{"id":"https://openalex.org/W2786767133","doi":"https://doi.org/10.1109/asru.2017.8268939","title":"Incremental training and constructing the very deep convolutional residual network acoustic models","display_name":"Incremental training and constructing the very deep convolutional residual network acoustic models","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2786767133","doi":"https://doi.org/10.1109/asru.2017.8268939","mag":"2786767133"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8268939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268939","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5053726259","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-7636-3797"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034792613","display_name":"Xugang Lu","orcid":"https://orcid.org/0000-0001-7075-448X"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xugang Lu","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060329279","display_name":"Peng Sken","orcid":null},"institutions":[{"id":"https://openalex.org/I15922215","display_name":"National Center for University Entrance Examinations","ror":"https://ror.org/0182n4f20","country_code":"JP","type":"education","lineage":["https://openalex.org/I1319490839","https://openalex.org/I15922215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Peng Sken","raw_affiliation_strings":["Dokuritsu Gyosei Hojin Joho Tsushin Kenkyu Kiko, Koganei, Tokyo, JP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dokuritsu Gyosei Hojin Joho Tsushin Kenkyu Kiko, Koganei, Tokyo, JP","institution_ids":["https://openalex.org/I15922215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057295313","display_name":"Ryoichi Takashima","orcid":"https://orcid.org/0000-0002-9808-0250"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryoichi Takashima","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114514387","display_name":"Hisashi Kawai","orcid":"https://orcid.org/0000-0002-0914-5092"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hisashi Kawai","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"222","last_page":"227"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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":0.998199999332428,"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/residual","display_name":"Residual","score":0.8142887353897095},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.806685209274292},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.7366933822631836},{"id":"https://openalex.org/keywords/residual-neural-network","display_name":"Residual neural network","score":0.6476991772651672},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5802635550498962},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5794554948806763},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5686113834381104},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5622924566268921},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5443917512893677},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5383791327476501},{"id":"https://openalex.org/keywords/skeleton","display_name":"Skeleton (computer programming)","score":0.49930620193481445},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.467684805393219},{"id":"https://openalex.org/keywords/network-model","display_name":"Network model","score":0.46161943674087524},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.45483818650245667},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2589567303657532}],"concepts":[{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.8142887353897095},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.806685209274292},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7366933822631836},{"id":"https://openalex.org/C2944601119","wikidata":"https://www.wikidata.org/wiki/Q43744058","display_name":"Residual neural network","level":3,"score":0.6476991772651672},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5802635550498962},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5794554948806763},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5686113834381104},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5622924566268921},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5443917512893677},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5383791327476501},{"id":"https://openalex.org/C18969341","wikidata":"https://www.wikidata.org/wiki/Q1169129","display_name":"Skeleton (computer programming)","level":2,"score":0.49930620193481445},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.467684805393219},{"id":"https://openalex.org/C104122410","wikidata":"https://www.wikidata.org/wiki/Q1416406","display_name":"Network model","level":2,"score":0.46161943674087524},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.45483818650245667},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2589567303657532},{"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/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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru.2017.8268939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268939","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50728233","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100930696","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6100000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W87954838","https://openalex.org/W1524333225","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W2110798204","https://openalex.org/W2117539524","https://openalex.org/W2160306971","https://openalex.org/W2163605009","https://openalex.org/W2168231600","https://openalex.org/W2181607856","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2331143823","https://openalex.org/W2397947827","https://openalex.org/W2401231614","https://openalex.org/W2405883473","https://openalex.org/W2515753980","https://openalex.org/W2515801922","https://openalex.org/W2530876040","https://openalex.org/W2531409750","https://openalex.org/W2541674938","https://openalex.org/W2578475560","https://openalex.org/W2593910181","https://openalex.org/W2627092829","https://openalex.org/W2682975603","https://openalex.org/W2745422919","https://openalex.org/W2962835968","https://openalex.org/W2963000224","https://openalex.org/W2963211739","https://openalex.org/W2963410064","https://openalex.org/W2964137095","https://openalex.org/W2969945254","https://openalex.org/W3034729383","https://openalex.org/W3118608800","https://openalex.org/W6603550504","https://openalex.org/W6631362777","https://openalex.org/W6637373629","https://openalex.org/W6676481782","https://openalex.org/W6684859321","https://openalex.org/W6698183232","https://openalex.org/W6701947533","https://openalex.org/W6712816420","https://openalex.org/W6725543821","https://openalex.org/W6729059855","https://openalex.org/W6739366949","https://openalex.org/W6779469704","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W3196952692","https://openalex.org/W2984708981","https://openalex.org/W2755231872","https://openalex.org/W4300939921","https://openalex.org/W4383097772","https://openalex.org/W2964350391","https://openalex.org/W2274287116","https://openalex.org/W2897517148","https://openalex.org/W2983358626","https://openalex.org/W2967403871"],"abstract_inverted_index":{"Inspired":[0],"by":[1],"the":[2,8,26,33,53,57,67,76,104,112,121,128,139,146,155,168,177],"successful":[3],"applications":[4],"in":[5,20,75],"image":[6],"recognition,":[7],"very":[9,113],"deep":[10,114],"convolutional":[11],"residual":[12],"network":[13],"(ResNet)":[14],"based":[15,65],"model":[16,48,61,106,123,141,148,169],"has":[17],"been":[18],"applied":[19],"automatic":[21],"speech":[22],"recognition":[23],"(ASR).":[24],"However,":[25],"computational":[27],"load":[28],"is":[29,64,107,124],"heavy":[30],"for":[31],"training":[32,49,54,62,130,158,164,170],"ResNet":[34],"with":[35,80,127,167],"a":[36,88,172],"large":[37],"quantity":[38],"of":[39,56,70,103,176,180],"data.":[40],"In":[41,117],"this":[42],"paper,":[43],"we":[44],"propose":[45],"an":[46,97],"incremental":[47,60,119,157],"framework":[50,63],"to":[51,111,138,145],"accelerate":[52],"process":[55],"ResNet.":[58,77],"The":[59,78,100],"on":[66],"unequal":[68],"importance":[69,179],"each":[71,181],"layer":[72],"and":[73,83,135,149,162],"connection":[74],"modules":[79],"important":[81],"layers":[82,134],"connections":[84,136],"are":[85,94,142],"regarded":[86,95],"as":[87,96,171],"skeleton":[89,105,122,147],"model,":[90],"while":[91],"those":[92],"left":[93],"auxiliary":[98,140],"model.":[99],"total":[101],"depth":[102],"quite":[108],"shallow":[109],"compared":[110,166],"full":[115,129],"network.":[116],"our":[118],"training,":[120],"first":[125],"trained":[126],"data":[131],"set.":[132],"Other":[133],"belonging":[137],"gradually":[143],"attached":[144],"tuned.":[150],"Our":[151],"experiments":[152],"showed":[153],"that":[154],"proposed":[156],"obtained":[159],"comparable":[160],"performances":[161],"faster":[163],"speed":[165],"whole":[173],"without":[174],"consideration":[175],"different":[178],"layer.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}