{"id":"https://openalex.org/W2071515987","doi":"https://doi.org/10.1109/taslp.2015.2392944","title":"State-Clustering Based Multiple Deep Neural Networks Modeling Approach for Speech Recognition","display_name":"State-Clustering Based Multiple Deep Neural Networks Modeling Approach for Speech Recognition","publication_year":2015,"publication_date":"2015-01-15","ids":{"openalex":"https://openalex.org/W2071515987","doi":"https://doi.org/10.1109/taslp.2015.2392944","mag":"2071515987"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2015.2392944","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2392944","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5100693197","display_name":"Pan Zhou","orcid":"https://orcid.org/0000-0002-8629-4622"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan Zhou","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101454723","display_name":"Hui Jiang","orcid":"https://orcid.org/0000-0003-4062-7206"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hui Jiang","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, York University, Toronto, Ontario, Canada","[Department of Electrical Engineering and Computer Science, Lassonde school of Engineering, York University, Toronto, ON, Canada]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, York University, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I192455969"]},{"raw_affiliation_string":"[Department of Electrical Engineering and Computer Science, Lassonde school of Engineering, York University, Toronto, ON, Canada]","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101816319","display_name":"Yu Hu","orcid":"https://orcid.org/0000-0002-6302-3539"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Hu","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100349220","display_name":"Qingfeng Liu","orcid":"https://orcid.org/0000-0001-8857-6677"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing-Feng Liu","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0557,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.92619492,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"23","issue":"4","first_page":"631","last_page":"642"},"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":0.9991999864578247,"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":0.9991999864578247,"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":0.8148423433303833},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7930254936218262},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6587511301040649},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6395443677902222},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6188573241233826},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5320618748664856},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5004067420959473},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49793386459350586},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.46554669737815857},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45842093229293823},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18517711758613586},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.10132753849029541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8148423433303833},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7930254936218262},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6587511301040649},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6395443677902222},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6188573241233826},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5320618748664856},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5004067420959473},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49793386459350586},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.46554669737815857},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45842093229293823},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18517711758613586},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.10132753849029541}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2015.2392944","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2392944","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6299999952316284,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W38527073","https://openalex.org/W217970951","https://openalex.org/W1218987319","https://openalex.org/W1498436455","https://openalex.org/W1553004968","https://openalex.org/W1559401186","https://openalex.org/W1588471869","https://openalex.org/W1972845249","https://openalex.org/W1987238397","https://openalex.org/W1993882792","https://openalex.org/W1995562189","https://openalex.org/W1998656041","https://openalex.org/W2012257340","https://openalex.org/W2012897754","https://openalex.org/W2020144989","https://openalex.org/W2033565080","https://openalex.org/W2058641082","https://openalex.org/W2063689849","https://openalex.org/W2076094076","https://openalex.org/W2081884280","https://openalex.org/W2087402357","https://openalex.org/W2093794678","https://openalex.org/W2093866254","https://openalex.org/W2112021726","https://openalex.org/W2112739286","https://openalex.org/W2112984492","https://openalex.org/W2120480077","https://openalex.org/W2124173482","https://openalex.org/W2125964738","https://openalex.org/W2136922672","https://openalex.org/W2144792281","https://openalex.org/W2147768505","https://openalex.org/W2155273149","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2165712214","https://openalex.org/W2172097686","https://openalex.org/W2184045248","https://openalex.org/W2253807446","https://openalex.org/W2294543795","https://openalex.org/W2296748324","https://openalex.org/W2394932179","https://openalex.org/W2395981916","https://openalex.org/W2403195671","https://openalex.org/W2407022425","https://openalex.org/W4285719527","https://openalex.org/W6608710415","https://openalex.org/W6678242812","https://openalex.org/W6684249834","https://openalex.org/W6696912008"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2146343568","https://openalex.org/W2013643406","https://openalex.org/W2157978810","https://openalex.org/W2597809628","https://openalex.org/W2167155152"],"abstract_inverted_index":{"The":[0,22,166],"hybrid":[1],"deep":[2],"neural":[3],"network":[4],"(DNN)":[5],"and":[6,154,183,190,212,252],"hidden":[7],"Markov":[8],"model":[9,25,225],"(HMM)":[10],"has":[11],"recently":[12],"achieved":[13],"dramatic":[14],"performance":[15,233,239],"gains":[16],"in":[17,106,188,234,249,257],"automatic":[18],"speech":[19,48],"recognition":[20,232],"(ASR).":[21],"DNN-based":[23,43],"acoustic":[24,44],"is":[26,33,169,186],"very":[27],"powerful":[28],"but":[29],"its":[30],"learning":[31],"process":[32],"extremely":[34],"time-consuming.":[35],"In":[36,78,117,134],"this":[37,135],"paper,":[38],"we":[39,137],"propose":[40],"a":[41,65,194,207,222,242,253],"novel":[42],"modeling":[45],"framework":[46],"for":[47,69,108],"recognition,":[49],"where":[50],"the":[51,70,79,119,141,145,173,202,213,219],"posterior":[52,120],"probabilities":[53,121],"of":[54,64,72,122,144,196],"HMM":[55,85,123],"states":[56,86,124],"are":[57,87,103,178,263],"computed":[58],"from":[59,131],"multiple":[60,112,132,176,181],"DNNs":[61,102,177],"(mDNN),":[62],"instead":[63],"single":[66],"large":[67],"DNN,":[68,221],"purpose":[71],"parallel":[73,107],"training":[74,142,167,197,251],"towards":[75],"faster":[76],"turnaround.":[77],"proposed":[80,203],"mDNN":[81,146,204,224],"method":[82,205],"all":[83],"tied":[84],"first":[88],"grouped":[89],"into":[90],"several":[91,99],"disjoint":[92],"clusters":[93,110],"based":[94],"on":[95,206],"data-driven":[96],"methods.":[97],"Next,":[98],"hierarchically":[100],"structured":[101],"trained":[104,191],"separately":[105],"these":[109],"using":[111],"computing":[113],"units":[114],"(e.g.":[115],"GPUs).":[116],"decoding,":[118],"can":[125,158,229],"be":[126,159],"calculated":[127],"by":[128,192],"combining":[129],"outputs":[130],"DNNs.":[133],"work,":[136],"have":[138,200],"shown":[139],"that":[140,175],"procedure":[143],"under":[147],"popular":[148],"criteria,":[149],"including":[150],"both":[151],"frame-level":[152],"cross-entropy":[153],"sequence-level":[155],"discriminative":[156],"training,":[157,259],"parallelized":[160,179],"efficiently":[161],"to":[162,172,218],"yield":[163,230],"significant":[164],"speedup.":[165],"speedup":[168],"mainly":[170],"attributed":[171],"fact":[174],"over":[180],"GPUs":[182,262],"each":[184],"DNN":[185],"smaller":[187],"size":[189,228],"only":[193],"subset":[195],"data.":[198],"We":[199],"evaluated":[201],"64-hour":[208],"Mandarin":[209],"transcription":[210],"task":[211],"320-hour":[214],"Switchboard":[215,235],"task.":[216],"Compared":[217],"conventional":[220],"4-cluster":[223],"with":[226,241],"similar":[227],"comparable":[231],"(only":[236],"about":[237],"2%":[238],"degradation)":[240],"greater":[243],"than":[244],"7":[245],"times":[246,255],"speed":[247],"improvement":[248,256],"CE":[250],"2.9":[254],"sequence":[258],"when":[260],"4":[261],"used.":[264]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}