{"id":"https://openalex.org/W2136883355","doi":"https://doi.org/10.1109/tasl.2008.2004306","title":"Speech Dereverberation Based on Maximum-Likelihood Estimation With Time-Varying Gaussian Source Model","display_name":"Speech Dereverberation Based on Maximum-Likelihood Estimation With Time-Varying Gaussian Source Model","publication_year":2008,"publication_date":"2008-10-22","ids":{"openalex":"https://openalex.org/W2136883355","doi":"https://doi.org/10.1109/tasl.2008.2004306","mag":"2136883355"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2008.2004306","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2008.2004306","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 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/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Labs., NTT Corp., Kyoto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Labs., NTT Corp., Kyoto","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","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":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","[School of Electrical & Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"[School of Electrical & Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA]","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111931228","display_name":"Masato Miyoshi","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Miyoshi","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0096,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.91606081,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"16","issue":"8","first_page":"1512","last_page":"1527"},"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":0.9983000159263611,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.718222975730896},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.6986277103424072},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6926419734954834},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5228567123413086},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4977274239063263},{"id":"https://openalex.org/keywords/autocorrelation","display_name":"Autocorrelation","score":0.48880383372306824},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.45461970567703247},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2616429328918457},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18602648377418518},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09311583638191223},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07769399881362915}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.718222975730896},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.6986277103424072},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6926419734954834},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5228567123413086},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4977274239063263},{"id":"https://openalex.org/C5297727","wikidata":"https://www.wikidata.org/wiki/Q786970","display_name":"Autocorrelation","level":2,"score":0.48880383372306824},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.45461970567703247},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2616429328918457},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18602648377418518},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09311583638191223},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07769399881362915},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/tasl.2008.2004306","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2008.2004306","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W172015143","https://openalex.org/W1560013842","https://openalex.org/W1808196926","https://openalex.org/W1898225171","https://openalex.org/W1963866889","https://openalex.org/W1965199331","https://openalex.org/W2045043668","https://openalex.org/W2049633694","https://openalex.org/W2083212479","https://openalex.org/W2100432131","https://openalex.org/W2102072896","https://openalex.org/W2103034511","https://openalex.org/W2105083236","https://openalex.org/W2105592556","https://openalex.org/W2109419971","https://openalex.org/W2110913111","https://openalex.org/W2111512576","https://openalex.org/W2112197391","https://openalex.org/W2116157288","https://openalex.org/W2130432819","https://openalex.org/W2130640611","https://openalex.org/W2131748306","https://openalex.org/W2132214945","https://openalex.org/W2134958708","https://openalex.org/W2139302694","https://openalex.org/W2139361972","https://openalex.org/W2140571699","https://openalex.org/W2140693991","https://openalex.org/W2142117481","https://openalex.org/W2152949589","https://openalex.org/W2168227362","https://openalex.org/W3105118415","https://openalex.org/W3129711340","https://openalex.org/W4230562743","https://openalex.org/W4247773827","https://openalex.org/W4299681030","https://openalex.org/W6606966975","https://openalex.org/W6676542974","https://openalex.org/W6679561100","https://openalex.org/W6680165021","https://openalex.org/W6684452406","https://openalex.org/W6758139422"],"related_works":["https://openalex.org/W2293149949","https://openalex.org/W2026099691","https://openalex.org/W4284672201","https://openalex.org/W2377486419","https://openalex.org/W2036727454","https://openalex.org/W2378628076","https://openalex.org/W1485597629","https://openalex.org/W4205914160","https://openalex.org/W2052532834","https://openalex.org/W2296422491"],"abstract_inverted_index":{"<para":[0],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[1],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[2],"Distant":[3],"acquisition":[4],"of":[5,80,90,98,162,166,169,197,249,259],"acoustic":[6,18],"signals":[7,252],"in":[8,20,26,37,114,215,257],"an":[9],"enclosed":[10],"space":[11],"often":[12],"produces":[13],"reverberant":[14,250],"components":[15],"due":[16],"to":[17,236],"reflections":[19],"the":[21,30,75,85,91,99,116,123,209,216,227,232,239,247,260],"room.":[22],"Speech":[23],"dereverberation":[24,54,97,148,187],"is":[25,32,68,102,119,129,171],"general":[27,139],"desirable":[28],"when":[29],"signal":[31,101,118,125,272],"acquired":[33],"through":[34],"distant":[35],"microphones":[36],"such":[38],"applications":[39],"as":[40,70,104],"hands-free":[41],"speech":[42,53,60,82,92,100,117,177,223,241,251,271],"recognition,":[43],"teleconferencing,":[44],"and":[45,87,145,211,225,263],"meeting":[46],"recording.":[47],"This":[48],"paper":[49],"proposes":[50],"a":[51,58,71,105,138,158,163,174,181,194,202,269,274],"new":[52],"approach":[55],"based":[56,109,142,150,189],"on":[57,110,143,151,190],"statistical":[59],"model.":[61],"A":[62],"time-varying":[63],"Gaussian":[64],"source":[65,153,159,217],"model":[66,72,160,192],"(TVGSM)":[67],"introduced":[69],"that":[73,128,200,207,226,246],"represents":[74],"dynamic":[76],"short":[77,175,270],"time":[78,86,176,210],"characteristics":[79,213],"nonreverberant":[81,133],"segments,":[83],"including":[84],"frequency":[88,212],"structures":[89],"spectrum.":[93],"With":[94],"this":[95,191],"model,":[96],"formulated":[103],"maximum-likelihood":[106],"(ML)":[107],"problem":[108],"multichannel":[111],"linear":[112],"prediction,":[113],"which":[115,170],"recovered":[120],"by":[121,173,180,231],"transforming":[122],"observed":[124],"into":[126],"one":[127],"probabilistically":[130],"more":[131],"like":[132],"speech.":[134],"We":[135,204,243],"first":[136],"present":[137,157],"ML":[140],"solution":[141],"TVGSM,":[144],"derive":[146],"several":[147],"algorithms":[149],"various":[152],"models.":[154],"Specifically,":[155],"we":[156],"consisting":[161],"finite":[164,195],"number":[165],"states,":[167],"each":[168],"manifested":[172],"spectrum,":[178],"defined":[179],"corresponding":[182],"autocorrelation":[183],"(AC)":[184],"vector.":[185],"The":[186],"algorithm":[188],"involves":[193],"collection":[196],"spectral":[198,261],"patterns":[199],"form":[201],"codebook.":[203,276],"confirm":[205,245],"experimentally":[206],"both":[208],"represented":[214,230],"models":[218],"are":[219],"very":[220],"important":[221],"for":[222],"dereverberation,":[224],"prior":[228],"knowledge":[229],"codebook":[233],"allows":[234],"us":[235],"further":[237],"improve":[238],"dereverberated":[240],"quality.":[242],"also":[244],"quality":[248],"can":[253],"be":[254],"greatly":[255],"improved":[256],"terms":[258],"shape":[262],"energy":[264],"time-pattern":[265],"distortions":[266],"from":[267],"simply":[268],"using":[273],"speaker-independent":[275],"</para>":[277]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}