{"id":"https://openalex.org/W4408352362","doi":"https://doi.org/10.1109/icassp49660.2025.10890560","title":"Chain-of-Thought Prompting for Speech Translation","display_name":"Chain-of-Thought Prompting for Speech Translation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352362","doi":"https://doi.org/10.1109/icassp49660.2025.10890560"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890560","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890560","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/A5029338576","display_name":"Ke Hu","orcid":"https://orcid.org/0000-0002-1599-1519"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ke Hu","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002433660","display_name":"Zhehuai Chen","orcid":"https://orcid.org/0000-0003-4400-5340"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhehuai Chen","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020376803","display_name":"Chao-Han Huck Yang","orcid":"https://orcid.org/0000-0003-2879-8811"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao-Han Huck Yang","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027217976","display_name":"Piotr \u017belasko","orcid":"https://orcid.org/0000-0002-8245-0413"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Piotr \u017belasko","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088392468","display_name":"Oleksii Hrinchuk","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oleksii Hrinchuk","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026088310","display_name":"Vitaly Lavrukhin","orcid":"https://orcid.org/0009-0006-7866-8301"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vitaly Lavrukhin","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040747392","display_name":"Jagadeesh Balam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jagadeesh Balam","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032957280","display_name":"Boris Ginsburg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boris Ginsburg","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5029338576"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.6828,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.9486366,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.8302000164985657,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.8302000164985657,"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":0.7189000248908997,"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":0.637082576751709},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.56903475522995},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5639995336532593},{"id":"https://openalex.org/keywords/chain","display_name":"Chain (unit)","score":0.5362220406532288},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.4440076947212219},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3459232747554779},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.25105857849121094},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06085804104804993}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.637082576751709},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.56903475522995},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5639995336532593},{"id":"https://openalex.org/C199185054","wikidata":"https://www.wikidata.org/wiki/Q552299","display_name":"Chain (unit)","level":2,"score":0.5362220406532288},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.4440076947212219},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3459232747554779},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.25105857849121094},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06085804104804993},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890560","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890560","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W3011339933","https://openalex.org/W3174770825","https://openalex.org/W4205991051","https://openalex.org/W4226302523","https://openalex.org/W4319862635","https://openalex.org/W4385567149","https://openalex.org/W4387595589","https://openalex.org/W4391021623","https://openalex.org/W4391021627","https://openalex.org/W4391021666","https://openalex.org/W4391021773","https://openalex.org/W4392679398","https://openalex.org/W4392902925","https://openalex.org/W4392903288","https://openalex.org/W4392903872","https://openalex.org/W4392903956","https://openalex.org/W4392931630","https://openalex.org/W4402111558","https://openalex.org/W4402667113","https://openalex.org/W4402670331","https://openalex.org/W6743726175","https://openalex.org/W6767440493","https://openalex.org/W6767671539","https://openalex.org/W6767997687","https://openalex.org/W6769627184","https://openalex.org/W6778883912","https://openalex.org/W6796581206","https://openalex.org/W6809646742","https://openalex.org/W6810081322","https://openalex.org/W6847363464","https://openalex.org/W6850625674","https://openalex.org/W6856800273","https://openalex.org/W6857054612","https://openalex.org/W6859863615","https://openalex.org/W6860041859","https://openalex.org/W6861859833","https://openalex.org/W6873018358"],"related_works":["https://openalex.org/W4301342010","https://openalex.org/W158465921","https://openalex.org/W2279116787","https://openalex.org/W2261315194","https://openalex.org/W2099033952","https://openalex.org/W2520872336","https://openalex.org/W2339399820","https://openalex.org/W2338806053","https://openalex.org/W2759521758","https://openalex.org/W123774389"],"abstract_inverted_index":{"Large":[0],"language":[1,9],"models":[2,25,35],"(LLMs)":[3],"have":[4],"demonstrated":[5],"remarkable":[6],"advancements":[7],"in":[8,33,40,66,112],"understanding":[10],"and":[11,45,83,96,132,187],"generation.":[12],"Building":[13],"on":[14,70],"the":[15,109,126,144],"success":[16],"of":[17,79,156,185,197],"text-based":[18],"LLMs,":[19],"recent":[20],"research":[21],"has":[22],"adapted":[23],"these":[24,99],"to":[26,58,92,136,168,174],"use":[27],"speech":[28,42,47,81,91,104,110,169],"embeddings":[29],"for":[30,64,105,125,129],"prompting,":[31,106],"resulting":[32],"Speech-LLM":[34,68,76],"that":[36,143,180],"exhibit":[37],"strong":[38],"performance":[39,135],"automatic":[41,46],"recognition":[43],"(ASR)":[44],"translation":[48,111],"(AST).":[49],"In":[50],"this":[51],"work,":[52],"we":[53,107],"propose":[54],"a":[55,67,80,113,175,182],"novel":[56],"approach":[57],"leverage":[59],"ASR":[60,94,186],"transcripts":[61,95,100],"as":[62],"prompts":[63],"AST":[65,150,165,188],"built":[69],"an":[71,84,153,195],"encoder-decoder":[72,85],"text":[73],"LLM.":[74],"The":[75],"model":[77,130,138],"consists":[78],"encoder":[82],"structure":[86],"Megatron-T5.":[87],"By":[88],"first":[89],"decoding":[90],"generate":[93],"subsequently":[97],"using":[98],"along":[101],"with":[102],"encoded":[103],"guide":[108],"two-step":[114],"process":[115],"like":[116],"chain-of-thought":[117],"(CoT)":[118],"prompting.":[119],"Low-rank":[120],"adaptation":[121,131],"(LoRA)":[122],"is":[123],"used":[124],"T5":[127],"LLM":[128],"shows":[133],"superior":[134],"full":[137],"fine-tuning.":[139],"Experimental":[140],"results":[141],"show":[142],"proposed":[145],"CoT":[146,177],"prompting":[147,170],"significantly":[148],"improves":[149],"performance,":[151],"achieving":[152],"average":[154,196],"increase":[155],"2.4":[157],"BLEU":[158,199],"points":[159],"across":[160],"6":[161],"En\u2192X":[162],"or":[163],"X\u2192En":[164],"tasks":[166],"compared":[167,173],"alone.":[171],"Additionally,":[172],"related":[176],"prediction":[178],"method":[179,191],"predicts":[181],"concatenated":[183],"sequence":[184],"transcripts,":[189],"our":[190],"performs":[192],"better":[193],"by":[194],"2":[198],"points.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}