{"id":"https://openalex.org/W7164197310","doi":"https://doi.org/10.48550/arxiv.2606.10368","title":"Speech Meets ELF: Audio Conditional Continuous-Target Diffusion for Speech Recognition and Translation","display_name":"Speech Meets ELF: Audio Conditional Continuous-Target Diffusion for Speech Recognition and Translation","publication_year":2026,"publication_date":"2026-06-09","ids":{"openalex":"https://openalex.org/W7164197310","doi":"https://doi.org/10.48550/arxiv.2606.10368"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2606.10368","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.10368","pdf_url":"https://arxiv.org/pdf/2606.10368","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2606.10368","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058869295","display_name":"Xuanchen Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Xuanchen","raw_affiliation_strings":["Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136016731","display_name":"Tianrui Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Tianrui","raw_affiliation_strings":["Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006690717","display_name":"Yuheng Lu","orcid":"https://orcid.org/0000-0002-2767-0894","observed_orcids":["https://orcid.org/0000-0002-2767-0894","https://orcid.org/0000-0002-2271-8748"]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu, Yuheng","raw_affiliation_strings":["Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125672542","display_name":"Zikang Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Zikang","raw_affiliation_strings":["Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136085064","display_name":"Yu Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang, Yu","raw_affiliation_strings":["Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134197507","display_name":"Chenghan Lin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin, Chenghan","raw_affiliation_strings":["Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114138967","display_name":"Chenrui Cui","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cui, Chenrui","raw_affiliation_strings":["Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138380026","display_name":"Ziyang Ma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ma, Ziyang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138342765","display_name":"Xingyu Ma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726915","display_name":"Zhipu AI (China)","ror":"https://ror.org/005dzvw93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ma, Xingyu","raw_affiliation_strings":["Zhipu AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhipu AI","institution_ids":["https://openalex.org/I4401726915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028353824","display_name":"Chunyu Qiang","orcid":"https://orcid.org/0009-0007-2290-3074","observed_orcids":["https://orcid.org/0009-0007-2290-3074"]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang, Chunyu","raw_affiliation_strings":["Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136359090","display_name":"Guochen Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726915","display_name":"Zhipu AI (China)","ror":"https://ror.org/005dzvw93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu, Guochen","raw_affiliation_strings":["Zhipu AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhipu AI","institution_ids":["https://openalex.org/I4401726915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138240310","display_name":"Xie Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Xie","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105269944","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-8094-6861","observed_orcids":["https://orcid.org/0000-0002-8094-6861"]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Longbiao","raw_affiliation_strings":["Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135909674","display_name":"Jianwu Dang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dang, Jianwu","raw_affiliation_strings":["Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":9.999999747378752e-05,"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/speech-to-text","display_name":"speech-to-text","score":0.7979999780654907},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.7210000157356262},{"id":"https://openalex.org/keywords/speech-to-text-translation","display_name":"speech-to-text translation","score":0.9089999794960022},{"id":"https://openalex.org/keywords/flow-matching","display_name":"flow matching","score":0.6769999861717224},{"id":"https://openalex.org/keywords/classifier-free-guidance","display_name":"classifier-free guidance","score":0.984000027179718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803000211715698},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7495999932289124},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.490200012922287},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4738999903202057},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4684000015258789},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.4627000093460083},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44530001282691956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4447000026702881},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44440001249313354},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.43790000677108765},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4302000105381012},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.40849998593330383},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.39750000834465027},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.38679999113082886},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.37279999256134033},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3084999918937683},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.30309998989105225},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2924000024795532},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2606.10368","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.10368","pdf_url":"https://arxiv.org/pdf/2606.10368","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2606.10368","doi":"https://doi.org/10.48550/arxiv.2606.10368","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.10368","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2606.10368","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.10368","pdf_url":"https://arxiv.org/pdf/2606.10368","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7164197310.pdf","grobid_xml":"https://content.openalex.org/works/W7164197310.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2981852735","https://openalex.org/W3054645415","https://openalex.org/W4288099666","https://openalex.org/W4303647933","https://openalex.org/W4311000453","https://openalex.org/W4312661859","https://openalex.org/W4386142098","https://openalex.org/W4391835492","https://openalex.org/W4392903956","https://openalex.org/W4392931626","https://openalex.org/W4402112335","https://openalex.org/W4403583519","https://openalex.org/W4409051416","https://openalex.org/W4415194460","https://openalex.org/W4415255153","https://openalex.org/W6929399311","https://openalex.org/W7077895598","https://openalex.org/W7160596537","https://openalex.org/W7160895307"],"related_works":["https://openalex.org/W4287079508","https://openalex.org/W4389519423","https://openalex.org/W3118578889","https://openalex.org/W7148362168","https://openalex.org/W3207738474","https://openalex.org/W4414845989","https://openalex.org/W4223622550","https://openalex.org/W4411113121","https://openalex.org/W7148570168","https://openalex.org/W7138932820"],"abstract_inverted_index":{"Speech-to-text":[0],"(S2T)":[1],"systems":[2],"for":[3,28,44,78],"recognition":[4,174],"(ASR)":[5],"and":[6,63,99,113,121,132,175,179],"translation":[7],"(S2TT)":[8],"typically":[9],"generate":[10],"discrete":[11],"text":[12,76,91],"tokens.":[13],"In":[14],"contrast,":[15],"continuous-target":[16,41],"language":[17],"modelling":[18],"performs":[19],"generation":[20,165],"in":[21,152],"a":[22,59,64,148,168],"continuous":[23,154,163],"space,":[24],"yet":[25],"its":[26,89],"potential":[27],"S2T":[29],"remains":[30],"unexplored.":[31],"To":[32,82],"bridge":[33],"this":[34],"gap,":[35],"we":[36,93],"propose":[37],"ELF-S2T,":[38],"an":[39],"audio-conditioned":[40],"generative":[42],"model":[43,85],"S2T.":[45],"Built":[46],"upon":[47],"the":[48,69,74,84,102,139,144,153,162],"pre-trained":[49,90],"Embedded":[50],"Language":[51],"Flows":[52],"(ELF)":[53],"backbone,":[54],"ELF-S2T":[55,117],"processes":[56],"speech":[57],"via":[58,105],"frozen":[60],"Whisper":[61],"encoder":[62],"single":[65],"linear":[66],"projector,":[67],"prepending":[68],"resulting":[70],"audio":[71,95,103],"condition":[72,104],"to":[73],"noisy":[75],"latent":[77,155],"in-context,":[79],"flow-matching":[80],"denoising.":[81],"prevent":[83],"from":[86,143],"over-relying":[87],"on":[88,111,138],"context,":[92],"introduce":[94],"forcing":[96],"during":[97],"training,":[98],"further":[100],"amplify":[101],"classifier-free":[106],"guidance":[107],"at":[108,185],"inference.":[109],"Experiments":[110],"LibriSpeech":[112],"CoVoST2":[114],"show":[115],"that":[116],"achieves":[118],"competitive":[119],"ASR":[120,131],"S2TT":[122,133],"performance.":[123],"Crucially,":[124],"our":[125],"error":[126],"analysis":[127],"reveals":[128],"that,":[129],"although":[130],"errors":[134],"look":[135],"very":[136],"different":[137],"surface,":[140],"both":[141],"stem":[142],"same":[145],"underlying":[146],"cause,":[147],"close":[149],"distance":[150],"confusion":[151],"space.":[156],"This":[157],"finding":[158],"naturally":[159],"aligns":[160],"with":[161],"representation":[164],"paradigm,":[166],"indicating":[167],"common":[169],"semantic":[170],"mapping":[171],"process":[172],"beneath":[173],"translation.":[176],"Our":[177],"code":[178],"pretrained":[180],"models":[181],"are":[182],"publicly":[183],"available":[184],"https://github.com/Sslnon/ELF-S2T.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-06-11T00:00:00"}