{"id":"https://openalex.org/W2113545518","doi":"https://doi.org/10.1109/icassp.2006.1659982","title":"HMM-Based Speech Enhancement using Explicit Gain Modeling","display_name":"HMM-Based Speech Enhancement using Explicit Gain Modeling","publication_year":2006,"publication_date":"2006-08-02","ids":{"openalex":"https://openalex.org/W2113545518","doi":"https://doi.org/10.1109/icassp.2006.1659982","mag":"2113545518"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2006.1659982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1659982","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/A5054610700","display_name":"David Zhao","orcid":"https://orcid.org/0000-0002-3857-5016"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"D.Y. Zhao","raw_affiliation_strings":["School of Electrical Engineering, Royal Institute of Technology, Stockholm, Sweden","Sch. of Electr. Eng., R. Inst. of Technol., Stockholm"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Sch. of Electr. Eng., R. Inst. of Technol., Stockholm","institution_ids":["https://openalex.org/I86987016"]}]},{"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/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"W.B. Kleijn","raw_affiliation_strings":["School of Electrical Engineering, Royal Institute of Technology, Stockholm, Sweden","Sch. of Electr. Eng., R. Inst. of Technol., Stockholm"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Sch. of Electr. Eng., R. Inst. of Technol., Stockholm","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5054610700"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16395279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"161"},"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":0.9969000220298767,"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/T13289","display_name":"Infant Health and Development","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8100987672805786},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6840384006500244},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6747716665267944},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6709641814231873},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5956763029098511},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.505542516708374},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.43456465005874634},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4207429885864258},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33865657448768616},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3243352770805359},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.21356052160263062},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18233251571655273}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8100987672805786},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6840384006500244},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6747716665267944},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6709641814231873},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5956763029098511},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.505542516708374},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.43456465005874634},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4207429885864258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33865657448768616},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3243352770805359},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.21356052160263062},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18233251571655273},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/icassp.2006.1659982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1659982","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1546107096","https://openalex.org/W1572919226","https://openalex.org/W2016254085","https://openalex.org/W2049633694","https://openalex.org/W2115916404","https://openalex.org/W2157885315","https://openalex.org/W2158336491","https://openalex.org/W2161182969","https://openalex.org/W2167090878","https://openalex.org/W2308181013","https://openalex.org/W6632688141","https://openalex.org/W7048738093"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W3110551121","https://openalex.org/W2131486661","https://openalex.org/W2089240210","https://openalex.org/W2161396743","https://openalex.org/W2386453889","https://openalex.org/W3134790285","https://openalex.org/W1989451948","https://openalex.org/W1937661627","https://openalex.org/W2345063900"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2],"hidden":[3],"Markov":[4],"model":[5],"(HMM)":[6],"based":[7],"speech":[8,15,32,39],"enhancement":[9,90],"method":[10],"using":[11,78],"explicit":[12,107],"modeling":[13],"of":[14,38,50,61,65,71,87,106],"and":[16,97],"noise":[17,54,113],"gains.":[18],"The":[19,31,53,68,85,100],"gains":[20],"are":[21,75],"considered":[22],"to":[23,43,57],"be":[24],"stochastic":[25],"variables":[26],"in":[27,45],"an":[28],"HMM":[29],"framework.":[30],"gain":[33,55,73,108],"models":[34,74],"the":[35,59,62,72,79,88,104],"energy":[36,64],"variations":[37],"phones,":[40],"typically":[41],"due":[42],"differences":[44],"pronunciation":[46],"and/or":[47],"different":[48],"vocalizations":[49],"individual":[51],"speakers.":[52],"helps":[56],"improve":[58],"tracking":[60],"time-varying":[63,69],"non-stationary":[66,112],"noise.":[67],"parameters":[70],"estimated":[76],"on-line":[77],"recursive":[80],"expectation":[81],"maximization":[82],"(EM)":[83],"algorithm.":[84],"performance":[86],"proposed":[89],"system":[91],"is":[92],"evaluated":[93],"through":[94],"both":[95],"objective":[96],"subjective":[98],"tests.":[99],"experimental":[101],"results":[102],"confirm":[103],"advantage":[105],"modeling,":[109],"particularly":[110],"for":[111],"sources":[114]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
