{"id":"https://openalex.org/W3207805159","doi":"https://doi.org/10.1109/icassp43922.2022.9746187","title":"SRU++: Pioneering Fast Recurrence with Attention for Speech Recognition","display_name":"SRU++: Pioneering Fast Recurrence with Attention for Speech Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3207805159","doi":"https://doi.org/10.1109/icassp43922.2022.9746187","mag":"3207805159"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746187","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/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":true,"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/A5030752617","display_name":"Tao Le\u00ed","orcid":"https://orcid.org/0000-0002-0900-1582"},"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":"Tao Lei","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/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":false,"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/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":5,"corresponding_author_ids":["https://openalex.org/A5101875418"],"corresponding_institution_ids":["https://openalex.org/I1283576576"],"apc_list":null,"apc_paid":null,"fwci":0.6236,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.65508511,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7872","last_page":"7876"},"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":0.9998000264167786,"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":0.9990000128746033,"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":0.7726532816886902},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6867357492446899},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.66090327501297},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.659278154373169},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5880401134490967},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5637185573577881},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5320186614990234},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5191218256950378},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.46631085872650146},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.45771849155426025},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4418301284313202},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38460874557495117},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1947210729122162},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1395077407360077},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.099781334400177}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7726532816886902},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6867357492446899},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.66090327501297},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.659278154373169},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5880401134490967},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5637185573577881},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5320186614990234},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5191218256950378},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.46631085872650146},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.45771849155426025},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4418301284313202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38460874557495117},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1947210729122162},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1395077407360077},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.099781334400177},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746187","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2143612262","https://openalex.org/W2795935804","https://openalex.org/W2799473636","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2962824709","https://openalex.org/W2963174729","https://openalex.org/W2963242190","https://openalex.org/W2963403868","https://openalex.org/W2981857663","https://openalex.org/W2991324852","https://openalex.org/W3015974384","https://openalex.org/W3021469861","https://openalex.org/W3025165719","https://openalex.org/W3095173472","https://openalex.org/W3097777922","https://openalex.org/W3101648800","https://openalex.org/W3130868440","https://openalex.org/W3163211337","https://openalex.org/W3163793923","https://openalex.org/W3213903651","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6770514768"],"related_works":["https://openalex.org/W3176018525","https://openalex.org/W2903533908","https://openalex.org/W3026554633","https://openalex.org/W2903810591","https://openalex.org/W4289548192","https://openalex.org/W2888520903","https://openalex.org/W2963499882","https://openalex.org/W2903399267","https://openalex.org/W2949454572","https://openalex.org/W3098873988"],"abstract_inverted_index":{"The":[0],"Transformer":[1],"architecture":[2,10],"has":[3],"been":[4],"well":[5],"adopted":[6],"as":[7],"a":[8,43,155],"dominant":[9],"in":[11,26,63,70,92],"most":[12],"sequence":[13,64],"transduction":[14],"tasks":[15,77,94],"including":[16],"automatic":[17],"speech":[18,113,152],"recognition":[19],"(ASR),":[20],"since":[21],"its":[22],"attention":[23,35,57],"mechanism":[24],"excels":[25],"capturing":[27],"long-range":[28],"dependencies.":[29],"While":[30],"models":[31],"built":[32],"solely":[33],"upon":[34],"can":[36,108,147],"be":[37,109],"better":[38],"parallelized":[39],"than":[40],"regular":[41],"RNN,":[42],"novel":[44],"network":[45],"architecture,":[46],"SRU++,":[47],"was":[48],"recently":[49],"proposed.":[50],"By":[51],"combining":[52],"the":[53,87,106,116,137,142],"fast":[54],"recurrence":[55],"and":[56,66,74,103],"mechanism,":[58],"SRU++":[59,91,121,146],"exhibits":[60],"strong":[61],"capability":[62],"modeling":[65,73],"achieves":[67,123],"near-state-of-the-art":[68],"results":[69],"various":[71],"language":[72],"machine":[75],"translation":[76],"with":[78,97,136,154],"improved":[79],"compute":[80],"efficiency.":[81],"In":[82],"this":[83],"work,":[84],"we":[85],"present":[86],"advantages":[88],"of":[89],"applying":[90],"ASR":[93,101],"by":[95],"comparing":[96],"Conformer":[98,139,149],"across":[99],"multiple":[100],"benchmarks":[102],"study":[104],"how":[105],"benefits":[107],"generalized":[110],"to":[111],"long-form":[112,151],"inputs.":[114],"On":[115],"popular":[117],"LibriSpeech":[118],"benchmark,":[119],"our":[120,160],"model":[122],"2.0%":[124],"/":[125,130],"4.7%":[126],"WER":[127],"on":[128,150,159],"test-clean":[129],"test-other,":[131],"showing":[132],"competitive":[133],"performances":[134],"compared":[135],"state-of-the-art":[138],"encoder":[140],"under":[141],"same":[143],"set-up.":[144],"Specifically,":[145],"surpass":[148],"input":[153],"large":[156],"margin,":[157],"based":[158],"analysis.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}