{"id":"https://openalex.org/W2066824132","doi":"https://doi.org/10.1109/apsipa.2013.6694268","title":"Context-dependent deep neural networks for commercial Mandarin speech recognition applications","display_name":"Context-dependent deep neural networks for commercial Mandarin speech recognition applications","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W2066824132","doi":"https://doi.org/10.1109/apsipa.2013.6694268","mag":"2066824132"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2013.6694268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2013.6694268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference","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/A5109187643","display_name":"Jianwei Niu","orcid":"https://orcid.org/0009-0004-0914-338X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwei Niu","raw_affiliation_strings":["Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066245750","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-9051-2111"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022255906","display_name":"Lei Jia","orcid":"https://orcid.org/0000-0002-4405-7274"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Jia","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100685461","display_name":"Na Hu","orcid":"https://orcid.org/0000-0001-6362-0969"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na Hu","raw_affiliation_strings":["Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9883,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.82808912,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9983000159263611,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.996399998664856,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8712061643600464},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8072032928466797},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7731859087944031},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6503395438194275},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6408114433288574},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5498951077461243},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5278795957565308},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5121252536773682},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5095282196998596},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.47910216450691223},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4628191888332367},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.44082069396972656},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4067004323005676},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10022610425949097}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8712061643600464},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8072032928466797},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7731859087944031},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6503395438194275},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6408114433288574},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5498951077461243},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5278795957565308},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5121252536773682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5095282196998596},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.47910216450691223},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4628191888332367},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.44082069396972656},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4067004323005676},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10022610425949097},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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":2,"locations":[{"id":"doi:10.1109/apsipa.2013.6694268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2013.6694268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.652.2574","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.652.2574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.nwpu-aslp.org/lxie/papers/APSIPA2013-NJW.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6600000262260437}],"awards":[],"funders":[{"id":"https://openalex.org/F4320318547","display_name":"Baidu","ror":"https://ror.org/03vs3wt56"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326297","display_name":"Fok Ying Tung Education Foundation","ror":null},{"id":"https://openalex.org/F4320336567","display_name":"Natural Science Basic Research Program of Shaanxi Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W217970951","https://openalex.org/W2093794678","https://openalex.org/W2112477549","https://openalex.org/W2115439799","https://openalex.org/W2144792281","https://openalex.org/W2147627917","https://openalex.org/W2147768505","https://openalex.org/W2158289097","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2165712214","https://openalex.org/W2394932179","https://openalex.org/W2465562739"],"related_works":["https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2160650576","https://openalex.org/W2150890698","https://openalex.org/W2163874654","https://openalex.org/W2401394187","https://openalex.org/W4245698648","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290"],"abstract_inverted_index":{"Recently,":[0],"context-dependent":[1,31],"deep":[2],"neural":[3],"network":[4],"hidden":[5],"Markov":[6],"models":[7],"(CD-DNN-HMMs)":[8],"have":[9],"been":[10,23],"successfully":[11],"used":[12],"in":[13,53,72],"some":[14],"commercial":[15,48,109],"large-vocabulary":[16],"English":[17],"speech":[18,50,111],"recognition":[19,51,112],"systems.":[20],"It":[21],"has":[22],"proved":[24],"that":[25,57],"CD-DNN-HMMs":[26,46,58,105],"significantly":[27],"outperform":[28],"the":[29,92,99,102],"conventional":[30],"Gaussian":[32],"mixture":[33],"model":[34],"(GMM)-HMMs":[35],"(CD-GMM-HMMs).":[36],"In":[37],"this":[38,97],"paper,":[39],"we":[40],"report":[41],"our":[42,95],"latest":[43],"progress":[44],"on":[45],"for":[47,108,132],"Mandarin":[49,110],"applications":[52],"Baidu.":[54],"Experiments":[55],"demonstrate":[56],"can":[59,124],"get":[60],"relative":[61,67],"26%":[62],"word":[63],"error":[64,70],"reduction":[65,71],"and":[66,79],"16%":[68],"sentence":[69],"Baidu's":[73],"short":[74],"message":[75],"(SMS)":[76],"voice":[77,80],"input":[78],"search":[81],"applications,":[82],"respectively,":[83],"compared":[84],"with":[85],"state-of-the-art":[86],"CD-GMM-HMMs":[87],"trained":[88],"using":[89],"fMPE.":[90],"To":[91],"best":[93],"of":[94,104,129],"knowledge,":[96],"is":[98],"first":[100],"time":[101],"performances":[103],"are":[106],"reported":[107],"applications.":[113],"We":[114],"also":[115],"propose":[116],"a":[117,126],"GPU":[118],"on-chip":[119],"speed-up":[120,127],"training":[121],"approach":[122],"which":[123],"achieve":[125],"ratio":[128],"nearly":[130],"two":[131],"DNN":[133],"training.":[134]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}