{"id":"https://openalex.org/W2015354467","doi":"https://doi.org/10.1109/taslp.2015.2458585","title":"Sparse Hidden Markov Models for Speech Enhancement in Non-Stationary Noise Environments","display_name":"Sparse Hidden Markov Models for Speech Enhancement in Non-Stationary Noise Environments","publication_year":2015,"publication_date":"2015-07-20","ids":{"openalex":"https://openalex.org/W2015354467","doi":"https://doi.org/10.1109/taslp.2015.2458585","mag":"2015354467"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2015.2458585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2458585","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM 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/A5101374328","display_name":"Feng Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Feng Deng","raw_affiliation_strings":["Speech and Audio Signal Processing Laboratory, Beijing University of Technology, Beijing, CO, China","Speech and Audio Signal Processing Laboratory, School of Electronic Information and Control Engineering, Beijing University of Technology Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Audio Signal Processing Laboratory, Beijing University of Technology, Beijing, CO, China","institution_ids":["https://openalex.org/I37796252","https://openalex.org/I4210121626"]},{"raw_affiliation_string":"Speech and Audio Signal Processing Laboratory, School of Electronic Information and Control Engineering, Beijing University of Technology Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070475244","display_name":"Changchun Bao","orcid":"https://orcid.org/0000-0002-5606-5343"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Changchun Bao","raw_affiliation_strings":["Speech and Audio Signal Processing Laboratory, Beijing University of Technology, Beijing, CO, China","Speech and Audio Signal Processing Laboratory, School of Electronic Information and Control Engineering, Beijing University of Technology Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Audio Signal Processing Laboratory, Beijing University of Technology, Beijing, CO, China","institution_ids":["https://openalex.org/I37796252","https://openalex.org/I4210121626"]},{"raw_affiliation_string":"Speech and Audio Signal Processing Laboratory, School of Electronic Information and Control Engineering, Beijing University of Technology Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087492771","display_name":"W. Bastiaan Kleijn","orcid":"https://orcid.org/0000-0002-1973-3920"},"institutions":[{"id":"https://openalex.org/I41156924","display_name":"Victoria University of Wellington","ror":"https://ror.org/0040r6f76","country_code":"NZ","type":"education","lineage":["https://openalex.org/I41156924"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"W. Bastiaan Kleijn","raw_affiliation_strings":["Communications and Signal Processing Group, Victoria University of Wellington, Wellington, New Zealand","Communications and Signal Processing Group, School of Engineering and Computer Science, Victoria University of Wellington, Wellington, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communications and Signal Processing Group, Victoria University of Wellington, Wellington, New Zealand","institution_ids":["https://openalex.org/I41156924"]},{"raw_affiliation_string":"Communications and Signal Processing Group, School of Engineering and Computer Science, Victoria University of Wellington, Wellington, New Zealand","institution_ids":["https://openalex.org/I41156924"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5478,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.95347744,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"23","issue":"11","first_page":"1973","last_page":"1987"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6465851068496704},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6357698440551758},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6324692964553833},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6173182129859924},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5896141529083252},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5867335200309753},{"id":"https://openalex.org/keywords/noise-power","display_name":"Noise power","score":0.5456831455230713},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.5130230784416199},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.490204393863678},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4254693388938904},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3592008054256439},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3207228183746338},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2865896224975586},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2581990361213684},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.18937039375305176},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.16162392497062683},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07871866226196289},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06889519095420837}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6465851068496704},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6357698440551758},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6324692964553833},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6173182129859924},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5896141529083252},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5867335200309753},{"id":"https://openalex.org/C203234222","wikidata":"https://www.wikidata.org/wiki/Q2133519","display_name":"Noise power","level":3,"score":0.5456831455230713},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.5130230784416199},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.490204393863678},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4254693388938904},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3592008054256439},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3207228183746338},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2865896224975586},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2581990361213684},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.18937039375305176},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.16162392497062683},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07871866226196289},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06889519095420837},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2015.2458585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2458585","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6499999761581421}],"awards":[{"id":"https://openalex.org/G8134645764","display_name":"\u81ea\u56de\u5f52\u7ef4\u7eb3\u6ee4\u6ce2\u8bed\u97f3\u589e\u5f3a\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61471014","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1486632395","https://openalex.org/W1495679096","https://openalex.org/W1546107096","https://openalex.org/W1546892833","https://openalex.org/W1845499840","https://openalex.org/W1973538555","https://openalex.org/W1974387177","https://openalex.org/W1992475611","https://openalex.org/W2011057521","https://openalex.org/W2013682896","https://openalex.org/W2016254085","https://openalex.org/W2016313444","https://openalex.org/W2016874282","https://openalex.org/W2017866319","https://openalex.org/W2025515167","https://openalex.org/W2052818671","https://openalex.org/W2077799289","https://openalex.org/W2078528584","https://openalex.org/W2096779346","https://openalex.org/W2101042021","https://openalex.org/W2101182319","https://openalex.org/W2109215269","https://openalex.org/W2112197391","https://openalex.org/W2113367867","https://openalex.org/W2115916404","https://openalex.org/W2121973264","https://openalex.org/W2125838338","https://openalex.org/W2128653836","https://openalex.org/W2132105090","https://openalex.org/W2146324387","https://openalex.org/W2146544734","https://openalex.org/W2155889651","https://openalex.org/W2158291955","https://openalex.org/W2158336491","https://openalex.org/W2159514726","https://openalex.org/W2161182969","https://openalex.org/W2163195137","https://openalex.org/W2163835077","https://openalex.org/W2167090878","https://openalex.org/W2169147844","https://openalex.org/W2289394825","https://openalex.org/W2291948167","https://openalex.org/W2403917367","https://openalex.org/W3147539069","https://openalex.org/W4206196235","https://openalex.org/W4245919820","https://openalex.org/W6632688141","https://openalex.org/W6683202405","https://openalex.org/W6696392866","https://openalex.org/W6713432956"],"related_works":["https://openalex.org/W2135485548","https://openalex.org/W2002243964","https://openalex.org/W2022538999","https://openalex.org/W3090086172","https://openalex.org/W1955763106","https://openalex.org/W2373767407","https://openalex.org/W2025188156","https://openalex.org/W2187949121","https://openalex.org/W1585241115","https://openalex.org/W2157852352"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,35,68,87,148,158,185,190,195],"sparse":[3,69],"hidden":[4],"Markov":[5],"model":[6,57,97],"(HMM)-based":[7],"single-channel":[8],"speech":[9,15,31,40,102,111,116,141,160,168,180,197],"enhancement":[10,181],"method":[11,212],"that":[12,74,177],"models":[13,25],"the":[14,30,39,56,78,84,96,113,123,126,139,153,166,178,210],"and":[16,32,38,41,80,110,117,132,142,172,194],"noise":[17,22,33,42,109,118,143,149,154,201,217],"gains":[18,43],"accurately":[19],"in":[20,34,67,77,199],"non-stationary":[21,136,216],"environments.":[23],"Autoregressive":[24],"are":[26,44],"employed":[27],"to":[28,95,121,151,164],"describe":[29],"unified":[36],"framework":[37],"modeled":[45,140],"as":[46],"random":[47],"processes":[48],"with":[49,61],"memory.":[50],"The":[51,170,207],"likelihood":[52],"criterion":[53],"for":[54,215],"finding":[55],"parameters":[58],"is":[59,162,213],"augmented":[60],"an":[62],"lp":[63],"regularization":[64],"term":[65],"resulting":[66],"autoregressive":[70],"HMM":[71,91],"(SARHMM)":[72],"system":[73],"encourages":[75],"sparsity":[76,114],"speech-":[79],"noise-":[81],"modeling.":[82],"In":[83],"SARHMM":[85],"only":[86],"small":[88],"number":[89],"of":[90,98,115,125,128,135,209],"states":[92],"contribute":[93],"significantly":[94],"each":[99],"particular":[100],"observed":[101],"segment.":[103],"As":[104],"it":[105],"eliminates":[106],"ambiguity":[107],"between":[108],"spectra,":[112],"modeling":[119],"helps":[120],"improve":[122],"tracking":[124],"changes":[127],"both":[129],"spectral":[130],"shapes":[131],"power":[133,155],"levels":[134],"noise.":[137],"Using":[138],"SARHMMs,":[144],"we":[145],"first":[146],"construct":[147],"estimator":[150,161],"estimate":[152],"spectrum.":[156],"Then,":[157],"Bayesian":[159],"derived":[163],"obtain":[165],"enhanced":[167],"signal.":[169],"subjective":[171],"objective":[173],"test":[174],"results":[175],"indicate":[176],"proposed":[179],"scheme":[182],"can":[183],"achieve":[184],"larger":[186],"segmental":[187],"SNR":[188],"improvement,":[189],"lower":[191],"log-spectral":[192],"distortion":[193],"better":[196],"quality":[198],"stationary":[200],"conditions":[202,218],"than":[203],"state-of-the-art":[204],"reference":[205],"methods.":[206],"advantage":[208],"new":[211],"largest":[214],".":[219]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}