{"id":"https://openalex.org/W4408352487","doi":"https://doi.org/10.1109/icassp49660.2025.10890787","title":"Bridging Modality Gap with Large Speech and Language Models for End-to-End Speech-to-Text Translation","display_name":"Bridging Modality Gap with Large Speech and Language Models for End-to-End Speech-to-Text Translation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352487","doi":"https://doi.org/10.1109/icassp49660.2025.10890787"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890787","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890787","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":"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/A5042203856","display_name":"Weitai Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weitai Zhang","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116594343","display_name":"Simran Naagar","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Simran Naagar","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087587703","display_name":"Zhongyi Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongyi Ye","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027981943","display_name":"Peiwang Tang","orcid":"https://orcid.org/0000-0003-3681-0761"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peiwang Tang","raw_affiliation_strings":["iFLYTEK Research,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102864167","display_name":"Xinyuan Zhou","orcid":"https://orcid.org/0000-0003-2815-8857"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyuan Zhou","raw_affiliation_strings":["iFLYTEK Research,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100741943","display_name":"Junhua Liu","orcid":"https://orcid.org/0000-0003-4477-7439"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhua Liu","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lirong Dai","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.019,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94340208,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"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":0.9919999837875366,"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":0.9919999837875366,"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":0.9282000064849854,"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/bridging","display_name":"Bridging (networking)","score":0.8669567108154297},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.806329071521759},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.7132788896560669},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6859642267227173},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5013689994812012},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4992549419403076},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.44212955236434937},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4109797477722168},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3888915479183197},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.35845261812210083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31557613611221313},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09444108605384827}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8669567108154297},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.806329071521759},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.7132788896560669},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6859642267227173},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5013689994812012},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4992549419403076},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44212955236434937},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4109797477722168},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3888915479183197},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.35845261812210083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31557613611221313},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09444108605384827},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890787","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890787","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":[{"score":0.44999998807907104,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2582956876","https://openalex.org/W2605131327","https://openalex.org/W2766219058","https://openalex.org/W2936774411","https://openalex.org/W2963532001","https://openalex.org/W2998386507","https://openalex.org/W3007142233","https://openalex.org/W3034571331","https://openalex.org/W3037465386","https://openalex.org/W3113676066","https://openalex.org/W4226054021","https://openalex.org/W4385570170","https://openalex.org/W4385570216","https://openalex.org/W4385573012","https://openalex.org/W4385764125","https://openalex.org/W4391021666","https://openalex.org/W4392903148","https://openalex.org/W4392903872","https://openalex.org/W4402111673","https://openalex.org/W4402111984","https://openalex.org/W4404781855","https://openalex.org/W6691680507","https://openalex.org/W6720005687","https://openalex.org/W6778883912","https://openalex.org/W6781811055","https://openalex.org/W6795829636","https://openalex.org/W6810252168","https://openalex.org/W6847363464","https://openalex.org/W6852500804","https://openalex.org/W6853998256","https://openalex.org/W6857338356","https://openalex.org/W6859099255","https://openalex.org/W6859863615","https://openalex.org/W6861707884","https://openalex.org/W6872593549"],"related_works":["https://openalex.org/W2799713421","https://openalex.org/W3007142233","https://openalex.org/W2990025607","https://openalex.org/W3045103338","https://openalex.org/W2338806053","https://openalex.org/W4385571610","https://openalex.org/W39235475","https://openalex.org/W1540615732","https://openalex.org/W3177132412","https://openalex.org/W3198731777"],"abstract_inverted_index":{"End-to-end":[0],"speech-to-text":[1],"translation":[2],"(E2E":[3],"ST)":[4],"has":[5],"increasingly":[6],"aroused":[7],"interest":[8],"and":[9,20,31,51,58,76,95,122,142,160],"attention":[10],"recently,":[11],"attempting":[12],"to":[13,38,136,157],"address":[14],"the":[15,26,46,89,103,108,117,138,150,175],"problem":[16],"of":[17,28,120],"data":[18],"scarcity":[19],"modeling":[21],"burden.":[22],"Several":[23],"attempts":[24],"exploring":[25],"combination":[27],"Large":[29,74,110],"Speech":[30,75],"Language":[32,77,111],"Models":[33,78],"into":[34,102],"a":[35,67,132],"unified":[36],"model":[37,69],"improve":[39],"E2E":[40,81],"ST":[41,144,153,179],"are":[42],"carried":[43],"out.":[44],"However,":[45],"inherent":[47],"differences":[48],"between":[49],"speech":[50,84,91,96,100,121],"text":[52,123],"modalities":[53,124],"often":[54],"impede":[55],"effective":[56],"cross-modal":[57],"cross-lingual":[59],"transfer.":[60],"In":[61],"this":[62],"study,":[63],"we":[64,129],"introduce":[65],"LaSaLM-ST,":[66],"novel":[68],"architecture":[70],"built":[71],"upon":[72],"Pre-trained":[73],"for":[79,107],"improving":[80],"ST.":[82],"Our":[83],"encoder":[85],"begins":[86],"with":[87,125],"processing":[88],"source":[90],"sequence.":[92],"An":[93],"adaptor":[94],"decoder":[97],"then":[98,115],"project":[99],"features":[101],"compatible":[104],"feature":[105],"space":[106],"decoder-only":[109],"Model":[112],"(LLM),":[113],"which":[114],"aligns":[116],"representation":[118],"spaces":[119],"attentive":[126],"interactions.":[127],"Besides,":[128],"also":[130,173],"develop":[131],"multi-step":[133],"fine-tuning":[134,145],"method":[135],"preserve":[137],"pre-trained":[139],"multilingual":[140],"knowledge":[141],"keep":[143],"stably.":[146],"Experiments":[147],"conducted":[148],"on":[149],"IWSLT2023":[151],"offline":[152],"task":[154],"from":[155],"English":[156],"German,":[158],"Chinese":[159],"Japanese":[161],"demonstrate":[162],"that":[163],"our":[164],"methodology":[165],"not":[166],"only":[167],"achieves":[168],"state-of-the-art":[169],"BLEU":[170],"scores":[171],"but":[172],"outperforms":[174],"highly":[176],"competitive":[177],"cascaded":[178],"systems":[180],"in":[181],"an":[182],"unrestricted":[183],"setting.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
