{"id":"https://openalex.org/W4319862255","doi":"https://doi.org/10.1109/slt54892.2023.10022656","title":"E-Branchformer: Branchformer with Enhanced Merging for Speech Recognition","display_name":"E-Branchformer: Branchformer with Enhanced Merging for Speech Recognition","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862255","doi":"https://doi.org/10.1109/slt54892.2023.10022656"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022656","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5052377938","display_name":"Kwangyoun Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kwangyoun Kim","raw_affiliation_strings":["ASAPP Inc.,Mountain View,CA,USA","ASAPP Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"ASAPP Inc.,Mountain View,CA,USA","institution_ids":["https://openalex.org/I1283576576"]},{"raw_affiliation_string":"ASAPP Inc., Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074393700","display_name":"Felix Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Felix Wu","raw_affiliation_strings":["ASAPP Inc.,Mountain View,CA,USA","ASAPP Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"ASAPP Inc.,Mountain View,CA,USA","institution_ids":["https://openalex.org/I1283576576"]},{"raw_affiliation_string":"ASAPP Inc., Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033862822","display_name":"Yifan Peng","orcid":"https://orcid.org/0000-0002-8581-8674"},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]},{"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":"Yifan Peng","raw_affiliation_strings":["ASAPP Inc.,Mountain View,CA,USA","ASAPP Inc., Mountain View, CA, USA","Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"ASAPP Inc.,Mountain View,CA,USA","institution_ids":["https://openalex.org/I1283576576"]},{"raw_affiliation_string":"ASAPP Inc., Mountain View, CA, USA","institution_ids":[]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101875418","display_name":"Jing Pan","orcid":"https://orcid.org/0000-0002-5178-2247"},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Pan","raw_affiliation_strings":["ASAPP Inc.,Mountain View,CA,USA","ASAPP Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"ASAPP Inc.,Mountain View,CA,USA","institution_ids":["https://openalex.org/I1283576576"]},{"raw_affiliation_string":"ASAPP Inc., Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006917911","display_name":"Prashant Sridhar","orcid":null},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prashant Sridhar","raw_affiliation_strings":["ASAPP Inc.,Mountain View,CA,USA","ASAPP Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"ASAPP Inc.,Mountain View,CA,USA","institution_ids":["https://openalex.org/I1283576576"]},{"raw_affiliation_string":"ASAPP Inc., Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106859201","display_name":"Kyu J. Han","orcid":null},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyu J. Han","raw_affiliation_strings":["ASAPP Inc.,Mountain View,CA,USA","ASAPP Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"ASAPP Inc.,Mountain View,CA,USA","institution_ids":["https://openalex.org/I1283576576"]},{"raw_affiliation_string":"ASAPP Inc., Mountain View, CA, USA","institution_ids":[]}]},{"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,Pittsburgh,PA,USA","Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5052377938"],"corresponding_institution_ids":["https://openalex.org/I1283576576"],"apc_list":null,"apc_paid":null,"fwci":9.7975,"has_fulltext":false,"cited_by_count":89,"citation_normalized_percentile":{"value":0.98659794,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"84","last_page":"91"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.7953698635101318},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7067111730575562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6667097806930542},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.551784336566925},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5272126197814941},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5221845507621765},{"id":"https://openalex.org/keywords/overlap\u2013add-method","display_name":"Overlap\u2013add method","score":0.4276410937309265},{"id":"https://openalex.org/keywords/circular-convolution","display_name":"Circular convolution","score":0.4179348349571228},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3909337520599365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38013583421707153},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3378923535346985},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19813022017478943}],"concepts":[{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.7953698635101318},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7067111730575562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6667097806930542},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.551784336566925},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5272126197814941},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5221845507621765},{"id":"https://openalex.org/C181002996","wikidata":"https://www.wikidata.org/wiki/Q1611641","display_name":"Overlap\u2013add method","level":5,"score":0.4276410937309265},{"id":"https://openalex.org/C194980680","wikidata":"https://www.wikidata.org/wiki/Q245450","display_name":"Circular convolution","level":5,"score":0.4179348349571228},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3909337520599365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38013583421707153},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3378923535346985},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19813022017478943},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C76563020","wikidata":"https://www.wikidata.org/wiki/Q4817582","display_name":"Fractional Fourier transform","level":4,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022656","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":89,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W1922655562","https://openalex.org/W2095705004","https://openalex.org/W2127141656","https://openalex.org/W2302255633","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2752782242","https://openalex.org/W2799800213","https://openalex.org/W2892009249","https://openalex.org/W2896457183","https://openalex.org/W2899663614","https://openalex.org/W2936774411","https://openalex.org/W2952809536","https://openalex.org/W2962780374","https://openalex.org/W2963091558","https://openalex.org/W2963414781","https://openalex.org/W2963925437","https://openalex.org/W2972818416","https://openalex.org/W2973215447","https://openalex.org/W2991213871","https://openalex.org/W2995181338","https://openalex.org/W3006683367","https://openalex.org/W3007328579","https://openalex.org/W3007528493","https://openalex.org/W3015966793","https://openalex.org/W3015974384","https://openalex.org/W3016010032","https://openalex.org/W3033529678","https://openalex.org/W3035691519","https://openalex.org/W3047171714","https://openalex.org/W3085139254","https://openalex.org/W3095173472","https://openalex.org/W3095189764","https://openalex.org/W3097777922","https://openalex.org/W3100460087","https://openalex.org/W3123221884","https://openalex.org/W3152221657","https://openalex.org/W3163793923","https://openalex.org/W3171087525","https://openalex.org/W3194203264","https://openalex.org/W3197956630","https://openalex.org/W3207805159","https://openalex.org/W4214493665","https://openalex.org/W4226033575","https://openalex.org/W4226102207","https://openalex.org/W4226103796","https://openalex.org/W4226224676","https://openalex.org/W4226334005","https://openalex.org/W4284973286","https://openalex.org/W4285045102","https://openalex.org/W4287824654","https://openalex.org/W4295253143","https://openalex.org/W4308558335","https://openalex.org/W4309793872","https://openalex.org/W4312847199","https://openalex.org/W4315705623","https://openalex.org/W4320930577","https://openalex.org/W6629717138","https://openalex.org/W6638749077","https://openalex.org/W6640090968","https://openalex.org/W6674330103","https://openalex.org/W6746023985","https://openalex.org/W6751097180","https://openalex.org/W6755207826","https://openalex.org/W6755977528","https://openalex.org/W6757585730","https://openalex.org/W6758657797","https://openalex.org/W6770280828","https://openalex.org/W6770506093","https://openalex.org/W6770812743","https://openalex.org/W6771917389","https://openalex.org/W6772991762","https://openalex.org/W6773475747","https://openalex.org/W6774054309","https://openalex.org/W6776480786","https://openalex.org/W6779163297","https://openalex.org/W6780226713","https://openalex.org/W6781275321","https://openalex.org/W6783944145","https://openalex.org/W6784531339","https://openalex.org/W6789463137","https://openalex.org/W6796931752","https://openalex.org/W6800388583","https://openalex.org/W6800664022","https://openalex.org/W6810443081","https://openalex.org/W6838697126","https://openalex.org/W6839026989"],"related_works":["https://openalex.org/W4372260258","https://openalex.org/W2133280289","https://openalex.org/W3106959200","https://openalex.org/W2267589039","https://openalex.org/W2382152453","https://openalex.org/W1796097737","https://openalex.org/W2759540840","https://openalex.org/W2385700956","https://openalex.org/W2126886659","https://openalex.org/W2143803328"],"abstract_inverted_index":{"Conformer,":[0],"combining":[1],"convolution":[2,35,61],"and":[3,10,17,36,62,64,67,88,102,107],"self-attention":[4,37,63],"sequentially":[5],"to":[6,43,54],"capture":[7],"both":[8],"local":[9,66],"global":[11,68],"information,":[12],"has":[13],"shown":[14],"remarkable":[15],"performance":[16,53],"is":[18],"currently":[19],"regarded":[20],"as":[21],"the":[22],"state-of-the-art":[23,96],"for":[24],"automatic":[25],"speech":[26],"recognition":[27],"(ASR).":[28],"Several":[29],"other":[30],"studies":[31],"have":[32,40],"explored":[33],"integrating":[34],"but":[38],"they":[39],"not":[41],"managed":[42],"match":[44],"Conformer's":[45],"performance.":[46],"The":[47],"recently":[48],"introduced":[49],"Branchformer":[50,81],"achieves":[51],"comparable":[52],"Conformer":[55],"by":[56,82],"using":[57,111],"dedicated":[58],"branches":[59],"of":[60],"merging":[65,86],"context":[69],"from":[70],"each":[71],"branch.":[72],"In":[73],"this":[74],"paper,":[75],"we":[76],"propose":[77],"E-Branchformer,":[78],"which":[79],"enhances":[80],"applying":[83],"an":[84],"effective":[85],"method":[87],"stacking":[89],"additional":[90],"point-wise":[91],"modules.":[92],"E-Branchformer":[93],"sets":[94,109],"new":[95],"word":[97],"error":[98],"rates":[99],"(WERs)":[100],"1.81%":[101],"3.65%":[103],"on":[104],"LibriSpeech":[105],"test-clean":[106],"test-other":[108],"without":[110],"any":[112],"external":[113],"training":[114],"data.":[115]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":33},{"year":2024,"cited_by_count":32},{"year":2023,"cited_by_count":19}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}