{"id":"https://openalex.org/W1971734011","doi":"https://doi.org/10.1109/iscslp.2014.6936617","title":"Deep neural network acoustic modeling for native and non-native Mandarin speech recognition","display_name":"Deep neural network acoustic modeling for native and non-native Mandarin speech recognition","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W1971734011","doi":"https://doi.org/10.1109/iscslp.2014.6936617","mag":"1971734011"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2014.6936617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language 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/A5100633270","display_name":"Xin Chen","orcid":"https://orcid.org/0000-0003-2903-5525"},"institutions":[{"id":"https://openalex.org/I1283104182","display_name":"Pearson (United States)","ror":"https://ror.org/02naadr48","country_code":"US","type":"company","lineage":["https://openalex.org/I1283104182","https://openalex.org/I4210088969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xin Chen","raw_affiliation_strings":["Knowledge Technologies, Menlo Park, California, USA","Knowledge Technologies, Pearson, 4040 Campbell Ave., Menlo Park, California 94025, USA"],"affiliations":[{"raw_affiliation_string":"Knowledge Technologies, Menlo Park, California, USA","institution_ids":[]},{"raw_affiliation_string":"Knowledge Technologies, Pearson, 4040 Campbell Ave., Menlo Park, California 94025, USA","institution_ids":["https://openalex.org/I1283104182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112149353","display_name":"Jian Cheng","orcid":"https://orcid.org/0000-0003-1289-2758"},"institutions":[{"id":"https://openalex.org/I1283104182","display_name":"Pearson (United States)","ror":"https://ror.org/02naadr48","country_code":"US","type":"company","lineage":["https://openalex.org/I1283104182","https://openalex.org/I4210088969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Cheng","raw_affiliation_strings":["Knowledge Technologies, Menlo Park, California, USA","Knowledge Technologies, Pearson, 4040 Campbell Ave., Menlo Park, California 94025, USA"],"affiliations":[{"raw_affiliation_string":"Knowledge Technologies, Menlo Park, California, USA","institution_ids":[]},{"raw_affiliation_string":"Knowledge Technologies, Pearson, 4040 Campbell Ave., Menlo Park, California 94025, USA","institution_ids":["https://openalex.org/I1283104182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100633270"],"corresponding_institution_ids":["https://openalex.org/I1283104182"],"apc_list":null,"apc_paid":null,"fwci":1.636,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.86588169,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6","last_page":"9"},"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/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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":0.9950000047683716,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8107928037643433},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7759881615638733},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7265889048576355},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6414936184883118},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5673696994781494},{"id":"https://openalex.org/keywords/sigmoid-function","display_name":"Sigmoid function","score":0.526386022567749},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5221315026283264},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4802734851837158},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.47568047046661377},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.4528244435787201},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42396777868270874},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.42059680819511414},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4191960394382477},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.41740506887435913}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8107928037643433},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7759881615638733},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7265889048576355},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6414936184883118},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5673696994781494},{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.526386022567749},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5221315026283264},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4802734851837158},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.47568047046661377},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.4528244435787201},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42396777868270874},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.42059680819511414},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4191960394382477},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.41740506887435913},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2014.6936617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W88081813","https://openalex.org/W184039015","https://openalex.org/W185613617","https://openalex.org/W943204654","https://openalex.org/W1537275613","https://openalex.org/W1968419113","https://openalex.org/W1989549063","https://openalex.org/W2004227461","https://openalex.org/W2016000176","https://openalex.org/W2052086036","https://openalex.org/W2063689849","https://openalex.org/W2087006792","https://openalex.org/W2116064496","https://openalex.org/W2117824967","https://openalex.org/W2141125852","https://openalex.org/W2147768505","https://openalex.org/W2155273149","https://openalex.org/W2155648385","https://openalex.org/W2156387975","https://openalex.org/W2160306971","https://openalex.org/W2162042984","https://openalex.org/W3029593813","https://openalex.org/W6603403951","https://openalex.org/W6603616073","https://openalex.org/W6607553906","https://openalex.org/W6607605394","https://openalex.org/W6654293680","https://openalex.org/W6682889407","https://openalex.org/W6684010798","https://openalex.org/W6777990011"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W4385957115","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2031478549","https://openalex.org/W3048205211","https://openalex.org/W2163874654"],"abstract_inverted_index":{"Recently,":[0],"Context-Dependent":[1],"Deep":[2],"Neural":[3],"Network":[4,88],"Hidden":[5],"Markov":[6],"Models":[7],"(CD-DNN-HMMs)":[8],"proved":[9],"to":[10,33,95],"be":[11],"a":[12,50,85,156,165,182],"great":[13],"success":[14],"in":[15],"improving":[16],"the":[17,42,63,97,103,115,118,139,141,170,187],"speech":[18,43,99],"recognition":[19,44,100],"accuracy":[20],"over":[21,173],"traditional":[22,174],"Gaussian":[23],"Mixture":[24],"Model":[25],"(GMM)-HMMs.":[26],"In":[27,123],"this":[28],"paper,":[29],"we":[30,126],"applied":[31,113],"CD-DNN-HMMs":[32],"an":[34],"automatic":[35],"Spoken":[36],"Chinese":[37],"Test":[38],"(SCT)":[39],"and":[40,55,61,72,120,164],"improved":[41],"performance":[45,142],"significantly.":[46],"We":[47,80],"experimented":[48],"on":[49,84,160,169,186],"large":[51],"amount":[52],"of":[53,65,117],"native":[54,171],"non-native":[56,98,162,188],"data":[57],"collected":[58],"for":[59,77],"SCT":[60],"evaluated":[62],"effect":[64],"using":[66,143],"different":[67],"network":[68,93],"activation":[69],"functions:":[70],"sigmoid":[71,147],"Rectified":[73],"Linear":[74,86,106],"Unit":[75],"(ReLU)":[76],"acoustic":[78,153],"modeling.":[79],"investigated":[81],"accent":[82,110,178],"adaptation":[83,111,179],"Input":[87],"(LIN)":[89],"-":[90],"ReLU":[91,144],"DNN":[92],"structure":[94],"enhance":[96],"accuracy.":[101],"Furthermore,":[102],"feature-space":[104],"Discriminative":[105],"Regression":[107],"fDLR":[108],"based":[109],"was":[112,121,132,149],"at":[114],"bottom":[116],"system":[119],"evaluated.":[122],"our":[124,161],"task,":[125,163],"observed":[127],"that":[128],"applying":[129],"prior":[130],"probabilities":[131],"critical;":[133],"pre-training":[134],"did":[135],"not":[136],"help":[137],"improve":[138],"performance;":[140],"DNNs":[145,148],"or":[146],"similar.":[150],"Overall,":[151],"CD-DNN-HMM":[152],"models":[154],"made":[155],"relative":[157,166,184],"20%":[158],"improvement":[159,168],"47%":[167],"task":[172],"GMM-HMM":[175],"models.":[176],"The":[177],"additionally":[180],"contributed":[181],"2.7%":[183],"gain":[185],"task.":[189]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}