{"id":"https://openalex.org/W4372260576","doi":"https://doi.org/10.1109/icassp49357.2023.10095186","title":"BECTRA: Transducer-Based End-To-End ASR with Bert-Enhanced Encoder","display_name":"BECTRA: Transducer-Based End-To-End ASR with Bert-Enhanced Encoder","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260576","doi":"https://doi.org/10.1109/icassp49357.2023.10095186"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5102017467","display_name":"Yosuke Higuchi","orcid":"https://orcid.org/0000-0003-4500-8957"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yosuke Higuchi","raw_affiliation_strings":["Waseda University,Japan","Waseda University, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087632404","display_name":"Tetsuji Ogawa","orcid":"https://orcid.org/0000-0002-7316-2073"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuji Ogawa","raw_affiliation_strings":["Waseda University,Japan","Waseda University, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101188700","display_name":"Tetsunori Kobayashi","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsunori Kobayashi","raw_affiliation_strings":["Waseda University,Japan","Waseda University, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102017467"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":2.0463,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89139657,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.8294833898544312},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7931591272354126},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6631453037261963},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6536955833435059},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.642362117767334},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.582861602306366},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5045450925827026},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4873529374599457},{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.4647108316421509},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4122235178947449},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32166847586631775},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1356751024723053},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08993089199066162},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08523449301719666},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06542554497718811}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8294833898544312},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7931591272354126},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6631453037261963},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6536955833435059},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.642362117767334},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.582861602306366},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5045450925827026},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4873529374599457},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.4647108316421509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4122235178947449},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32166847586631775},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1356751024723053},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08993089199066162},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08523449301719666},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06542554497718811},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7900000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338246","display_name":"ACT-X","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1828163288","https://openalex.org/W2127141656","https://openalex.org/W2251321385","https://openalex.org/W2407080277","https://openalex.org/W2896457183","https://openalex.org/W2936774411","https://openalex.org/W2946417913","https://openalex.org/W2962780374","https://openalex.org/W2963242190","https://openalex.org/W2963979492","https://openalex.org/W2973122799","https://openalex.org/W2979826702","https://openalex.org/W2988975212","https://openalex.org/W2990391581","https://openalex.org/W3024308166","https://openalex.org/W3034775979","https://openalex.org/W3035445001","https://openalex.org/W3096297644","https://openalex.org/W3097777922","https://openalex.org/W3097882114","https://openalex.org/W3122931219","https://openalex.org/W3141961557","https://openalex.org/W3155427814","https://openalex.org/W3161048756","https://openalex.org/W3162249256","https://openalex.org/W3162899666","https://openalex.org/W3164692279","https://openalex.org/W3197304116","https://openalex.org/W3200601846","https://openalex.org/W4210300569","https://openalex.org/W4210663600","https://openalex.org/W4210758944","https://openalex.org/W4221151577","https://openalex.org/W4224916448","https://openalex.org/W4225824617","https://openalex.org/W4226521565","https://openalex.org/W4292779060","https://openalex.org/W4297841367","https://openalex.org/W4319862680","https://openalex.org/W4385245566","https://openalex.org/W4385567350","https://openalex.org/W6631190155","https://openalex.org/W6638749077","https://openalex.org/W6691770337","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6770528390","https://openalex.org/W6774835902","https://openalex.org/W6778883912","https://openalex.org/W6845595086"],"related_works":["https://openalex.org/W2012283803","https://openalex.org/W4384820447","https://openalex.org/W2072454424","https://openalex.org/W2117438306","https://openalex.org/W2185942010","https://openalex.org/W2260725127","https://openalex.org/W2004297762","https://openalex.org/W1992056405","https://openalex.org/W1966826629","https://openalex.org/W767846903"],"abstract_inverted_index":{"We":[0],"present":[1],"BERT-CTC-Transducer":[2],"(BECTRA),":[3],"a":[4,17,21,60,75,78,102,108,123,127,141],"novel":[5,142],"end-to-end":[6],"automatic":[7],"speech":[8],"recognition":[9],"(E2E-ASR)":[10],"model":[11,25],"formulated":[12],"by":[13,174],"the":[14,53,56,131,134,178],"transducer":[15,135],"with":[16,177],"BERT-enhanced":[18],"encoder.":[19],"Integrating":[20],"large-scale":[22],"pre-trained":[23,61],"language":[24],"(LM)":[26],"into":[27],"E2E-ASR":[28,68,100],"has":[29],"been":[30],"actively":[31],"studied,":[32],"aiming":[33],"to":[34,73],"utilize":[35],"versatile":[36],"linguistic":[37],"knowledge":[38],"for":[39,59,67,114,126,145],"generating":[40],"accurate":[41],"text.":[42],"One":[43],"crucial":[44],"factor":[45],"that":[46,97,170],"makes":[47],"this":[48],"integration":[49],"challenging":[50],"lies":[51],"in":[52,161],"vocabulary":[54,57,103,124,179],"mismatch;":[55],"constructed":[58],"LM":[62],"is":[63,71,107],"generally":[64],"too":[65],"large":[66],"training":[69],"and":[70,117,136,151,167],"likely":[72],"have":[74],"mismatch":[76,180],"against":[77],"target":[79,128],"ASR":[80,158],"domain.":[81],"To":[82],"overcome":[83],"such":[84],"an":[85,90,119],"issue,":[86],"we":[87,138],"propose":[88,140],"BECTRA,":[89],"extended":[91],"version":[92],"of":[93,104,133,148,163],"our":[94],"previous":[95],"BERT-CTC,":[96,137],"realizes":[98],"BERT-based":[99],"using":[101,122],"interest.":[105],"BECTRA":[106,171],"transducer-based":[109],"model,":[110],"which":[111],"adopts":[112],"BERT-CTC":[113,173],"its":[115],"encoder":[116],"trains":[118],"ASR-specific":[120],"decoder":[121],"suitable":[125],"task.":[129],"With":[130],"combination":[132],"also":[139],"inference":[143],"algorithm":[144],"taking":[146],"advantage":[147],"both":[149],"autoregressive":[150],"non-autoregressive":[152],"decoding.":[153],"Experimental":[154],"results":[155],"on":[156],"several":[157],"tasks,":[159],"varying":[160],"amounts":[162],"data,":[164],"speaking":[165],"styles,":[166],"languages,":[168],"demonstrate":[169],"outperforms":[172],"effectively":[175],"dealing":[176],"while":[181],"exploiting":[182],"BERT":[183],"knowledge.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}