{"id":"https://openalex.org/W2156761992","doi":"https://doi.org/10.1109/icassp.2012.6288980","title":"Discriminative dynamic Gaussian mixture selection with enhanced robustness and performance for multi-accent speech recognition","display_name":"Discriminative dynamic Gaussian mixture selection with enhanced robustness and performance for multi-accent speech recognition","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2156761992","doi":"https://doi.org/10.1109/icassp.2012.6288980","mag":"2156761992"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288980","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288980","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 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/A5100460206","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0002-7730-5131"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Center for Speech and Language Technologies, Division of Technology Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Division of Technology Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330660","display_name":"Yi Liu","orcid":"https://orcid.org/0009-0001-4797-7826"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["Center for Speech and Language Technologies, Division of Technology Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Division of Technology Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069555295","display_name":"Yunqing Xia","orcid":"https://orcid.org/0009-0005-8608-574X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunqing Xia","raw_affiliation_strings":["Center for Speech and Language Technologies, Division of Technology Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Division of Technology Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13981326,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"4749","last_page":"4752"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991999864578247,"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":0.9987000226974487,"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":0.8433656096458435},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7472425699234009},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7037342190742493},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6867064237594604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6538373827934265},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5202420949935913},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5152547955513},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5014688968658447},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4457295536994934},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4205250144004822}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8433656096458435},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7472425699234009},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7037342190742493},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6867064237594604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6538373827934265},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5202420949935913},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5152547955513},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5014688968658447},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4457295536994934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4205250144004822},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6288980","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288980","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 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":0.7400000095367432,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1979356488","https://openalex.org/W2094975628","https://openalex.org/W2097571405","https://openalex.org/W2100969003","https://openalex.org/W2113419766","https://openalex.org/W2113890879","https://openalex.org/W2158289097","https://openalex.org/W2162432783","https://openalex.org/W6677198281"],"related_works":["https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2146591867","https://openalex.org/W2160650576","https://openalex.org/W2162582511","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290"],"abstract_inverted_index":{"We":[0,55],"propose":[1],"a":[2,14,50,58,102],"discriminative":[3],"DGMS":[4,129],"(dynamic":[5],"Gaussian":[6,18,36],"mixture":[7,19],"selection)":[8],"strategy":[9],"to":[10,21,61,67,78,90,100],"enhance":[11],"restructuring":[12],"of":[13,17,35,104],"pre-trained":[15],"set":[16,45],"models":[20],"cover":[22,101],"unexpected":[23],"acoustic":[24],"variations":[25,106],"at":[26],"run":[27],"time":[28],"in":[29,38,107],"automatic":[30],"speech":[31,87,113],"recognition.":[32],"The":[33],"number":[34],"components":[37],"each":[39,85],"hidden":[40],"Markov":[41],"model":[42],"(HMM)":[43],"state":[44,72,82],"aside":[46],"is":[47,76],"determined":[48],"by":[49],"minimum":[51],"classification":[52],"error":[53,123],"criterion.":[54],"also":[56],"use":[57],"genetic":[59],"algorithm":[60],"solve":[62],"the":[63,69,80,116,127],"integer":[64],"programing":[65],"problem":[66],"find":[68],"globally":[70],"optimal":[71],"size.":[73],"This":[74],"parameter":[75],"used":[77],"adjust":[79],"HMM":[81,132],"densities":[83],"for":[84,97,149],"input":[86],"frame,":[88],"leading":[89],"both":[91],"high":[92],"robustness":[93],"and":[94,130,143],"good":[95],"resolution":[96],"dynamic":[98],"tracking":[99],"diversity":[103],"temporal":[105],"speech.":[108],"Tested":[109],"on":[110,136],"an":[111,120],"accented":[112],"recognition":[114],"application,":[115],"proposed":[117],"framework":[118],"yields":[119],"improved":[121],"syllable":[122],"rate":[124],"reduction":[125],"over":[126],"conventional":[128],"augmented":[131],"systems":[133],"when":[134],"evaluated":[135],"three":[137],"typical":[138],"Chinese":[139],"accents,":[140],"Chuan,":[141],"Yue":[142],"Wu,":[144],"while":[145],"maintaining":[146],"its":[147],"performance":[148],"standard":[150],"Putonghua.":[151]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}