{"id":"https://openalex.org/W3015584167","doi":"https://doi.org/10.1109/icassp40776.2020.9053993","title":"Fast Training of Deep Neural Networks for Speech Recognition","display_name":"Fast Training of Deep Neural Networks for Speech Recognition","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015584167","doi":"https://doi.org/10.1109/icassp40776.2020.9053993","mag":"3015584167"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053993","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053993","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/A5089801879","display_name":"Guojing Cong","orcid":"https://orcid.org/0000-0003-0850-7714"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Guojing Cong","raw_affiliation_strings":["IBM T.J. Waston Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Waston Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM T.J. Waston Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Waston Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101738461","display_name":"Chih-Chieh Yang","orcid":"https://orcid.org/0000-0003-2816-4464"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chih-Chieh Yang","raw_affiliation_strings":["IBM T.J. Waston Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Waston Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100430606","display_name":"Tianyi Liu","orcid":"https://orcid.org/0000-0002-5573-5093"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianyi Liu","raw_affiliation_strings":["School of Industrial and Systems Engineering, Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"School of Industrial and Systems Engineering, Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5089801879"],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":0.6628,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75047877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6884","last_page":"6888"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.8425784111022949},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.7245429754257202},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6996561884880066},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6133537292480469},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6011930108070374},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5979747772216797},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5655689239501953},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5603630542755127},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5277398824691772},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5112009644508362},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5082816481590271},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4540347754955292},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41466134786605835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3803653120994568},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2347564995288849},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16319549083709717}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8425784111022949},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.7245429754257202},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6996561884880066},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6133537292480469},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6011930108070374},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5979747772216797},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5655689239501953},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5603630542755127},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5277398824691772},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5112009644508362},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5082816481590271},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4540347754955292},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41466134786605835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3803653120994568},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2347564995288849},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16319549083709717},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053993","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053993","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W778657980","https://openalex.org/W2058641082","https://openalex.org/W2064675550","https://openalex.org/W2094233035","https://openalex.org/W2130062883","https://openalex.org/W2166637769","https://openalex.org/W2166706236","https://openalex.org/W2168231600","https://openalex.org/W2288502450","https://openalex.org/W2405883473","https://openalex.org/W2606833507","https://openalex.org/W2744599870","https://openalex.org/W2765865054","https://openalex.org/W2899771611","https://openalex.org/W2900182564","https://openalex.org/W2936012302","https://openalex.org/W2962863496","https://openalex.org/W2963804082","https://openalex.org/W2963903325","https://openalex.org/W2973188344","https://openalex.org/W3102816259","https://openalex.org/W6622473587","https://openalex.org/W6638803421","https://openalex.org/W6679314259","https://openalex.org/W6684249991","https://openalex.org/W6684859321","https://openalex.org/W6756561314"],"related_works":["https://openalex.org/W1999699871","https://openalex.org/W2145230572","https://openalex.org/W4225124612","https://openalex.org/W2043806667","https://openalex.org/W2146197305","https://openalex.org/W2021633306","https://openalex.org/W2006801911","https://openalex.org/W2166312020","https://openalex.org/W2033669961","https://openalex.org/W2971899271"],"abstract_inverted_index":{"Training":[0],"large,":[1],"deep":[2],"neural":[3],"network":[4],"acoustic":[5,36],"models":[6],"for":[7,31],"speech":[8],"recognition":[9],"on":[10,17,23,38,53,61],"large":[11],"datasets":[12],"takes":[13,117,124],"a":[14,18,33,106],"long":[15],"time":[16],"single":[19],"GPU,":[20],"motivating":[21],"research":[22],"parallel":[24],"training":[25,32,116,123],"algorithms.":[26],"We":[27],"present":[28],"an":[29,69],"approach":[30],"bidirectional":[34],"LSTM":[35],"model":[37,44],"the":[39,54,62],"2000-hour":[40],"Switchboard":[41,56],"corpus.":[42],"The":[43],"we":[45],"train":[46],"achieves":[47],"state-of-the-art":[48,103],"word":[49],"error":[50],"rate,":[51],"7.5%":[52],"Hub5-2000":[55],"test":[57,64],"set":[58],"and":[59,66],"13.1%":[60],"Callhome":[63],"set,":[65],"scales":[67],"to":[68,101],"unprecedented":[70],"96":[71,121],"learners":[72],"while":[73],"employing":[74],"only":[75],"12":[76],"global":[77],"reductions":[78,89],"per":[79],"epoch":[80],"of":[81,109],"training.":[82],"As":[83],"our":[84],"implementation":[85],"incurs":[86],"far":[87],"fewer":[88],"than":[90],"prior":[91],"work,":[92],"it":[93],"does":[94],"not":[95],"require":[96],"aggressively":[97],"optimized":[98],"communication":[99],"primitives":[100],"reach":[102],"performance":[104],"in":[105],"short":[107],"amount":[108],"time.":[110],"With":[111],"48":[112],"NVIDIA":[113],"V100":[114],"GPUs":[115],"5":[118],"hours;":[119],"with":[120],"GPUs,":[122],"around":[125],"3":[126],"hours.":[127]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}