{"id":"https://openalex.org/W2075255969","doi":"https://doi.org/10.1109/icassp.2014.6853585","title":"On combining DNN and GMM with unsupervised speaker adaptation for robust automatic speech recognition","display_name":"On combining DNN and GMM with unsupervised speaker adaptation for robust automatic speech recognition","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2075255969","doi":"https://doi.org/10.1109/icassp.2014.6853585","mag":"2075255969"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6853585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100399763","display_name":"Shilin Liu","orcid":"https://orcid.org/0000-0002-3704-3798"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Shilin Liu","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore","Sch. of Comput. Nat., Univ. of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Sch. of Comput. Nat., Univ. of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032798707","display_name":"Khe Chai Sim","orcid":"https://orcid.org/0000-0002-0866-2223"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Khe Chai Sim","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore","Sch. of Comput. Nat., Univ. of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Sch. of Comput. Nat., Univ. of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100399763"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":4.9082,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.95306217,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"pp","issue":null,"first_page":"195","last_page":"199"},"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/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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9897000193595886,"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/mixture-model","display_name":"Mixture model","score":0.7719699144363403},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7523339986801147},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.680457592010498},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6706552505493164},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6172501444816589},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5627829432487488},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5355080962181091},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5083255171775818},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49695661664009094},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4800911247730255},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45469680428504944},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4413769543170929},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4380044937133789}],"concepts":[{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.7719699144363403},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7523339986801147},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.680457592010498},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6706552505493164},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6172501444816589},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5627829432487488},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5355080962181091},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5083255171775818},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49695661664009094},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4800911247730255},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45469680428504944},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4413769543170929},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4380044937133789},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6853585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.699999988079071,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1993409002","https://openalex.org/W1993882792","https://openalex.org/W2001900102","https://openalex.org/W2012897754","https://openalex.org/W2037740282","https://openalex.org/W2064153692","https://openalex.org/W2100969003","https://openalex.org/W2123237149","https://openalex.org/W2125838338","https://openalex.org/W2147768505","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2164243880","https://openalex.org/W2165712214","https://openalex.org/W2400718301","https://openalex.org/W6650718749","https://openalex.org/W6712963495"],"related_works":["https://openalex.org/W2167155152","https://openalex.org/W4324119469","https://openalex.org/W2146591867","https://openalex.org/W2164868312","https://openalex.org/W2160650576","https://openalex.org/W2162582511","https://openalex.org/W4245698648","https://openalex.org/W2401394187","https://openalex.org/W2405257913","https://openalex.org/W3133710586"],"abstract_inverted_index":{"Recently,":[0],"context-dependent":[1],"Deep":[2],"Neural":[3],"Network":[4],"(CD-DNN)":[5],"has":[6],"been":[7,77],"found":[8],"to":[9,41,61,81,91,112],"significantly":[10],"outperform":[11],"Gaussian":[12],"Mixture":[13],"Model":[14],"(GMM)":[15],"for":[16,46,68,84],"various":[17],"large":[18,155],"vocabulary":[19,156],"continuous":[20],"speech":[21],"recognition":[22],"tasks.":[23],"Unlike":[24],"the":[25,34,106,116,120,123,127,132,136,146,161,170,179,189],"GMM":[26,104],"approach,":[27],"there":[28],"is":[29,52,58],"no":[30],"meaningful":[31],"interpretation":[32],"of":[33,100,115,119,126,134],"DNN":[35,49,102],"parameters,":[36],"which":[37,57],"makes":[38],"it":[39],"difficult":[40],"devise":[42],"effective":[43,72],"adaptation":[44,73],"methods":[45],"DNNs.":[47,92],"Furthermore,":[48],"parameter":[50],"estimation":[51],"based":[53],"on":[54,151],"discriminative":[55],"criteria,":[56],"more":[59],"sensitive":[60],"label":[62],"errors":[63],"and":[64,79,103,122],"therefore":[65],"less":[66],"reliable":[67],"unsupervised":[69,176],"adaptation.":[70],"Many":[71],"techniques":[74],"that":[75,160],"have":[76],"developed":[78],"proven":[80],"work":[82],"well":[83],"GMM/HMM":[85],"systems":[86],"cannot":[87],"be":[88],"easily":[89],"applied":[90],"Therefore,":[93],"this":[94,141],"paper":[95,130],"proposes":[96],"a":[97,152],"novel":[98],"method":[99],"combining":[101],"using":[105],"Temporally":[107],"Varying":[108],"Weight":[109],"Regression":[110],"framework":[111,142],"take":[113],"advantage":[114],"superior":[117],"performance":[118,167],"DNNs":[121],"robust":[124],"adaptability":[125],"GMMs.":[128],"This":[129],"addresses":[131],"issue":[133],"incorporating":[135],"high-dimensional":[137],"CD-DNN":[138],"posteriors":[139],"into":[140],"without":[143],"dramatically":[144],"increasing":[145],"system":[147,164,182],"complexity.":[148],"Experimental":[149],"results":[150],"broadcast":[153],"news":[154],"transcription":[157],"task":[158],"show":[159],"proposed":[162],"GMM+DNN/HMM":[163,181],"achieved":[165],"significant":[166],"gain":[168],"over":[169,188],"baseline":[171],"DNN/HMM":[172,190],"system.":[173],"With":[174],"additional":[175],"speaker":[177],"adaptation,":[178],"best":[180],"obtained":[183],"about":[184],"20%":[185],"relative":[186],"improvements":[187],"baseline.":[191]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}