{"id":"https://openalex.org/W7117449328","doi":"https://doi.org/10.1109/access.2025.3649090","title":"Cross-Attention Reprogramming for ASR: Bridging Discrete Speech Units and Pretrained Language Models","display_name":"Cross-Attention Reprogramming for ASR: Bridging Discrete Speech Units and Pretrained Language Models","publication_year":2025,"publication_date":"2025-12-29","ids":{"openalex":"https://openalex.org/W7117449328","doi":"https://doi.org/10.1109/access.2025.3649090"},"language":null,"primary_location":{"id":"doi:10.1109/access.2025.3649090","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3649090","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3649090","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016978905","display_name":"Pei-Jun Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Pei-Jun Liao","raw_affiliation_strings":["Graduate Institute of Electrical Engineering, National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0009-0002-5992-2846","affiliations":[{"raw_affiliation_string":"Graduate Institute of Electrical Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120054983","display_name":"Hung-yi Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yi Lee","raw_affiliation_strings":["Graduate Institute of Electrical Engineering, National Taiwan University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Electrical Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033417091","display_name":"H. L. Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-3599-5071","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74458058,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"662","last_page":"678"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5432999730110168,"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":0.5432999730110168,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.36320000886917114,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.011599999852478504,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/language-model","display_name":"Language model","score":0.644599974155426},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6270999908447266},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5054000020027161},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.49140000343322754},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.48510000109672546},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.47130000591278076},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.4494999945163727},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4228000044822693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8197000026702881},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.644599974155426},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6270999908447266},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6245999932289124},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5054000020027161},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49219998717308044},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49140000343322754},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.48510000109672546},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4803999960422516},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.47130000591278076},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.4494999945163727},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4228000044822693},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.40540000796318054},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.3741999864578247},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2773999869823456},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/access.2025.3649090","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3649090","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3649090","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3649090","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6755986213684082}],"awards":[{"id":"https://openalex.org/G7340088035","display_name":null,"funder_award_id":"NSTC 112-2221-E-001-009-MY3","funder_id":"https://openalex.org/F4320331164","funder_display_name":"National Science and Technology Council"}],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1566256432","https://openalex.org/W2027461913","https://openalex.org/W2123649031","https://openalex.org/W2127141656","https://openalex.org/W2136023023","https://openalex.org/W2995181338","https://openalex.org/W3015356564","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221146627","https://openalex.org/W4296069362","https://openalex.org/W4372266960","https://openalex.org/W4372270126","https://openalex.org/W4372347505","https://openalex.org/W4375869259","https://openalex.org/W4381786045","https://openalex.org/W4385245566","https://openalex.org/W4385570550","https://openalex.org/W4385571440","https://openalex.org/W4385807416","https://openalex.org/W4385822683","https://openalex.org/W4392909068","https://openalex.org/W4402111259","https://openalex.org/W4402111612","https://openalex.org/W4402111789","https://openalex.org/W4402112125","https://openalex.org/W4402112493","https://openalex.org/W4405599885","https://openalex.org/W4405709818","https://openalex.org/W4406461496","https://openalex.org/W4408352084","https://openalex.org/W4410770311","https://openalex.org/W4415433821","https://openalex.org/W4415433896"],"related_works":[],"abstract_inverted_index":{"In":[0,73],"automatic":[1],"speech":[2,15,22,212,223,227],"recognition":[3,229],"(ASR),":[4],"one":[5],"emerging":[6],"direction":[7],"is":[8,34,55,237],"to":[9,47,67,83,111,121,198],"convert":[10],"a":[11,18,26,79,99,195,208],"sequence":[12,19],"of":[13,20,31,75,136,222],"continuous":[14],"features":[16],"into":[17],"discrete":[21],"units":[23],"(DSUs)":[24],"using":[25,199],"quantizer.":[27],"A":[28],"key":[29],"advantage":[30],"DSU":[32,109],"representations":[33,213],"their":[35],"compatibility":[36],"with":[37,116,214],"pretrained":[38],"language":[39,216],"models":[40,217],"(PLMs),":[41],"where":[42],"DSUs":[43,115],"are":[44],"directly":[45,122],"mapped":[46],"PLM":[48,86,118,125,200],"token":[49],"indices":[50],"and":[51,139,142,162,165,171,189,206,230],"the":[52,70,85,91,108,114,117,124,133,147,176,184],"embedding":[53,87,201],"layer":[54],"fine-tuned.":[56],"However,":[57],"this":[58],"strategy":[59],"may":[60],"rely":[61],"solely":[62],"on":[63,132,159],"large-scale":[64],"training":[65],"data":[66,167],"compensate":[68],"for":[69,210],"modality":[71],"mismatch.":[72],"light":[74],"this,":[76],"we":[77,97],"explore":[78],"more":[80],"effective":[81],"way":[82],"exploit":[84],"dictionary.":[88],"Inspired":[89],"by":[90],"recent":[92],"time-series":[93],"forecasting":[94],"model":[95],"Time-LLM,":[96],"introduce":[98],"cross-attention":[100],"reprogramming":[101,178],"mechanism":[102],"that":[103],"incorporates":[104],"codebook":[105],"information":[106],"from":[107,168],"quantizer":[110],"better":[112],"align":[113],"embeddings.":[119],"Compared":[120],"fine-tuning":[123,185],"embeddings,":[126],"our":[127,157],"method":[128,158,179],"achieves":[129,143],"consistent":[130],"improvements":[131],"ASR":[134,149],"task":[135],"Discrete":[137],"Audio":[138],"Speech":[140],"Benchmark,":[141],"state-of-the-art":[144],"performance":[145],"under":[146],"DASB-style":[148],"setting":[150],"in":[151,187,203,218],"most":[152],"cases.":[153],"We":[154],"also":[155],"evaluate":[156],"LibriSpeech-960,":[160],"LibriLight-10,":[161],"Swedish,":[163],"Czech,":[164],"Hungarian":[166],"Common":[169],"Voice,":[170],"observe":[172],"similar":[173],"trends.":[174],"Notably,":[175],"proposed":[177],"shows":[180],"clear":[181],"gains":[182],"over":[183],"baseline":[186],"cross-lingual":[188],"low-resource":[190],"settings.":[191],"This":[192],"study":[193],"proposes":[194],"new":[196],"approach":[197],"dictionaries":[202],"DSU-based":[204],"ASR,":[205],"lays":[207],"foundation":[209],"combining":[211],"large":[215],"other":[219],"discriminative":[220],"tasks":[221],"processing":[224],"such":[225],"as":[226],"emotion":[228],"spoken":[231],"question":[232],"answering.":[233],"The":[234],"inference":[235],"recipe":[236],"available":[238],"at":[239],"https://github.com/d06921018/CATT-RPG_for_ASR.":[240]},"counts_by_year":[],"updated_date":"2026-01-08T20:05:33.558190","created_date":"2025-12-29T00:00:00"}