{"id":"https://openalex.org/W4200394824","doi":"https://doi.org/10.1145/3461615.3491109","title":"Efficient Gradient-Based Neural Architecture Search For End-to-End ASR","display_name":"Efficient Gradient-Based Neural Architecture Search For End-to-End ASR","publication_year":2021,"publication_date":"2021-10-18","ids":{"openalex":"https://openalex.org/W4200394824","doi":"https://doi.org/10.1145/3461615.3491109"},"language":"en","primary_location":{"id":"doi:10.1145/3461615.3491109","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461615.3491109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Publication of the 2021 International Conference on Multimodal Interaction","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/A5057060591","display_name":"Xian Shi","orcid":"https://orcid.org/0009-0000-5236-0372"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xian Shi","raw_affiliation_strings":["School of Computer Scienc, Northwestern Polytechnical University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Scienc, Northwestern Polytechnical University, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693197","display_name":"Pan Zhou","orcid":"https://orcid.org/0000-0002-8629-4622"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan Zhou","raw_affiliation_strings":["AI Interaction Division, Sogou Inc., China"],"affiliations":[{"raw_affiliation_string":"AI Interaction Division, Sogou Inc., China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100664762","display_name":"Wei Chen","orcid":"https://orcid.org/0000-0002-3316-5368"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Chen","raw_affiliation_strings":["AI Interaction Division, Sogou Inc., China"],"affiliations":[{"raw_affiliation_string":"AI Interaction Division, Sogou Inc., China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["School of Computer Scienc, Northwestern Polytechnical University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Scienc, Northwestern Polytechnical University, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5057060591"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.5806,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.69586742,"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":"91","last_page":"96"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9937000274658203,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.817997932434082},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6143521666526794},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6015293002128601},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5298095941543579},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5241513252258301},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07710212469100952}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.817997932434082},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6143521666526794},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6015293002128601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5298095941543579},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5241513252258301},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07710212469100952},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3461615.3491109","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461615.3491109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Publication of the 2021 International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2526425061","https://openalex.org/W2615063356","https://openalex.org/W2939297570","https://openalex.org/W2962780374","https://openalex.org/W2963032572","https://openalex.org/W2963242190","https://openalex.org/W2963414781","https://openalex.org/W2964081807","https://openalex.org/W2965658867","https://openalex.org/W2972482531","https://openalex.org/W3007227084","https://openalex.org/W3096123040","https://openalex.org/W3096329809","https://openalex.org/W3150425637"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W1999612375","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Neural":[0],"architecture":[1,68,92,148],"search":[2,69,86],"(NAS)":[3],"has":[4],"been":[5],"successfully":[6],"applied":[7],"to":[8,82,154],"tasks":[9],"like":[10],"image":[11],"classification":[12],"and":[13,52,79],"language":[14],"modeling":[15],"for":[16],"finding":[17],"efficient":[18,55],"high-performance":[19],"network":[20],"architectures.":[21],"In":[22,36],"ASR":[23,56,123],"field":[24],"especially":[25],"end-to-end":[26,122],"ASR,":[27],"the":[28,45,63,112,130,137,144,147],"related":[29],"research":[30],"is":[31,96],"still":[32],"in":[33,71],"its":[34],"infancy.":[35],"this":[37],"work,":[38],"we":[39,119,142],"focus":[40],"on":[41,44,103,136,150],"applying":[42],"NAS":[43],"most":[46],"popular":[47],"manually":[48],"designed":[49],"model:":[50],"Conformer,":[51],"propose":[53],"an":[54,121],"model":[57,124],"searching":[58,101],"method":[59],"that":[60,128],"benefits":[61],"from":[62],"natural":[64],"advantage":[65],"of":[66,146],"differentiable":[67],"(Darts)":[70],"reducing":[72],"computational":[73],"overheads.":[74],"We":[75],"fuse":[76],"Darts":[77],"mutator":[78],"Conformer":[80,113,131],"blocks":[81],"form":[83],"a":[84,90,151,155],"complete":[85],"space,":[87],"within":[88],"which":[89],"modified":[91],"called":[93],"Darts-Conformer":[94],"cell":[95],"found":[97],"automatically.":[98],"The":[99],"entire":[100],"process":[102],"AISHELL-1":[104,139],"dataset":[105,153],"costs":[106],"only":[107],"0.7":[108],"GPU":[109],"days.":[110],"Replacing":[111],"encoder":[114],"by":[115,133],"stacking":[116],"searched":[117,149],"architecture,":[118],"get":[120],"(named":[125],"as":[126],"Darts-Conformner)":[127],"outperforms":[129],"baseline":[132],"4.7%":[134],"relatively":[135],"open-source":[138],"dataset.":[140,158],"Besides,":[141],"verify":[143],"transferability":[145],"small":[152],"larger":[156],"2k-hour":[157]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}