{"id":"https://openalex.org/W3015966793","doi":"https://doi.org/10.1109/icassp40776.2020.9053887","title":"Attention-Based ASR with Lightweight and Dynamic Convolutions","display_name":"Attention-Based ASR with Lightweight and Dynamic Convolutions","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015966793","doi":"https://doi.org/10.1109/icassp40776.2020.9053887","mag":"3015966793"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053887","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053887","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5040732498","display_name":"Yuya Fujita","orcid":"https://orcid.org/0000-0001-8155-6040"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yuya Fujita","raw_affiliation_strings":["Yahoo Japan Corporation, Tokyo, JAPAN"],"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation, Tokyo, JAPAN","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048730867","display_name":"Aswin Shanmugam Subramanian","orcid":"https://orcid.org/0000-0003-4446-001X"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aswin Shanmugam Subramanian","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088171135","display_name":"Motoi Omachi","orcid":"https://orcid.org/0000-0002-9159-4371"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Motoi Omachi","raw_affiliation_strings":["Yahoo Japan Corporation, Tokyo, JAPAN"],"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation, Tokyo, JAPAN","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/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040732498"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0579,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.89369183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7034","last_page":"7038"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9997000098228455,"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":0.9977999925613403,"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/computer-science","display_name":"Computer science","score":0.8287741541862488},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6889768838882446},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6113579273223877},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6057618856430054},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5564774870872498},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5513944625854492},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.49653345346450806},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.46468260884284973},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4411521553993225},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.41395923495292664},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.32683563232421875},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2507622539997101},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08319485187530518}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8287741541862488},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6889768838882446},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6113579273223877},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6057618856430054},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5564774870872498},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5513944625854492},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.49653345346450806},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.46468260884284973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4411521553993225},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.41395923495292664},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32683563232421875},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2507622539997101},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08319485187530518},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053887","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053887","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2148613904","https://openalex.org/W2164502538","https://openalex.org/W2166637769","https://openalex.org/W2193413348","https://openalex.org/W2242685705","https://openalex.org/W2291522532","https://openalex.org/W2327501763","https://openalex.org/W2475988411","https://openalex.org/W2530876040","https://openalex.org/W2559260703","https://openalex.org/W2567070169","https://openalex.org/W2613904329","https://openalex.org/W2750499125","https://openalex.org/W2766219058","https://openalex.org/W2799800213","https://openalex.org/W2892009249","https://openalex.org/W2904818793","https://openalex.org/W2908336025","https://openalex.org/W2936774411","https://openalex.org/W2944255943","https://openalex.org/W2952809536","https://openalex.org/W2962778134","https://openalex.org/W2962780374","https://openalex.org/W2962824709","https://openalex.org/W2963403664","https://openalex.org/W2963403868","https://openalex.org/W2963970792","https://openalex.org/W2964265128","https://openalex.org/W2972389417","https://openalex.org/W2972630480","https://openalex.org/W2972818416","https://openalex.org/W2973215447","https://openalex.org/W3007328579","https://openalex.org/W3103005696","https://openalex.org/W4385245566","https://openalex.org/W6601563604","https://openalex.org/W6623517193","https://openalex.org/W6629717138","https://openalex.org/W6683968285","https://openalex.org/W6687566353","https://openalex.org/W6696972928","https://openalex.org/W6731370813","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6754299077","https://openalex.org/W6757424787","https://openalex.org/W6757585730"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1732468982","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W2021128377","https://openalex.org/W2604685715","https://openalex.org/W350032239","https://openalex.org/W2412160900","https://openalex.org/W2136453575"],"abstract_inverted_index":{"End-to-end":[0],"(E2E)":[1],"automatic":[2],"speech":[3],"recognition":[4],"(ASR)":[5],"with":[6,19,105,116],"sequence-to-sequence":[7],"models":[8],"has":[9],"gained":[10],"attention":[11],"because":[12],"of":[13,48],"its":[14,70],"simple":[15],"model":[16,23,130],"training":[17,47,104],"compared":[18],"conventional":[20],"hidden":[21],"Markov":[22],"based":[24,44],"ASR.":[25],"Recently,":[26],"several":[27],"studies":[28],"report":[29],"the":[30,92,96,111,121],"state-of-the-art":[31,135],"E2E":[32,45,85,129],"ASR":[33,86,139],"results":[34],"obtained":[35],"by":[36],"Transformer.":[37],"Compared":[38],"to":[39,78,84,91,94,134],"recurrent":[40],"neural":[41],"network":[42],"(RNN)":[43],"models,":[46],"Transformer":[49,65,136],"is":[50],"more":[51],"efficient":[52],"and":[53,81,114,131],"also":[54,101],"achieves":[55],"better":[56,125],"performance":[57,126,132],"on":[58,110,137],"various":[59,138],"tasks.":[60,143],"However,":[61],"self-attention":[62,93],"used":[63],"in":[64,69],"requires":[66],"computation":[67],"quadratic":[68],"input":[71],"length.":[72],"In":[73],"this":[74],"paper,":[75],"we":[76],"propose":[77,102],"apply":[79],"lightweight":[80],"dynamic":[82],"convolution":[83,109],"as":[87],"an":[88],"alternative":[89],"architecture":[90],"make":[95],"computational":[97],"order":[98],"linear.":[99],"We":[100],"joint":[103],"connectionist":[106],"temporal":[107],"classification,":[108],"frequency":[112],"axis,":[113],"combination":[115],"self-attention.":[117],"With":[118],"these":[119],"techniques,":[120],"proposed":[122],"architectures":[123],"achieve":[124],"than":[127],"RNN-based":[128],"competitive":[133],"benchmarks":[140],"including":[141],"noisy/reverberant":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}