{"id":"https://openalex.org/W2012100713","doi":"https://doi.org/10.1109/icassp.2013.6639101","title":"Modeling heterogeneous data sources for speech recognition using synchronous hidden Markov models","display_name":"Modeling heterogeneous data sources for speech recognition using synchronous hidden Markov models","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2012100713","doi":"https://doi.org/10.1109/icassp.2013.6639101","mag":"2012100713"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100702071","display_name":"Yong Zhao","orcid":"https://orcid.org/0000-0003-2644-952X"},"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":"Yong Zhao","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, USA","[Dept. of Electr. & Comput. Eng., Georgia Inst. of Technol., Atlanta, GA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"[Dept. of Electr. & Comput. Eng., Georgia Inst. of Technol., Atlanta, GA, USA]","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070867959","display_name":"Biing\u2010Hwang Juang","orcid":"https://orcid.org/0000-0002-5773-5679"},"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":"Biing-Hwang Juang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, USA","[Dept. of Electr. & Comput. Eng., Georgia Inst. of Technol., Atlanta, GA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"[Dept. of Electr. & Comput. Eng., Georgia Inst. of Technol., Atlanta, GA, USA]","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.2288,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.46145155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"7403","last_page":"7407"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987000226974487,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9979000091552734,"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":0.9026691913604736},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7958166599273682},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.7116978764533997},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6255611777305603},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5351285338401794},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4865773916244507},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4627283811569214},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4494926929473877}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9026691913604736},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7958166599273682},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.7116978764533997},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6255611777305603},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5351285338401794},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4865773916244507},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4627283811569214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4494926929473877},{"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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6639101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1528056001","https://openalex.org/W1904457459","https://openalex.org/W2016185147","https://openalex.org/W2069631319","https://openalex.org/W2094709280","https://openalex.org/W2107361128","https://openalex.org/W2110575115","https://openalex.org/W2121178390","https://openalex.org/W2122028591","https://openalex.org/W2151484683","https://openalex.org/W2158069733","https://openalex.org/W2165108269","https://openalex.org/W2169967551"],"related_works":["https://openalex.org/W2136652457","https://openalex.org/W2169849734","https://openalex.org/W2116722627","https://openalex.org/W2129150969","https://openalex.org/W2236912844","https://openalex.org/W1975869217","https://openalex.org/W2401728283","https://openalex.org/W2383829109","https://openalex.org/W2379938888","https://openalex.org/W2386035178"],"abstract_inverted_index":{"In":[0],"this":[1,69],"paper,":[2],"we":[3,115],"propose":[4,116],"a":[5,95,128,153,167],"novel":[6],"acoustic":[7],"modeling":[8,30,73],"framework,":[9],"synchronous":[10,35,125,150],"HMM,":[11],"which":[12,62],"takes":[13],"full":[14],"advantage":[15],"of":[16,19,41,79,82,105,131,166],"the":[17,20,44,48,55,91,103,111,117,124,132,137,143,149,160,164,171],"capacity":[18],"heterogeneous":[21],"data":[22,92],"sources":[23],"and":[24,32,47,108,174],"achieves":[25],"an":[26,38,76],"optimal":[27],"balance":[28],"between":[29,43],"accuracy":[31],"robustness.":[33],"The":[34,52,71,140],"HMM":[36,45,161],"introduces":[37],"additional":[39],"layer":[40],"substates":[42,53],"states":[46],"Gaussian":[49],"component":[50],"variables.":[51],"have":[54],"capability":[56],"to":[57,101,109,121],"register":[58],"long-span":[59],"non-phonetic":[60],"attributes,":[61],"are":[63],"integrally":[64],"called":[65],"speech":[66,83,87,106],"scenes":[67,107],"in":[68,85,156,170],"study.":[70],"hierarchical":[72],"scheme":[74],"allows":[75],"accurate":[77],"description":[78],"probability":[80],"distribution":[81],"units":[84],"different":[86],"scenes.":[88],"To":[89],"address":[90],"sparsity":[93],"problem,":[94],"decision-based":[96],"clustering":[97],"algorithm":[98,120],"is":[99],"presented":[100],"determine":[102],"set":[104],"tie":[110],"substate":[112],"parameters.":[113],"Moreover,":[114],"multiplex":[118],"Viterbi":[119],"efficiently":[122],"decode":[123],"HMMs":[126,151],"within":[127],"search":[129],"space":[130],"same":[133],"size":[134],"as":[135],"for":[136],"standard":[138],"HMMs.":[139],"experiments":[141],"on":[142],"Aurora":[144],"2":[145],"task":[146],"show":[147],"that":[148],"produce":[152],"significant":[154],"improvement":[155],"recognition":[157],"performance":[158],"over":[159],"baseline":[162],"at":[163],"expense":[165],"moderate":[168],"increase":[169],"memory":[172],"requirement":[173],"computational":[175],"complexity.":[176]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}