{"id":"https://openalex.org/W2890698554","doi":null,"title":"ADAPTATION OF HYBRID DEEP NEURAL NETWORK-HIDDEN MARKOV MODEL SPEECH RECOGNITION SYSTEM USING A SUB-SPACE APPROACH","display_name":"ADAPTATION OF HYBRID DEEP NEURAL NETWORK-HIDDEN MARKOV MODEL SPEECH RECOGNITION SYSTEM USING A SUB-SPACE APPROACH","publication_year":2017,"publication_date":"2017-08-02","ids":{"openalex":"https://openalex.org/W2890698554","mag":"2890698554"},"language":"en","primary_location":{"id":"pmh:oai:smartech.gatech.edu:1853/60171","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/1853/60171","pdf_url":null,"source":{"id":"https://openalex.org/S4377196313","display_name":"SMARTech Repository (Georgia Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I130701444","host_organization_name":"Georgia Institute of Technology","host_organization_lineage":["https://openalex.org/I130701444"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dissertation"},"parent_works":[],"lineage":["https://openalex.org/W2890698554"],"child_works_count":0,"type":"dissertation","is_traditional":true,"indexed_in":[],"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/A5100775646","display_name":"Muhammad Rizwan","orcid":"https://orcid.org/0000-0001-5886-1063","observed_orcids":["https://orcid.org/0000-0001-5886-1063","https://orcid.org/0000-0002-7235-3142"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Muhammad Rizwan","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-5886-1063","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5100775646"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.0,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-adaptation","display_name":"speaker adaptation","score":0.7049999833106995},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.8080000281333923},{"id":"https://openalex.org/keywords/subspace-methods","display_name":"subspace methods","score":0.6809999942779541},{"id":"https://openalex.org/keywords/accent-classification","display_name":"accent classification","score":0.8190000057220459},{"id":"https://openalex.org/keywords/phoneme-classification","display_name":"phoneme classification","score":0.8100000023841858},{"id":"https://openalex.org/keywords/limited-adaptation-data","display_name":"limited adaptation data","score":0.8659999966621399},{"id":"https://openalex.org/keywords/training-test-mismatch","display_name":"training-test mismatch","score":0.6179999709129333},{"id":"https://openalex.org/keywords/hidden-layer-activations","display_name":"hidden layer activations","score":0.6010000109672546}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.787949800491333},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7115115523338318},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6488045454025269},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5838888883590698},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5482497811317444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5080023407936096},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4710892140865326},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.425004780292511},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4111485183238983},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38229820132255554},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28902608156204224},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2754775285720825},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1571837067604065},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.05170118808746338},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:smartech.gatech.edu:1853/60171","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/1853/60171","pdf_url":null,"source":{"id":"https://openalex.org/S4377196313","display_name":"SMARTech Repository (Georgia Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I130701444","host_organization_name":"Georgia Institute of Technology","host_organization_lineage":["https://openalex.org/I130701444"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dissertation"},{"id":"mag:2890698554","doi":null,"is_oa":false,"landing_page_url":"https://smartech.gatech.edu/bitstream/1853/60171/1/RIZWAN-DISSERTATION-2017.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2537979776","https://openalex.org/W7148474520","https://openalex.org/W2738470653","https://openalex.org/W1982768103","https://openalex.org/W2056445351","https://openalex.org/W3113244915","https://openalex.org/W2291725357","https://openalex.org/W7160861768","https://openalex.org/W2156739919","https://openalex.org/W2507389969"],"abstract_inverted_index":{"The":[0,49,113,207],"performance":[1],"of":[2,13,23,82,99,108,118,179,194,234],"automatic":[3],"speech":[4,100,201],"recognition":[5,101],"(ASR)":[6],"system":[7,73,102],"can":[8,56,136,140,212],"be":[9,57,137,172],"enhanced":[10],"by":[11,59,103,198],"adaptation":[12,61,65,83,98,193,233],"the":[14,35,88,97,161,200,204,218,232,235],"ASR":[15,195],"for":[16,87,96,217,229,231],"a":[17,21,45,68,79,105,119,134],"particular":[18],"speaker":[19,60,70,120,135,156,192,205,215,219],"or":[20],"group":[22],"speakers.":[24],"In":[25,75],"ASR,":[26],"training":[27,52,162],"and":[28,53,139],"testing":[29,54],"data":[30,66,84,109],"often":[31,40],"do":[32],"not":[33],"follow":[34],"same":[36],"statistics;":[37],"they":[38],"are":[39,169],"mismatched,":[41],"which":[42,63],"leads":[43],"to":[44,71,121,171,225],"gap":[46],"in":[47,124,160,175],"performance.":[48,74],"difference":[50],"between":[51],"statistics":[55],"minimized":[58],"techniques,":[62],"require":[64],"from":[67,133],"target":[69,89,155],"optimize":[72],"many":[76],"cases,":[77],"only":[78],"limited":[80,106],"amount":[81,107],"is":[85,151,196],"available":[86],"speaker.":[90],"This":[91],"thesis":[92],"proposes":[93],"multiple":[94,131],"methods":[95,222],"using":[104,130],"(a":[110],"few":[111],"words).":[112],"first":[114],"method":[115,150],"classifies":[116],"accent":[117,143],"identify":[122],"variability":[123],"speaking":[125],"style.":[126],"Results":[127],"indicated":[128],"that":[129],"words":[132],"efficient":[138],"provide":[141,213],"better":[142],"classification":[144,149],"accuracy.":[145],"Next":[146],"adaptive":[147],"phoneme":[148,177],"proposed":[152],"based":[153],"on":[154],"similarity":[157],"with":[158,183,203],"speakers":[159],"data.":[163],"DNNs":[164],"last":[165],"hidden":[166],"layer":[167],"activations":[168],"found":[170],"more":[173],"useful":[174,214],"identifying":[176],"classes":[178],"frames":[180],"as":[181,189],"compared":[182],"traditional":[184],"raw":[185],"Mel-frequency":[186],"cepstral":[187],"coefficients":[188],"features.":[190,206],"Finally,":[191],"presented":[197],"augmenting":[199],"features":[202],"universal":[208],"background":[209],"sparse":[210],"coding":[211],"information":[216],"adaptation.":[220],"These":[221],"may":[223],"lead":[224],"some":[226],"new":[227],"opportunities":[228],"research":[230],"ASR.":[236]},"counts_by_year":[],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2018-09-27T00:00:00"}