{"id":"https://openalex.org/W7148362011","doi":"https://doi.org/10.1109/asru65441.2025.11434782","title":"All-in-One ASR: Unifying Encoder-Decoder Models of CTC, Attention, and Transducer in Dual-Mode ASR","display_name":"All-in-One ASR: Unifying Encoder-Decoder Models of CTC, Attention, and Transducer in Dual-Mode ASR","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148362011","doi":"https://doi.org/10.1109/asru65441.2025.11434782"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5032842000","display_name":"Takafumi Moriya","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takafumi Moriya","raw_affiliation_strings":["NTT, Inc,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102851028","display_name":"Masato Mimura","orcid":"https://orcid.org/0000-0002-2403-0680"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Mimura","raw_affiliation_strings":["NTT, Inc,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132794058","display_name":"Tomohiro Tanaka","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Tanaka","raw_affiliation_strings":["NTT, Inc,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132808351","display_name":"Hiroshi Sato","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Sato","raw_affiliation_strings":["NTT, Inc,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":["NTT, Inc,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101949937","display_name":"Atsunori Ogawa","orcid":"https://orcid.org/0000-0002-2888-101X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsunori Ogawa","raw_affiliation_strings":["NTT, Inc,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5032842000"],"corresponding_institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"],"apc_list":null,"apc_paid":null,"fwci":1.2783,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85846642,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.08320000022649765,"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"}},"topics":[{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.08320000022649765,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0778999999165535,"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/T11021","display_name":"ECG Monitoring and Analysis","score":0.07760000228881836,"subfield":{"id":"https://openalex.org/subfields/2705","display_name":"Cardiology and Cardiovascular Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.5073000192642212},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3188000023365021},{"id":"https://openalex.org/keywords/transductor","display_name":"Transductor","score":0.2867000102996826},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.26330000162124634}],"concepts":[{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.5214999914169312},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.5073000192642212},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5029000043869019},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3188000023365021},{"id":"https://openalex.org/C156164531","wikidata":"https://www.wikidata.org/wiki/Q16930326","display_name":"Transductor","level":3,"score":0.2867000102996826},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.274399995803833},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.27070000767707825},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25839999318122864},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2574999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.422929972410202,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1836465849","https://openalex.org/W2064675550","https://openalex.org/W2127141656","https://openalex.org/W2407080277","https://openalex.org/W2631415506","https://openalex.org/W2750499125","https://openalex.org/W2766219058","https://openalex.org/W2936123380","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2963240019","https://openalex.org/W2963609956","https://openalex.org/W2964084166","https://openalex.org/W2972389417","https://openalex.org/W2972440193","https://openalex.org/W2972474532","https://openalex.org/W3007073761","https://openalex.org/W3008037978","https://openalex.org/W3008898571","https://openalex.org/W3011339933","https://openalex.org/W3013139777","https://openalex.org/W3015190365","https://openalex.org/W3015974384","https://openalex.org/W3015995734","https://openalex.org/W3016010032","https://openalex.org/W3016234571","https://openalex.org/W3048407879","https://openalex.org/W3097777922","https://openalex.org/W3133822476","https://openalex.org/W3148654612","https://openalex.org/W3152221657","https://openalex.org/W3160766462","https://openalex.org/W3161873870","https://openalex.org/W3163300396","https://openalex.org/W3163560333","https://openalex.org/W3198254488","https://openalex.org/W3198442913","https://openalex.org/W3207629995","https://openalex.org/W3211278025","https://openalex.org/W4210663600","https://openalex.org/W4224137820","https://openalex.org/W4224920108","https://openalex.org/W4224925623","https://openalex.org/W4226491018","https://openalex.org/W4283700324","https://openalex.org/W4297841877","https://openalex.org/W4319862683","https://openalex.org/W4319862724","https://openalex.org/W4372260137","https://openalex.org/W4372346432","https://openalex.org/W4385245566","https://openalex.org/W4385571513","https://openalex.org/W4385823037","https://openalex.org/W4385823307","https://openalex.org/W4388017359","https://openalex.org/W4391021708","https://openalex.org/W4392903330","https://openalex.org/W4402112354","https://openalex.org/W4402115989","https://openalex.org/W4406458406","https://openalex.org/W4408352482","https://openalex.org/W4408353174","https://openalex.org/W4408353520","https://openalex.org/W4408355618","https://openalex.org/W4410087476","https://openalex.org/W4415433437"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,10,68,80],"unified":[4,82],"framework,":[5],"All-in-One":[6,87],"ASR,":[7],"that":[8,71,86],"allows":[9],"single":[11,81],"model":[12,93],"to":[13],"support":[14],"multiple":[15],"automatic":[16],"speech":[17],"recognition":[18,101,123],"(ASR)":[19],"paradigms,":[20],"including":[21],"connectionist":[22],"temporal":[23],"classification":[24],"(CTC),":[25],"attention-based":[26],"encoder-decoder":[27],"(AED),":[28],"and":[29,34,44,59],"Transducer,":[30],"in":[31,122],"both":[32],"offline":[33],"streaming":[35],"modes.":[36],"While":[37],"each":[38,54],"ASR":[39,77,88,106,117],"architecture":[40],"offers":[41],"distinct":[42],"advantages":[43],"trade-offs":[45],"depending":[46],"on":[47],"the":[48,91,100,112],"application,":[49],"maintaining":[50],"separate":[51],"models":[52],"for":[53],"scenario":[55],"incurs":[56],"substantial":[57],"development":[58],"deployment":[60],"costs.":[61],"To":[62],"address":[63],"this":[64],"issue,":[65],"we":[66],"introduce":[67],"multi-mode":[69],"joiner":[70],"enables":[72],"seamless":[73],"integration":[74],"of":[75,103,115],"various":[76],"modes":[78],"within":[79],"model.":[83],"Experiments":[84],"show":[85],"significantly":[89],"reduces":[90],"total":[92],"footprint":[94],"while":[95],"matching":[96],"or":[97],"even":[98],"surpassing":[99],"performance":[102],"individually":[104],"optimized":[105],"models.":[107],"Furthermore,":[108],"joint":[109],"decoding":[110],"leverages":[111],"complementary":[113],"strengths":[114],"different":[116],"modes,":[118],"yielding":[119],"additional":[120],"improvements":[121],"accuracy.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2026-04-03T00:00:00"}