{"id":"https://openalex.org/W4224931284","doi":"https://doi.org/10.1109/icassp43922.2022.9746935","title":"CPT: Cross-Modal Prefix-Tuning for Speech-To-Text Translation","display_name":"CPT: Cross-Modal Prefix-Tuning for Speech-To-Text Translation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224931284","doi":"https://doi.org/10.1109/icassp43922.2022.9746935"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746935","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746935","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5101758551","display_name":"Yukun Ma","orcid":"https://orcid.org/0000-0002-7055-3597"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yukun Ma","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101562097","display_name":"Trung Hieu Nguyen","orcid":"https://orcid.org/0000-0002-2683-253X"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trung Hieu Nguyen","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080757156","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0001-8371-0590"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210095624"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6217","last_page":"6221"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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/prefix","display_name":"Prefix","score":0.9308526515960693},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.838373064994812},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.675276517868042},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6743018627166748},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6547530889511108},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6387783288955688},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5276055335998535},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.48274487257003784},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41881275177001953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4040506184101105},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.053560107946395874}],"concepts":[{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.9308526515960693},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.838373064994812},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.675276517868042},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6743018627166748},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6547530889511108},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6387783288955688},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5276055335998535},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.48274487257003784},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41881275177001953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4040506184101105},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.053560107946395874},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746935","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746935","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2113106066","https://openalex.org/W2964161387","https://openalex.org/W2964303773","https://openalex.org/W2970476646","https://openalex.org/W3001434439","https://openalex.org/W3015633994","https://openalex.org/W3036601975","https://openalex.org/W3097301532","https://openalex.org/W3156476125","https://openalex.org/W3172698324","https://openalex.org/W3173767661","https://openalex.org/W3174770825","https://openalex.org/W3175557894","https://openalex.org/W3176382501","https://openalex.org/W3176693010","https://openalex.org/W3176711365","https://openalex.org/W3197771105","https://openalex.org/W4205991051","https://openalex.org/W4287113019","https://openalex.org/W6759579507","https://openalex.org/W6780218876","https://openalex.org/W6785130102","https://openalex.org/W6797716411"],"related_works":["https://openalex.org/W2142481367","https://openalex.org/W3196321793","https://openalex.org/W3080705045","https://openalex.org/W2385527937","https://openalex.org/W2005880840","https://openalex.org/W2507465767","https://openalex.org/W4385305499","https://openalex.org/W2047674875","https://openalex.org/W2883671469","https://openalex.org/W2728761353"],"abstract_inverted_index":{"Speech":[0],"translation":[1,99,115,144],"models":[2],"benefit":[3],"from":[4],"adapting":[5,139],"multilingual":[6],"pretrained":[7,18,66],"language":[8],"models.":[9],"However,":[10],"such":[11],"adaptation":[12,29,37],"modifies":[13],"the":[14,17,42,59,75,82,85,95,109,119,123,129],"parameters":[15,46,76],"in":[16,52,100,122],"model":[19,86],"to":[20,117],"favor":[21],"a":[22,27,65,104,140],"specific":[23],"task.":[24],"Prefix-tuning,":[25],"as":[26,34],"lightweight":[28],"technique,":[30],"has":[31,48],"recently":[32],"emerged":[33],"an":[35],"efficient":[36],"method":[38],"that":[39,107,128],"significantly":[40],"reduces":[41],"number":[43],"of":[44,61,64,77,84,97],"trainable":[45],"and":[47,114,136,143],"demonstrated":[49],"great":[50],"potential":[51],"low-resource":[53],"settings.":[54],"It":[55],"inserts":[56],"prefixes":[57,78],"into":[58],"output":[60],"each":[62],"layer":[63],"model,":[67],"without":[68],"modifying":[69],"its":[70],"parameters.":[71],"During":[72],"training,":[73],"only":[74],"are":[79,87],"updated":[80],"while":[81],"rest":[83],"being":[88],"frozen.":[89],"In":[90],"this":[91],"paper,":[92],"we":[93],"improve":[94],"performance":[96],"speech":[98,112,141],"medium-/low-resource":[101],"settings":[102],"by":[103],"cross-modal":[105,131],"prefix":[106],"bridges":[108],"gap":[110],"between":[111],"input":[113],"modules":[116],"reduce":[118],"information":[120],"loss":[121],"cascaded":[124],"model.":[125],"We":[126],"show":[127],"proposed":[130],"prefix-tuning":[132],"is":[133],"effective,":[134],"robust":[135],"parameter-efficient":[137],"for":[138],"recognition":[142],"pipeline.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}