{"id":"https://openalex.org/W2012257340","doi":"https://doi.org/10.1109/icassp.2013.6638948","title":"A cluster-based multiple deep neural networks method for large vocabulary continuous speech recognition","display_name":"A cluster-based multiple deep neural networks method for large vocabulary continuous speech recognition","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2012257340","doi":"https://doi.org/10.1109/icassp.2013.6638948","mag":"2012257340"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6638948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638948","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/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":true,"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","Nat. Eng. Lab. of Speech & Language Inf. Process., Univ. of Sci. & Technol. of China, Hefei, China"],"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":"Nat. Eng. Lab. of Speech & Language Inf. Process., Univ. of Sci. & Technol. of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101409897","display_name":"Cong Liu","orcid":"https://orcid.org/0000-0002-2665-7153"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cong Liu","raw_affiliation_strings":["Anhui USTC iFlyTEK Company Limited, Hefei, China","Anhui USTC iFLYTEK Corp. Ltd., Hefei, China"],"affiliations":[{"raw_affiliation_string":"Anhui USTC iFlyTEK Company Limited, Hefei, China","institution_ids":[]},{"raw_affiliation_string":"Anhui USTC iFLYTEK Corp. Ltd., Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100349220","display_name":"Qingfeng Liu","orcid":"https://orcid.org/0000-0001-8857-6677"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingfeng Liu","raw_affiliation_strings":["Anhui USTC iFlyTEK Company Limited, Hefei, China","Anhui USTC iFLYTEK Corp. Ltd., Hefei, China"],"affiliations":[{"raw_affiliation_string":"Anhui USTC iFlyTEK Company Limited, Hefei, China","institution_ids":[]},{"raw_affiliation_string":"Anhui USTC iFLYTEK Corp. Ltd., Hefei, China","institution_ids":[]}]},{"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":"Lirong Dai","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","Nat. Eng. Lab. of Speech & Language Inf. Process., Univ. of Sci. & Technol. of China, Hefei, China"],"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":"Nat. Eng. Lab. of Speech & Language Inf. Process., Univ. of Sci. & Technol. of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","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 Computer Science and Engineering, York University, Toronto, Canada","Department of Computer Science and Engineering York University, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, York University, Toronto, Canada","institution_ids":["https://openalex.org/I192455969"]},{"raw_affiliation_string":"Department of Computer Science and Engineering York University, Toronto, ON, Canada","institution_ids":["https://openalex.org/I192455969"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100693197"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":6.2515,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.96147381,"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":"6650","last_page":"6654"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9988999962806702,"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":0.9983999729156494,"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":0.8268226981163025},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7464666962623596},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6196906566619873},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5983346700668335},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.582633912563324},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5731021761894226},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5515534281730652},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5283024311065674},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5198302865028381},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4655383825302124},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45581501722335815},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4531734585762024},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.4257866144180298},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.42560383677482605},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4164879024028778},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2153509259223938}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8268226981163025},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7464666962623596},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6196906566619873},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5983346700668335},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.582633912563324},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5731021761894226},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5515534281730652},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5283024311065674},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5198302865028381},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4655383825302124},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45581501722335815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4531734585762024},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.4257866144180298},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.42560383677482605},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4164879024028778},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2153509259223938},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6638948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638948","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W113709255","https://openalex.org/W177307080","https://openalex.org/W1218987319","https://openalex.org/W1553004968","https://openalex.org/W1559401186","https://openalex.org/W1588471869","https://openalex.org/W1993882792","https://openalex.org/W2063689849","https://openalex.org/W2093866254","https://openalex.org/W2104921946","https://openalex.org/W2110798204","https://openalex.org/W2120480077","https://openalex.org/W2124173482","https://openalex.org/W2125964738","https://openalex.org/W2136922672","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2253807446","https://openalex.org/W2296748324","https://openalex.org/W2394932179","https://openalex.org/W2395981916","https://openalex.org/W2950789693","https://openalex.org/W6604631218","https://openalex.org/W6676481782","https://openalex.org/W6678242812","https://openalex.org/W6679053740","https://openalex.org/W6711962127"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2163874654","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306"],"abstract_inverted_index":{"Recently":[0],"a":[1,50,59,69,80,163],"pre-trained":[2],"context-dependent":[3,99],"hybrid":[4],"deep":[5,51],"neural":[6,33,52],"network":[7,53],"(DNN)":[8],"and":[9,39,168],"HMM":[10,90,116,144],"method":[11,161,180],"has":[12],"achieved":[13],"significant":[14],"performance":[15,198],"gain":[16],"in":[17,37,191,202],"many":[18],"large-scale":[19],"automatic":[20],"speech":[21],"recognition":[22],"(ASR)":[23],"tasks.":[24],"However,":[25],"the":[26,85,110,137,159,178],"error":[27],"back-propagation":[28],"(BP)":[29],"algorithm":[30],"for":[31,126],"training":[32,49,111,193],"networks":[34],"is":[35,40,54],"sequential":[36],"nature":[38],"hard":[41],"to":[42,74,83],"parallelize":[43],"into":[44,104],"multiple":[45,76,133,154,183],"computing":[46],"threads.":[47],"Therefore,":[48],"extremely":[55],"time-consuming":[56],"even":[57],"with":[58,114,195],"modern":[60],"GPU":[61],"board.":[62],"In":[63,92,135],"this":[64],"paper":[65],"we":[66],"have":[67,157,175],"proposed":[68,160],"new":[70,179],"acoustic":[71],"modelling":[72],"framework":[73],"use":[75],"DNNs":[77,122,184],"instead":[78],"of":[79,88,98,130,141],"single":[81],"DNN":[82],"compute":[84],"posterior":[86,139],"probabilities":[87],"tied":[89,96,143],"states.":[91,117],"our":[93],"method,":[94],"all":[95],"states":[97],"HMMs":[100],"are":[101,123],"first":[102],"grouped":[103],"several":[105,119],"disjoined":[106,128],"clusters":[107,129],"based":[108,149],"on":[109,150,162],"data":[112,131],"associated":[113],"these":[115,127],"Then,":[118],"hierarchically":[120],"structured":[121],"trained":[124],"separately":[125],"using":[132,181,205],"GPUs.":[134],"decoding,":[136],"final":[138],"probability":[140],"each":[142],"state":[145],"can":[146,185],"be":[147],"calculated":[148],"output":[151],"posteriors":[152],"from":[153],"DNNs.":[155],"We":[156],"evaluated":[158],"64-hour":[164],"Mandarin":[165],"transcription":[166],"task":[167],"309-hour":[169],"Switchboard":[170],"Hub5":[171],"task.":[172],"Experimental":[173],"results":[174],"shown":[176],"that":[177],"clusterbased":[182],"achieve":[186],"over":[187],"5":[188],"times":[189],"reduction":[190],"total":[192],"time":[194],"only":[196],"negligible":[197],"degradation":[199],"(about":[200],"1-2%":[201],"average)":[203],"when":[204],"3":[206],"or":[207],"4":[208],"GPUs":[209],"respectively.":[210]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}