{"id":"https://openalex.org/W2000200144","doi":"https://doi.org/10.1109/icassp.2013.6638963","title":"An empirical study of learning rates in deep neural networks for speech recognition","display_name":"An empirical study of learning rates in deep neural networks for speech recognition","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2000200144","doi":"https://doi.org/10.1109/icassp.2013.6638963","mag":"2000200144"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6638963","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5079708487","display_name":"Andrew Senior","orcid":"https://orcid.org/0000-0002-2401-5691"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrew Senior","raw_affiliation_strings":["Google, Inc., NY, USA","Google Inc., New York, NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Google, Inc., NY, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., New York, NY, USA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071956319","display_name":"Georg Heigold","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Georg Heigold","raw_affiliation_strings":["Google, Inc., NY, USA","Google Inc., New York, NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Google, Inc., NY, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., New York, NY, USA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111465122","display_name":"Marc\u2019Aurelio Ranzato","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marc'Aurelio Ranzato","raw_affiliation_strings":["Google, Inc., NY, USA","Google Inc., New York, NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Google, Inc., NY, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., New York, NY, USA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031932067","display_name":"Ke Yang","orcid":"https://orcid.org/0000-0002-6441-2309"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Yang","raw_affiliation_strings":["Google, Inc., NY, USA","Google Inc., New York, NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Google, Inc., NY, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., New York, NY, USA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5079708487"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":26.6969,"has_fulltext":false,"cited_by_count":172,"citation_normalized_percentile":{"value":0.99598067,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6724","last_page":"6728"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9979000091552734,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9975000023841858,"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":0.8267923593521118},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.6021934151649475},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5814653038978577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5690310001373291},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5567250847816467},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5457798838615417},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5427622199058533},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49924278259277344},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4390416741371155},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42447978258132935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8267923593521118},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.6021934151649475},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5814653038978577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5690310001373291},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5567250847816467},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5457798838615417},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5427622199058533},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49924278259277344},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4390416741371155},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42447978258132935},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6638963","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.686.3706","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.686.3706","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://static.googleusercontent.com/media/research.google.com/en/us/pubs/archive/40808.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.800000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W137106866","https://openalex.org/W197326900","https://openalex.org/W587794757","https://openalex.org/W1629097610","https://openalex.org/W1994616650","https://openalex.org/W2076794394","https://openalex.org/W2086161653","https://openalex.org/W2106051978","https://openalex.org/W2125964738","https://openalex.org/W2130179707","https://openalex.org/W2140766383","https://openalex.org/W2143908786","https://openalex.org/W2144792281","https://openalex.org/W2146502635","https://openalex.org/W2160815625","https://openalex.org/W2168231600","https://openalex.org/W2170541567","https://openalex.org/W2184045248","https://openalex.org/W2296748324","https://openalex.org/W2394932179","https://openalex.org/W2403195671","https://openalex.org/W2914484425","https://openalex.org/W2950351588","https://openalex.org/W2951282416","https://openalex.org/W4238404964","https://openalex.org/W6617368339","https://openalex.org/W6674634876","https://openalex.org/W6679053740","https://openalex.org/W6680789778","https://openalex.org/W6681435938","https://openalex.org/W6684859321"],"related_works":["https://openalex.org/W2895097035","https://openalex.org/W4206903459","https://openalex.org/W2754816816","https://openalex.org/W4366280654","https://openalex.org/W3160167280","https://openalex.org/W3020853991","https://openalex.org/W4362706668","https://openalex.org/W4231621013","https://openalex.org/W3171021120","https://openalex.org/W3008318776"],"abstract_inverted_index":{"Recent":[0],"deep":[1],"neural":[2],"network":[3],"systems":[4],"for":[5],"large":[6],"vocabulary":[7],"speech":[8],"recognition":[9],"are":[10],"trained":[11],"with":[12],"minibatch":[13],"stochastic":[14],"gradient":[15],"descent":[16],"but":[17],"use":[18],"a":[19,43],"variety":[20],"of":[21,29,38,72],"learning":[22,54,73],"rate":[23,55,74],"scheduling":[24,51],"schemes.":[25],"We":[26],"investigate":[27],"several":[28],"these":[30],"schemes,":[31],"particularly":[32],"AdaGrad.":[33],"Based":[34],"on":[35],"our":[36],"analysis":[37],"its":[39],"limitations,":[40],"we":[41],"propose":[42],"new":[44],"variant":[45],"`AdaDec'":[46],"that":[47],"decouples":[48],"long-term":[49],"learning-rate":[50],"from":[52],"per-parameter":[53],"variation.":[56],"AdaDec":[57],"was":[58],"found":[59],"to":[60,77],"result":[61],"in":[62],"higher":[63],"frame":[64],"accuracies":[65],"than":[66],"other":[67],"methods.":[68],"Overall,":[69],"careful":[70],"choice":[71],"schemes":[75],"leads":[76],"faster":[78],"convergence":[79],"and":[80],"lower":[81],"word":[82],"error":[83],"rates.":[84]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":18},{"year":2015,"cited_by_count":17},{"year":2014,"cited_by_count":15},{"year":2013,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}