https://openalex.org/W6852781825","https://openalex.org/W6853998256","https://openalex.org/W6857054612","https://openalex.org/W6861618871"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W2358060160","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Large":[0],"language":[1,11,44,56],"models":[2,51,60],"(LLM)":[3],"have":[4,52],"demonstrated":[5,53],"the":[6,101],"ability":[7],"to":[8,75,86,98],"understand":[9],"human":[10,77],"by":[12,27],"leveraging":[13],"large":[14,43,62,126],"amount":[15],"of":[16,64],"text":[17,49,73],"data.":[18],"Automatic":[19],"speech":[20,30,47,71],"recognition":[21],"(ASR)":[22],"systems":[23],"are":[24],"often":[25],"limited":[26],"available":[28],"transcribed":[29],"data":[31,68],"and":[32,48,66,72,128],"benefit":[33,115],"from":[34],"a":[35],"second":[36],"pass":[37],"rescoring":[38,104],"using":[39],"LLM.":[40,135],"Recently":[41],"multi-modal":[42,88],"models,":[45],"particularly":[46],"foundational":[50,59,102],"strong":[54],"spoken":[55],"understanding.":[57],"Speech-Text":[58],"leverage":[61],"amounts":[63],"unlabelled":[65],"labelled":[67],"both":[69],"in":[70,111],"modalities":[74],"model":[76,103],"language.":[78],"In":[79],"this":[80],"work,":[81],"we":[82],"propose":[83],"novel":[84],"techniques":[85],"use":[87],"LLM":[89,113],"for":[90],"ASR":[91,127],"rescoring.":[92,116],"We":[93,106],"also":[94],"explore":[95],"discriminative":[96],"training":[97],"further":[99],"improve":[100],"performance.":[105],"demonstrate":[107,119],"cross-modal":[108],"knowledge":[109],"transfer":[110],"speech-text":[112],"can":[114],"Our":[117],"experiments":[118],"up-to":[120,129],"20%":[121],"relative":[122,131],"improvements":[123,132],"over":[124,133],"Whisper":[125],"15%":[130],"text-only":[134]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}