{"id":"https://openalex.org/W2121325018","doi":"https://doi.org/10.1109/icassp.2009.4959539","title":"Real-time speech enhancement in noisy reverberant multi-talker environments based on a location-independent room acoustics model","display_name":"Real-time speech enhancement in noisy reverberant multi-talker environments based on a location-independent room acoustics model","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2121325018","doi":"https://doi.org/10.1109/icassp.2009.4959539","mag":"2121325018"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4959539","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4959539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, 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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","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"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Biing-Hwang Juang","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","School of ECE, Georgia Institute of Technology, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"School of ECE, Georgia Institute of Technology, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"137","last_page":"140"},"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":0.9994000196456909,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9972000122070312,"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/reverberation","display_name":"Reverberation","score":0.8513739109039307},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7657971382141113},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7302252054214478},{"id":"https://openalex.org/keywords/room-acoustics","display_name":"Room acoustics","score":0.6608763337135315},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6591919660568237},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.6343833804130554},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5867922306060791},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.5412999391555786},{"id":"https://openalex.org/keywords/architectural-acoustics","display_name":"Architectural acoustics","score":0.5352727770805359},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.5166957378387451},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4961293637752533},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.47988760471343994},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46135732531547546},{"id":"https://openalex.org/keywords/impulse","display_name":"Impulse (physics)","score":0.4592774510383606},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4499269425868988},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.41088372468948364},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.28627777099609375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15315821766853333},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13720938563346863},{"id":"https://openalex.org/keywords/amplifier","display_name":"Amplifier","score":0.13496387004852295},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13267391920089722},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12702250480651855},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.11214357614517212},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08055239915847778}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.8513739109039307},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7657971382141113},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7302252054214478},{"id":"https://openalex.org/C178432105","wikidata":"https://www.wikidata.org/wiki/Q2182127","display_name":"Room acoustics","level":3,"score":0.6608763337135315},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6591919660568237},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.6343833804130554},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5867922306060791},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.5412999391555786},{"id":"https://openalex.org/C2776009117","wikidata":"https://www.wikidata.org/wiki/Q2305951","display_name":"Architectural acoustics","level":3,"score":0.5352727770805359},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.5166957378387451},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4961293637752533},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.47988760471343994},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46135732531547546},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.4592774510383606},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4499269425868988},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.41088372468948364},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.28627777099609375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15315821766853333},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13720938563346863},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.13496387004852295},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13267391920089722},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12702250480651855},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.11214357614517212},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08055239915847778},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"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/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.2009.4959539","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4959539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","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":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1996981692","https://openalex.org/W2045043668","https://openalex.org/W2103564015","https://openalex.org/W2110913111","https://openalex.org/W2130640611","https://openalex.org/W2132214945","https://openalex.org/W2140571699","https://openalex.org/W6675537059"],"related_works":["https://openalex.org/W1982530174","https://openalex.org/W1984453941","https://openalex.org/W4382136792","https://openalex.org/W4213090638","https://openalex.org/W2355680380","https://openalex.org/W49085616","https://openalex.org/W2089979310","https://openalex.org/W2371971575","https://openalex.org/W1540213843","https://openalex.org/W3189630"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,27,75,82,103,112,123,148,156],"new":[4],"real-time":[5,134],"speech":[6,23,135],"enhancement":[7,136],"method":[8,83,143],"that":[9],"reduces":[10],"signal":[11],"distortion":[12],"caused":[13],"by":[14,26],"stationary":[15],"noise":[16,127],"and":[17,80],"late":[18,46,89],"reflections":[19,47,90],"of":[20,44,88,99,115,140],"reverberation":[21],"in":[22,48,67,108,155],"signals":[24],"captured":[25],"single":[28],"distant":[29],"microphone":[30,61],"under":[31],"multi-talker":[32],"conditions.":[33],"A":[34],"major":[35],"problem":[36],"here":[37],"is":[38,144],"how":[39],"to":[40,59],"estimate":[41],"the":[42,45,52,60,86,100,119,141],"energy":[43,87],"real":[49],"time":[50],"when":[51],"room":[53,77,104],"impulse":[54],"responses":[55],"from":[56,111],"individual":[57],"talkers":[58,154],"are":[62,152],"not":[63],"given":[64],"or":[65],"fixed":[66,107],"advance.":[68],"To":[69],"solve":[70],"this":[71,93,96],"problem,":[72],"we":[73,130],"introduce":[74],"probabilistic":[76],"acoustics":[78],"model,":[79],"provide":[81],"for":[84,102,147],"estimating":[85],"based":[91],"on":[92],"model.":[94],"In":[95],"method,":[97],"parameters":[98],"model":[101],"can":[105],"be":[106],"advance":[109],"only":[110],"few":[113],"seconds":[114],"observation.":[116],"By":[117],"incorporating":[118],"proposed":[120,142],"approach":[121],"into":[122],"conventional":[124],"frequency":[125],"domain":[126],"reduction":[128],"scheme,":[129],"realize":[131],"an":[132],"integrated":[133],"framework.":[137],"The":[138],"effectiveness":[139],"confirmed":[145],"experimentally":[146],"case":[149],"where":[150],"there":[151],"two":[153],"room.":[157]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}