{"id":"https://openalex.org/W2107361128","doi":"https://doi.org/10.1109/icassp.2012.6288870","title":"Stranded Gaussian mixture hidden Markov models for robust speech recognition","display_name":"Stranded Gaussian mixture hidden Markov models for robust speech recognition","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2107361128","doi":"https://doi.org/10.1109/icassp.2012.6288870","mag":"2107361128"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288870","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":"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"],"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"]}]},{"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"],"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"]}]}],"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":2.3415,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.8973274,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4301","last_page":"4304"},"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":0.9973000288009644,"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":0.9958000183105469,"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":0.9481660723686218},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8676265478134155},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6818037629127502},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6203200221061707},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5985461473464966},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5342774391174316},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5227208733558655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5193558931350708},{"id":"https://openalex.org/keywords/mixture-theory","display_name":"Mixture theory","score":0.48139050602912903},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.45647627115249634}],"concepts":[{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.9481660723686218},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8676265478134155},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6818037629127502},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6203200221061707},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5985461473464966},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5342774391174316},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5227208733558655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5193558931350708},{"id":"https://openalex.org/C2779736610","wikidata":"https://www.wikidata.org/wiki/Q6884140","display_name":"Mixture theory","level":3,"score":0.48139050602912903},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.45647627115249634},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"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":2,"locations":[{"id":"doi:10.1109/icassp.2012.6288870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288870","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.720.443","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.720.443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://users.ece.gatech.edu/%7Eyzhao33/publications/ICASSP2012_StrandedGMM.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1833981795","https://openalex.org/W2051347452","https://openalex.org/W2096044236","https://openalex.org/W2108840068","https://openalex.org/W2110575115","https://openalex.org/W2122836549","https://openalex.org/W2125838338","https://openalex.org/W2140337865","https://openalex.org/W2140669298","https://openalex.org/W2151484683","https://openalex.org/W6678298469"],"related_works":["https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2160650576","https://openalex.org/W1578916557","https://openalex.org/W2095350775","https://openalex.org/W1975321310","https://openalex.org/W1992295166","https://openalex.org/W792241301","https://openalex.org/W1964286703","https://openalex.org/W2143508933"],"abstract_inverted_index":{"Gaussian":[0,30],"mixture":[1,31,45,49,58,105],"(GMM)-HMMs,":[2],"though":[3],"being":[4,16],"the":[5,28,36,41,44,56,63,69,72,76,89,96,104],"predominant":[6],"modeling":[7],"technique":[8],"for":[9],"speech":[10],"recognition,":[11],"are":[12],"often":[13],"criticized":[14],"as":[15],"inaccurate":[17],"to":[18,38,53,62],"model":[19,40],"heterogeneous":[20],"data":[21],"sources.":[22],"In":[23,68],"this":[24],"work,":[25],"we":[26],"propose":[27],"stranded":[29],"(SGMM)-HMM,":[32],"an":[33],"extension":[34],"of":[35,83],"GMM-HMM,":[37],"explicitly":[39],"dependence":[42],"among":[43],"components,":[46],"i.e.,":[47],"each":[48],"component":[50,59],"is":[51],"assumed":[52],"depend":[54],"on":[55],"previous":[57],"in":[60,107],"addition":[61],"state":[64],"that":[65,99],"generates":[66],"it.":[67],"evaluation":[70],"over":[71,88],"Aurora":[73],"2":[74],"database,":[75],"proposed":[77],"20-mixture":[78],"SGMM":[79],"system":[80],"obtains":[81],"WER":[82],"8.07%,":[84],"10%":[85],"relative":[86],"improvement":[87],"baseline":[90],"GMM":[91],"system.":[92],"The":[93],"experiments":[94],"demonstrate":[95],"discriminating":[97],"power":[98],"would":[100],"be":[101],"possessed":[102],"by":[103],"weights":[106],"their":[108],"advanced":[109],"form.":[110]},"counts_by_year":[{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}