{"id":"https://openalex.org/W2094250226","doi":"https://doi.org/10.1109/slt.2014.7078562","title":"Improving deep neural networks using state projection vectors of subspace Gaussian mixture model as features","display_name":"Improving deep neural networks using state projection vectors of subspace Gaussian mixture model as features","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2094250226","doi":"https://doi.org/10.1109/slt.2014.7078562","mag":"2094250226"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2014.7078562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078562","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","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/A5040315542","display_name":"Baskar Murali Karthick","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"B. Murali Karthick","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai, Tamil Nadu, IN","[Department of electrical engineering, Indian Institute of Technology Madras, India]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai, Tamil Nadu, IN","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"[Department of electrical engineering, Indian Institute of Technology Madras, India]","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085660348","display_name":"S. Umesh","orcid":"https://orcid.org/0000-0002-5957-1444"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. Umesh","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology - Madras, Madras, India","[Department of electrical engineering, Indian Institute of Technology Madras, India]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology - Madras, Madras, India","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"[Department of electrical engineering, Indian Institute of Technology Madras, India]","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5040315542"],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":0.409,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.74990588,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"129","last_page":"134"},"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":0.9958000183105469,"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":0.993399977684021,"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/timit","display_name":"TIMIT","score":0.8585867881774902},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7291114330291748},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.7074099779129028},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6479059457778931},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6402533054351807},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6279311776161194},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6240754127502441},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5343676209449768},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5280100703239441},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5185309648513794},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.516412079334259},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4799659252166748},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44704771041870117},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4291863739490509},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2079564332962036}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.8585867881774902},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7291114330291748},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.7074099779129028},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6479059457778931},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6402533054351807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6279311776161194},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6240754127502441},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5343676209449768},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5280100703239441},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5185309648513794},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.516412079334259},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4799659252166748},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44704771041870117},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4291863739490509},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2079564332962036},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2014.7078562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078562","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1635512741","https://openalex.org/W1981706894","https://openalex.org/W2012897754","https://openalex.org/W2024490156","https://openalex.org/W2038810952","https://openalex.org/W2079623482","https://openalex.org/W2105099419","https://openalex.org/W2107687614","https://openalex.org/W2295119550","https://openalex.org/W6631362777"],"related_works":["https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2146591867","https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2160650576","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779"],"abstract_inverted_index":{"Recent":[0],"advancement":[1],"in":[2,29,44,54,86,127],"deep":[3],"neural":[4],"network":[5,208],"(DNN)":[6],"has":[7],"surpassed":[8],"the":[9,30,51,79,87,90,101,119,133,185,195,213,228,262],"conventional":[10],"hidden":[11],"Markov":[12],"model-Gaussian":[13],"mixture":[14,47],"model":[15,48],"(HMM-GMM)":[16],"framework":[17],"due":[18],"to":[19,64,99,118,146,160,194,246],"its":[20],"efficient":[21,126],"training":[22,120,205],"procedure.":[23],"Providing":[24],"better":[25],"phonetic":[26,52,76],"context":[27],"information":[28,53,77,131,244],"input":[31,158],"gives":[32],"improved":[33,257],"performance":[34,258],"for":[35,78,132,170,178],"DNN.":[36],"The":[37,233],"state":[38,66,92,102,139,186,234],"projection":[39],"vectors":[40,68,94,236],"(state":[41],"specific":[42,67,93,103,140,187,235],"vectors)":[43],"subspace":[45],"Gaussian":[46],"(SGMM)":[49],"captures":[50],"low":[55],"dimensional":[56],"vector":[57,85,104,141,188],"space.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62],"propose":[63],"use":[65],"of":[69,95,152,168,220,230],"SGMM":[70,96],"as":[71,157,239],"features":[72,124,151,159,256],"thereby":[73],"providing":[74],"additional":[75,242],"DNN":[80,164,196,210,263],"framework.":[81,165,264],"To":[82],"each":[83],"observation":[84],"train":[88,161],"data,":[89],"corresponding":[91],"are":[97,113,125,144],"aligned":[98],"form":[100],"feature":[105,111,136,142,154,190,202,215],"set.":[106,203],"Linear":[107],"discriminant":[108],"analysis":[109],"(LDA)":[110],"set":[112,137,143,191,216,226],"formed":[114],"by":[115,183,250],"applying":[116],"LDA":[117,135,200,254],"data.":[121],"Since":[122],"bottleneck":[123,147,150,189,201,255],"extracting":[128],"useful":[129,243],"discriminative":[130],"phonemes,":[134],"and":[138,176],"converted":[145],"features.":[148],"These":[149],"both":[153],"sets":[155],"act":[156],"a":[162,218],"single":[163],"Relative":[166],"improvement":[167],"8.8%":[169],"TIMIT":[171,223],"database":[172],"(core":[173],"test":[174,225],"set)":[175],"9.7%":[177],"WSJ":[179],"corpus":[180],"is":[181,259],"obtained":[182,260],"using":[184,212,261],"when":[192],"compared":[193],"trained":[197],"only":[198],"with":[199,253],"Also":[204],"Deep":[206],"belief":[207],"-":[209],"(DBN-DNN)":[211],"proposed":[214],"attains":[217],"WER":[219],"20.46%":[221],"on":[222],"core":[224],"proving":[227],"effectiveness":[229],"our":[231],"method.":[232],"while":[237],"acting":[238],"features,":[240],"provide":[241],"related":[245],"phoneme":[247],"variation.":[248],"Thus":[249],"combining":[251],"it":[252]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}