{"id":"https://openalex.org/W3095175338","doi":"https://doi.org/10.21437/interspeech.2020-1315","title":"DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptation","display_name":"DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptation","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095175338","doi":"https://doi.org/10.21437/interspeech.2020-1315","mag":"3095175338"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1315","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1315","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5100450914","display_name":"Yi\u2010Chen Chen","orcid":"https://orcid.org/0000-0002-4616-2115"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi-Chen Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079943535","display_name":"Jui-Yang Hsu","orcid":"https://orcid.org/0000-0003-1855-5779"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jui-Yang Hsu","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022170150","display_name":"Cheng\u2010Kuang Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cheng-Kuang Lee","raw_affiliation_strings":["NVIDIA AI Technology Center, NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA AI Technology Center, NVIDIA","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Hung-yi Lee","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040508737"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":3.7117,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.9438107,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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":0.9983999729156494,"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/T11309","display_name":"Music and Audio Processing","score":0.9954000115394592,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9937999844551086,"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":0.7944433689117432},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7128467559814453},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6557978987693787},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6154632568359375},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4227173328399658},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.4110988676548004},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4097389876842499},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0844041109085083},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05232629179954529},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.04666697978973389}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7944433689117432},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7128467559814453},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6557978987693787},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6154632568359375},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4227173328399658},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.4110988676548004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4097389876842499},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0844041109085083},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05232629179954529},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.04666697978973389},{"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1315","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1315","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W2101926813","https://openalex.org/W2106440210","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2292087804","https://openalex.org/W2553303224","https://openalex.org/W2633221078","https://openalex.org/W2769437540","https://openalex.org/W2884975363","https://openalex.org/W2885706078","https://openalex.org/W2896457183","https://openalex.org/W2951104886","https://openalex.org/W2962780374","https://openalex.org/W2962847160","https://openalex.org/W2963032572","https://openalex.org/W2963292011","https://openalex.org/W2963431393","https://openalex.org/W2963446712","https://openalex.org/W2963840672","https://openalex.org/W2964081807","https://openalex.org/W2965658867","https://openalex.org/W2967733054","https://openalex.org/W2972482531","https://openalex.org/W2981748264","https://openalex.org/W3015585292","https://openalex.org/W4377862891"],"related_works":["https://openalex.org/W1571518467","https://openalex.org/W87991986","https://openalex.org/W2020291234","https://openalex.org/W2789919619","https://openalex.org/W2293457016","https://openalex.org/W3169305685","https://openalex.org/W2094520212","https://openalex.org/W2001850503","https://openalex.org/W2351428524","https://openalex.org/W2368779261"],"abstract_inverted_index":{"In":[0],"previous":[1,80],"works,":[2,81],"only":[3,65],"parameter":[4],"weights":[5],"of":[6,16,58],"ASR":[7,45,78,116],"models":[8],"are":[9],"optimized":[10],"under":[11,112],"fixed-topology":[12,100],"architecture.However,":[13],"the":[14,56,98,124],"design":[15],"successful":[17],"model":[18,32],"architecture":[19,33,50,101],"has":[20],"always":[21],"relied":[22],"on":[23,66,75,85,108,123],"human":[24],"experience":[25],"and":[26,104,114],"intuition.Besides,":[27],"many":[28,67],"hyperparameters":[29],"related":[30],"to":[31,35,54,69],"need":[34],"be":[36],"manually":[37],"tuned.Therefore":[38],"in":[39],"this":[40],"paper,":[41],"we":[42,60,82,119],"propose":[43],"an":[44],"approach":[46,63,96],"with":[47],"efficient":[48],"gradient-based":[49],"search,":[51],"DARTS-ASR.In":[52],"order":[53],"examine":[55],"generalizability":[57],"DARTS-ASR,":[59],"apply":[61],"our":[62,95],"not":[64],"languages":[68],"perform":[70,120],"monolingual":[71,113],"ASR,":[72],"but":[73],"also":[74],"a":[76,86],"multilingual":[77,87,115],"setting.Following":[79],"conducted":[83],"experiments":[84],"dataset,":[88],"IARPA":[89],"BABEL.The":[90],"experiment":[91],"results":[92],"show":[93],"that":[94],"outperformed":[97],"baseline":[99],"by":[102,127],"10.2%":[103],"10.0%":[105],"relative":[106],"reduction":[107],"character":[109],"error":[110],"rates":[111],"settings":[117],"respectively.Furthermore,":[118],"some":[121],"analysis":[122],"searched":[125],"architectures":[126],"DARTS-ASR.":[128]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
