{"id":"https://openalex.org/W2141623350","doi":"https://doi.org/10.1109/icassp.2006.1660221","title":"Modeling Variance Variation in a Variable Parameter HMM Framework for Noise Robust Speech Recognition","display_name":"Modeling Variance Variation in a Variable Parameter HMM Framework for Noise Robust Speech Recognition","publication_year":2006,"publication_date":"2006-08-03","ids":{"openalex":"https://openalex.org/W2141623350","doi":"https://doi.org/10.1109/icassp.2006.1660221","mag":"2141623350"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2006.1660221","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660221","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","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/A5102014291","display_name":"Xiaodong Cui","orcid":"https://orcid.org/0000-0003-4865-1307"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiaodong Cui","raw_affiliation_strings":["Department of Electrical Engineering, University of California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077401426","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0001-8786-3391"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102014291"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":0.4517,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.74745,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"1117"},"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":0.9998000264167786,"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":0.9984999895095825,"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":0.8605182766914368},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5643510222434998},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5505799651145935},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5460072755813599},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5381482839584351},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5047651529312134},{"id":"https://openalex.org/keywords/polynomial","display_name":"Polynomial","score":0.4783739149570465},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.46595531702041626},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.46249154210090637},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.45836883783340454},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4457401633262634},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.4340648651123047},{"id":"https://openalex.org/keywords/estimation-theory","display_name":"Estimation theory","score":0.4246402978897095},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.41845250129699707},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.41768431663513184},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3793341815471649},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3668699264526367},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34102100133895874}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8605182766914368},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5643510222434998},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5505799651145935},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5460072755813599},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5381482839584351},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5047651529312134},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.4783739149570465},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46595531702041626},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.46249154210090637},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.45836883783340454},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4457401633262634},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.4340648651123047},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.4246402978897095},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.41845250129699707},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.41768431663513184},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3793341815471649},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3668699264526367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34102100133895874},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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":1,"locations":[{"id":"doi:10.1109/icassp.2006.1660221","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660221","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2045036776","https://openalex.org/W2049633694","https://openalex.org/W2080921589","https://openalex.org/W2136466519","https://openalex.org/W2145475542","https://openalex.org/W2157342986","https://openalex.org/W3129711340","https://openalex.org/W7048738093"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2097963413","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W3145575561","https://openalex.org/W2995886640","https://openalex.org/W1591475660","https://openalex.org/W2001275470","https://openalex.org/W2164162849"],"abstract_inverted_index":{"Variance":[0],"variation":[1,27,82],"with":[2],"respect":[3],"to":[4,35],"a":[5,15,31],"continuous":[6],"environment-department":[7],"variable":[8,16],"is":[9,28,53,83],"investigated":[10],"in":[11,14,38],"this":[12],"paper":[13],"parameter":[17],"Gaussian":[18],"mixture":[19],"HMM":[20],"(VP-GMHMM)":[21],"for":[22],"noisy":[23],"speech":[24],"recognition.":[25],"The":[26,45],"modeled":[29],"by":[30,69],"scaling":[32,51,73],"polynomial":[33,52],"applied":[34],"the":[36,39,50,62,71,76],"variances":[37],"conventional":[40],"hidden":[41],"Markov":[42],"acoustic":[43],"models.":[44],"maximum":[46],"likelihood":[47],"estimation":[48],"of":[49],"performed":[54],"under":[55],"an":[56],"SNR":[57],"quantization":[58],"approximation.":[59],"Experiments":[60],"on":[61],"Aurora":[63],"2":[64],"database":[65],"show":[66],"significant":[67],"improvements":[68],"incorporating":[70],"variance":[72],"scheme":[74],"into":[75],"previous":[77],"VP-GMHMM":[78],"where":[79],"only":[80],"mean":[81],"considered.":[84]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}