{"id":"https://openalex.org/W1969025207","doi":"https://doi.org/10.1109/acssc.2012.6489304","title":"Joint tracking of clean speech and noise using HMMs and particle filters for robust speech recognition","display_name":"Joint tracking of clean speech and noise using HMMs and particle filters for robust speech recognition","publication_year":2012,"publication_date":"2012-11-01","ids":{"openalex":"https://openalex.org/W1969025207","doi":"https://doi.org/10.1109/acssc.2012.6489304","mag":"1969025207"},"language":"en","primary_location":{"id":"doi:10.1109/acssc.2012.6489304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acssc.2012.6489304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 Conference Record of the Forty Sixth Asilomar Conference on Signals, Systems and Computers (ASILOMAR)","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/A5033191202","display_name":"Aleem Mushtaq","orcid":null},"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":true,"raw_author_name":"Aleem Mushtaq","raw_affiliation_strings":["School of ECE, Georgia Institute of Technology, Atlanta, GA, USA","School of ECE, Georgia Institute of Technology, Atlanta, 30332-0250, USA"],"affiliations":[{"raw_affiliation_string":"School of ECE, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of ECE, Georgia Institute of Technology, Atlanta, 30332-0250, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"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 ECE, Georgia Institute of Technology, Atlanta, GA, USA","School of ECE, Georgia Institute of Technology, Atlanta, 30332-0250, USA"],"affiliations":[{"raw_affiliation_string":"School of ECE, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of ECE, Georgia Institute of Technology, Atlanta, 30332-0250, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5033191202"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.2448,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50347133,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"1618","last_page":"1622"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7580165863037109},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7311912775039673},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7088664174079895},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7001599073410034},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5982993245124817},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.5418956279754639},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.510847270488739},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.4620930552482605},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.45907872915267944},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44180306792259216},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42959344387054443},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.42235758900642395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40279054641723633},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.17978116869926453},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11699333786964417}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7580165863037109},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7311912775039673},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7088664174079895},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7001599073410034},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5982993245124817},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.5418956279754639},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.510847270488739},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.4620930552482605},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.45907872915267944},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44180306792259216},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42959344387054443},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.42235758900642395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40279054641723633},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.17978116869926453},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11699333786964417},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acssc.2012.6489304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acssc.2012.6489304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 Conference Record of the Forty Sixth Asilomar Conference on Signals, Systems and Computers (ASILOMAR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W87496662","https://openalex.org/W200523513","https://openalex.org/W1500564636","https://openalex.org/W1517348348","https://openalex.org/W1573570773","https://openalex.org/W1645647889","https://openalex.org/W2045036776","https://openalex.org/W2100969003","https://openalex.org/W2106958364","https://openalex.org/W2108215203","https://openalex.org/W2114548037","https://openalex.org/W2126597753","https://openalex.org/W2146871184","https://openalex.org/W2158069733","https://openalex.org/W2158699620","https://openalex.org/W2160337655","https://openalex.org/W6608128368","https://openalex.org/W6630687167","https://openalex.org/W6634340323"],"related_works":["https://openalex.org/W3211091508","https://openalex.org/W193702574","https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W1523214805","https://openalex.org/W4294771049","https://openalex.org/W2559040841","https://openalex.org/W2341426843","https://openalex.org/W2121894251","https://openalex.org/W2131711534"],"abstract_inverted_index":{"We":[0,76],"propose":[1],"a":[2],"dynamic":[3,60],"joint":[4],"tracking":[5,47,51],"framework":[6],"to":[7,18],"monitor":[8],"the":[9,20,54,64,67,83,92,95,105,110],"clean":[10,24],"speech":[11,25,46],"signal":[12,26],"and":[13,38,52,89],"noise":[14,55,61,97,111],"simultaneously":[15],"in":[16,69,74],"order":[17],"compensate":[19],"noisy":[21],"features.":[22],"The":[23,42,57],"is":[27,48,113],"tracked":[28],"using":[29],"an":[30],"integrated":[31],"algorithm":[32,68],"based":[33],"on":[34,78],"both":[35],"particle":[36],"filters":[37],"hidden":[39],"Markov":[40],"models.":[41],"information":[43,62],"available":[44],"from":[45],"used":[49],"for":[50,94],"estimating":[53],"parameters.":[56],"availability":[58],"of":[59,66,71],"enhances":[63],"robustness":[65],"case":[70],"large":[72],"fluctuations":[73],"noise.":[75],"report":[77],"experimental":[79],"results":[80],"obtained":[81],"with":[82],"Aurora-2":[84],"connected":[85],"digit":[86],"recognition":[87],"task,":[88],"show":[90],"that":[91],"performance":[93],"additive":[96],"cases":[98],"can":[99],"be":[100],"improved":[101],"by":[102],"12:15%":[103],"over":[104],"state-of-the-art":[106],"multi-condition":[107],"training":[108],"if":[109],"mean":[112],"updated":[114],"every":[115],"300":[116],"milliseconds.":[117]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}