{"id":"https://openalex.org/W4392903872","doi":"https://doi.org/10.1109/icassp48485.2024.10447553","title":"SALM: Speech-Augmented Language Model with in-Context Learning for Speech Recognition and Translation","display_name":"SALM: Speech-Augmented Language Model with in-Context Learning for Speech Recognition and Translation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903872","doi":"https://doi.org/10.1109/icassp48485.2024.10447553"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447553","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447553","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/A5002433660","display_name":"Zhehuai Chen","orcid":"https://orcid.org/0000-0003-4400-5340"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhehuai Chen","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100411301","display_name":"He Huang","orcid":"https://orcid.org/0000-0002-9217-4977"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"He Huang","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054253945","display_name":"Andrei Andrusenko","orcid":"https://orcid.org/0000-0002-8697-832X"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrei Andrusenko","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088392468","display_name":"Oleksii Hrinchuk","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oleksii Hrinchuk","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069691915","display_name":"Krishna C. Puvvada","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishna C. Puvvada","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100762970","display_name":"Jason Li","orcid":"https://orcid.org/0000-0002-1150-3549"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Li","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101935896","display_name":"Subhankar Ghosh","orcid":"https://orcid.org/0000-0001-9191-5684"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Subhankar Ghosh","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040747392","display_name":"Jagadeesh Balam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jagadeesh Balam","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032957280","display_name":"Boris Ginsburg","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boris Ginsburg","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":8.0617,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.97830326,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"13521","last_page":"13525"},"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":0.9987999796867371,"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":0.9980999827384949,"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":0.7923698425292969},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6855289340019226},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.6668733358383179},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6016342043876648},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5601551532745361},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.513323962688446},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5116696357727051},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4884997606277466},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47389310598373413},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45762383937835693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7923698425292969},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6855289340019226},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.6668733358383179},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6016342043876648},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5601551532745361},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.513323962688446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5116696357727051},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4884997606277466},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47389310598373413},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45762383937835693},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447553","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447553","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":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2886319145","https://openalex.org/W2889012072","https://openalex.org/W2938704169","https://openalex.org/W2963499882","https://openalex.org/W2973727699","https://openalex.org/W2974231335","https://openalex.org/W3005302685","https://openalex.org/W3092085609","https://openalex.org/W3097777922","https://openalex.org/W3168867926","https://openalex.org/W4225308107","https://openalex.org/W4226120743","https://openalex.org/W4252812408","https://openalex.org/W4310428868","https://openalex.org/W4313679638","https://openalex.org/W4372269772","https://openalex.org/W4375958083","https://openalex.org/W4377130946","https://openalex.org/W4381827575","https://openalex.org/W4385570170","https://openalex.org/W4385822949","https://openalex.org/W4385822953","https://openalex.org/W4387595589","https://openalex.org/W4387891768","https://openalex.org/W4389524500","https://openalex.org/W4391021542","https://openalex.org/W4391021666","https://openalex.org/W4391021773","https://openalex.org/W4392903956","https://openalex.org/W4392910583","https://openalex.org/W4392979802","https://openalex.org/W4393178509","https://openalex.org/W6761551260","https://openalex.org/W6767671539","https://openalex.org/W6767997687","https://openalex.org/W6796581206","https://openalex.org/W6800875267","https://openalex.org/W6846665566","https://openalex.org/W6848735303","https://openalex.org/W6852326057","https://openalex.org/W6853249747","https://openalex.org/W6853998256","https://openalex.org/W6855414158","https://openalex.org/W6857054612"],"related_works":["https://openalex.org/W2133028525","https://openalex.org/W4229060448","https://openalex.org/W4306381730","https://openalex.org/W2981692913","https://openalex.org/W3044188621","https://openalex.org/W3184035966","https://openalex.org/W2485605994","https://openalex.org/W2160602540","https://openalex.org/W4385571108","https://openalex.org/W4321593827"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,17,21,24],"novel":[3],"Speech":[4,54,58],"Augmented":[5],"Language":[6],"Model":[7],"(SALM)":[8],"with":[9,48],"multitask":[10],"and":[11,28,35,57,74,90],"in-context":[12,65,79,98],"learning":[13,66,99],"capabilities.":[14],"SALM":[15,41],"comprises":[16],"frozen":[18],"text":[19],"LLM,":[20],"audio":[22],"encoder,":[23],"modality":[25],"adapter":[26],"module,":[27],"LoRA":[29],"layers":[30],"to":[31,83],"accommodate":[32],"speech":[33,77,92],"input":[34],"associated":[36],"task":[37,71],"instructions.":[38],"The":[39],"unified":[40],"not":[42],"only":[43],"achieves":[44],"performance":[45],"on":[46],"par":[47],"task-specific":[49],"Conformer":[50],"baselines":[51],"for":[52,72],"Automatic":[53],"Recognition":[55],"(ASR)":[56],"Translation":[59],"(AST),":[60],"but":[61],"also":[62],"exhibits":[63],"zero-shot":[64],"capabilities,":[67],"demonstrated":[68],"through":[69],"keyword-boosting":[70],"ASR":[73],"AST.":[75],"Moreover,":[76],"supervised":[78],"training":[80,89],"is":[81,106],"proposed":[82],"bridge":[84],"the":[85,97],"gap":[86],"between":[87],"LLM":[88],"downstream":[91],"tasks,":[93],"which":[94],"further":[95],"boosts":[96],"ability":[100],"of":[101],"speech-to-text":[102],"models.":[103],"Proposed":[104],"model":[105],"open-sourced":[107],"via":[108],"NeMo":[109],"toolkit":[110],"<sup":[111],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[112],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[113],".":[114]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}