{"id":"https://openalex.org/W2063689849","doi":"https://doi.org/10.1109/iscslp.2012.6423452","title":"Investigation of deep neural networks (DNN) for large vocabulary continuous speech recognition: Why DNN surpasses GMMS in acoustic modeling","display_name":"Investigation of deep neural networks (DNN) for large vocabulary continuous speech recognition: Why DNN surpasses GMMS in acoustic modeling","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2063689849","doi":"https://doi.org/10.1109/iscslp.2012.6423452","mag":"2063689849"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2012.6423452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 8th International Symposium on Chinese Spoken Language Processing","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/A5101924451","display_name":"Jia Pan","orcid":"https://orcid.org/0000-0002-7073-1744"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Pan","raw_affiliation_strings":["IFlytek Research, Hefei, Anhui, China","iFlytek Research, Hefei, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFlytek Research, Hefei, Anhui, China","institution_ids":[]},{"raw_affiliation_string":"iFlytek Research, Hefei, Anhui, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103868831","display_name":"Cong Liu","orcid":"https://orcid.org/0000-0002-7313-9711"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cong Liu","raw_affiliation_strings":["IFlytek Research, Hefei, Anhui, China","iFlytek Research, Hefei, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFlytek Research, Hefei, Anhui, China","institution_ids":[]},{"raw_affiliation_string":"iFlytek Research, Hefei, Anhui, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430099","display_name":"Zhiguo Wang","orcid":"https://orcid.org/0000-0003-3686-6220"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiguo Wang","raw_affiliation_strings":["IFlytek Research, Hefei, Anhui, China","iFlytek Research, Hefei, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFlytek Research, Hefei, Anhui, China","institution_ids":[]},{"raw_affiliation_string":"iFlytek Research, Hefei, Anhui, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101816319","display_name":"Yu Hu","orcid":"https://orcid.org/0000-0002-6302-3539"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Hu","raw_affiliation_strings":["IFlytek Research, Hefei, Anhui, China","iFlytek Research, Hefei, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFlytek Research, Hefei, Anhui, China","institution_ids":[]},{"raw_affiliation_string":"iFlytek Research, Hefei, Anhui, China","institution_ids":[]}]},{"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","Dept. of Computer Science & Engineering, York University, Toronto, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, York University, Toronto, Canada","institution_ids":["https://openalex.org/I192455969"]},{"raw_affiliation_string":"Dept. of Computer Science & Engineering, York University, Toronto, Canada","institution_ids":["https://openalex.org/I192455969"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":98,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"301","last_page":"305"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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":0.9970999956130981,"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":0.8085678219795227},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7392733693122864},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6263344287872314},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5912017226219177},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5746012926101685},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5371974110603333},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5200014710426331},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5145165920257568},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48020824790000916},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.47592833638191223},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.46755921840667725},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4669191837310791},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.43838179111480713},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.436712384223938},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.35657399892807007},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09312900900840759}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8085678219795227},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7392733693122864},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6263344287872314},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5912017226219177},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5746012926101685},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5371974110603333},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5200014710426331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5145165920257568},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48020824790000916},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.47592833638191223},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.46755921840667725},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4669191837310791},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.43838179111480713},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.436712384223938},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.35657399892807007},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09312900900840759},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2012.6423452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 8th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W217970951","https://openalex.org/W2020144989","https://openalex.org/W2136922672","https://openalex.org/W2144792281","https://openalex.org/W2147768505","https://openalex.org/W2156373089","https://openalex.org/W2160306971","https://openalex.org/W2394932179","https://openalex.org/W6711962127"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2373675101","https://openalex.org/W4245698648","https://openalex.org/W2401394187","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306","https://openalex.org/W1494724239"],"abstract_inverted_index":{"Recently,":[0],"it":[1],"has":[2,11],"been":[3],"reported":[4],"that":[5,44,106,150],"context-dependent":[6],"deep":[7],"neural":[8],"network":[9],"(DNN)":[10],"achieved":[12],"some":[13,62],"unprecedented":[14,85],"gains":[15],"in":[16,61,144,168],"many":[17],"challenging":[18],"ASR":[19,63],"tasks,":[20],"including":[21],"the":[22,55,84,94,130,162],"well-known":[23],"Switchboard":[24],"task.":[25],"In":[26],"this":[27],"paper,":[28],"we":[29,74,122],"first":[30],"investigate":[31],"DNN":[32,45,88,97,131],"for":[33],"several":[34,110],"large":[35],"vocabulary":[36],"speech":[37,112],"recognition":[38],"tasks.":[39],"Our":[40,91,146],"results":[41,147],"have":[42,75,123,148],"confirmed":[43],"can":[46],"consistently":[47],"achieve":[48],"about":[49],"25-30%":[50],"relative":[51,158],"error":[52,159],"reduction":[53,160],"over":[54,156,161],"best":[56],"discriminatively":[57],"trained":[58],"GMMs":[59],"even":[60],"tasks":[64],"with":[65],"up":[66],"to":[67,81,102,128],"700":[68],"hours":[69],"of":[70,79,87,96,152],"training":[71],"data.":[72],"Next,":[73],"conducted":[76],"a":[77,115,125],"series":[78],"experiments":[80,92],"study":[82],"where":[83],"gain":[86,95],"comes":[89],"from.":[90],"show":[93],"is":[98],"almost":[99],"entirely":[100],"attributed":[101],"DNN's":[103],"feature":[104],"vectors":[105],"are":[107],"concatenated":[108],"from":[109],"consecutive":[111],"frames":[113],"within":[114],"relatively":[116],"long":[117],"context":[118],"window.":[119],"At":[120],"last,":[121],"proposed":[124],"few":[126],"ideas":[127],"reconfigure":[129],"input":[132],"features,":[133],"such":[134],"as":[135],"using":[136],"logarithm":[137],"spectrum":[138],"features":[139,143,167],"or":[140,165],"VTLN":[141],"normalized":[142],"DNN.":[145,169],"shown":[149],"each":[151],"these":[153],"methods":[154],"yields":[155],"3%":[157],"traditional":[163],"MFCC":[164],"PLP":[166]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}