{"id":"https://openalex.org/W2094975628","doi":"https://doi.org/10.1109/tasl.2013.2265087","title":"Reliable Accent-Specific Unit Generation With Discriminative Dynamic Gaussian Mixture Selection for Multi-Accent Chinese Speech Recognition","display_name":"Reliable Accent-Specific Unit Generation With Discriminative Dynamic Gaussian Mixture Selection for Multi-Accent Chinese Speech Recognition","publication_year":2013,"publication_date":"2013-05-29","ids":{"openalex":"https://openalex.org/W2094975628","doi":"https://doi.org/10.1109/tasl.2013.2265087","mag":"2094975628"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2013.2265087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2013.2265087","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5100460272","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0003-3009-598X"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Machine Intelligence Laboratory, Engineering Department, University of Cambridge, Cambridge, UK","Engineering Department University of Cambridge Cambridge UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Intelligence Laboratory, Engineering Department, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Engineering Department University of Cambridge Cambridge UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330576","display_name":"Yi Liu","orcid":"https://orcid.org/0000-0002-8490-6285"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I4210096887","display_name":"HKUST Shenzhen Research Institute","ror":"https://ror.org/00sz56h79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I200769079","https://openalex.org/I20231570","https://openalex.org/I4210096887","https://openalex.org/I4210147811"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["Shenzhen Key Laboratory of Intelligent Media and Speech, PKU-HKUST Shenzhen-Hong Kong Institution, Shenzhen, China","Shenzhen Key Lab. of Intell. Media & Speech, PKU-HKUST Shenzhen Hong Kong Instn., Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Key Laboratory of Intelligent Media and Speech, PKU-HKUST Shenzhen-Hong Kong Institution, Shenzhen, China","institution_ids":["https://openalex.org/I4210096887","https://openalex.org/I889458895"]},{"raw_affiliation_string":"Shenzhen Key Lab. of Intell. Media & Speech, PKU-HKUST Shenzhen Hong Kong Instn., Shenzhen, China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"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, Tsinghua University, Beijing, China","Center for Speech & Language Technol., Tsinghua Univ., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Center for Speech & Language Technol., Tsinghua Univ., Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328995","display_name":"Xuan Wang","orcid":"https://orcid.org/0000-0002-3512-0649"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Wang","raw_affiliation_strings":["Beijing Language and Cultural University, Beijing, China","Beijing Language & Cultural Univ., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Language and Cultural University, Beijing, China","institution_ids":["https://openalex.org/I115212828"]},{"raw_affiliation_string":"Beijing Language & Cultural Univ., Beijing, China","institution_ids":["https://openalex.org/I115212828"]}]},{"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","School or ECE, Georgia Institute of Technology, Atlanta, GA, USA#TAB#"],"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"]},{"raw_affiliation_string":"School or ECE, Georgia Institute of Technology, Atlanta, GA, USA#TAB#","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4589,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.92938191,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"21","issue":"10","first_page":"2073","last_page":"2084"},"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":0.9988999962806702,"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":0.998199999332428,"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/discriminative-model","display_name":"Discriminative model","score":0.8854383230209351},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8400342464447021},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7700527906417847},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.680850625038147},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.6617672443389893},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5760373473167419},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48614808917045593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4702262878417969},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45801299810409546},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4314943552017212},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.430736780166626},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.41504979133605957}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8854383230209351},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8400342464447021},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7700527906417847},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.680850625038147},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.6617672443389893},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5760373473167419},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48614808917045593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4702262878417969},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45801299810409546},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4314943552017212},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.430736780166626},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.41504979133605957},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2013.2265087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2013.2265087","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309321","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"},{"id":"https://openalex.org/F4320325046","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W5524598","https://openalex.org/W86944614","https://openalex.org/W93148613","https://openalex.org/W104457985","https://openalex.org/W105045830","https://openalex.org/W113498433","https://openalex.org/W117083981","https://openalex.org/W184039015","https://openalex.org/W1493946344","https://openalex.org/W1526236009","https://openalex.org/W1553129813","https://openalex.org/W1571305296","https://openalex.org/W1977806456","https://openalex.org/W1993607814","https://openalex.org/W1995609724","https://openalex.org/W1996545497","https://openalex.org/W2022464160","https://openalex.org/W2025929295","https://openalex.org/W2042281066","https://openalex.org/W2097571405","https://openalex.org/W2100969003","https://openalex.org/W2102893423","https://openalex.org/W2108872474","https://openalex.org/W2110467295","https://openalex.org/W2115900267","https://openalex.org/W2119785873","https://openalex.org/W2133803203","https://openalex.org/W2133853764","https://openalex.org/W2146591867","https://openalex.org/W2146871184","https://openalex.org/W2149609556","https://openalex.org/W2154092232","https://openalex.org/W2158289097","https://openalex.org/W2162432783","https://openalex.org/W2167188741","https://openalex.org/W2263610414","https://openalex.org/W2407381645","https://openalex.org/W6604211769","https://openalex.org/W6607605394","https://openalex.org/W6714010836"],"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":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,43,82,158,171],"discriminative":[6,64,91,96],"dynamic":[7,55],"Gaussian":[8],"mixture":[9],"selection":[10],"(DGMS)":[11],"strategy":[12],"to":[13,28,53,71,112],"generate":[14,29],"reliable":[15],"accent-specific":[16],"units":[17],"(ASUs)":[18],"for":[19,58,93],"multi-accent":[20,115],"speech":[21,61],"recognition.":[22],"Time-aligned":[23],"phone":[24],"recognition":[25],"is":[26,69,102,110],"used":[27],"the":[30,73,76,87,90,107,128,132],"ASUs":[31],"that":[32,101,148],"model":[33,49,129,135,154],"accent":[34],"variations":[35],"explicitly":[36],"and":[37,41,145,166],"accurately.":[38],"DGMS":[39,94],"reconstructs":[40],"adjusts":[42],"pre-trained":[44],"set":[45],"of":[46,75,98,131,163],"hidden":[47],"Markov":[48],"(HMM)":[50],"state":[51,78],"densities":[52,57,80],"build":[54],"observation":[56,79],"each":[59],"input":[60],"frame.":[62],"A":[63],"minimum":[65],"classification":[66],"error":[67,160],"criterion":[68],"adopted":[70],"optimize":[72],"sizes":[74],"HMM":[77],"with":[81,157],"genetic":[83],"algorithm":[84],"(GA).":[85],"To":[86],"author's":[88],"knowledge,":[89],"optimization":[92],"accomplishes":[95],"training":[97],"discrete":[99],"variables":[100],"first":[103],"proposed.":[104],"We":[105],"found":[106],"proposed":[108],"framework":[109],"able":[111],"cover":[113],"more":[114],"changes,":[116],"thus":[117],"reduce":[118],"some":[119],"performance":[120,173],"loss":[121],"in":[122],"pruned":[123],"beam":[124],"search,":[125],"without":[126],"increasing":[127],"size":[130],"original":[133],"acoustic":[134,153],"set.":[136],"Evaluation":[137],"on":[138,174],"three":[139],"typical":[140],"Chinese":[141],"accents,":[142],"Chuan,":[143],"Yue":[144],"Wu,":[146],"shows":[147],"our":[149],"approach":[150],"outperforms":[151],"traditional":[152],"reconstruction":[155],"techniques":[156],"syllable":[159],"rate":[161],"reduction":[162],"8.0%,":[164],"5.5%":[165],"5.0%,":[167],"respectively,":[168],"while":[169],"maintaining":[170],"good":[172],"standard":[175],"Putonghua":[176],"speech.":[177]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}