{"id":"https://openalex.org/W2400481151","doi":"https://doi.org/10.1109/icassp.2016.7471746","title":"Real-time integration of statistical model-based speech enhancement with unsupervised noise PSD estimation using microphone array","display_name":"Real-time integration of statistical model-based speech enhancement with unsupervised noise PSD estimation using microphone array","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2400481151","doi":"https://doi.org/10.1109/icassp.2016.7471746","mag":"2400481151"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7471746","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5002983657","display_name":"Tomoko Kawase","orcid":"https://orcid.org/0000-0002-0670-3319"},"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":"T. Kawase","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046170826","display_name":"Kenta Niwa","orcid":"https://orcid.org/0000-0002-6911-0238"},"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":"K. Niwa","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109368288","display_name":"Masakiyo Fujimoto","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":"M. Fujimoto","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064258560","display_name":"Noriyoshi Kamado","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":"N. Kamado","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003987248","display_name":"Kayoko Kobayashi","orcid":"https://orcid.org/0000-0003-0459-7900"},"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":"K. Kobayashi","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"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":"S. Araki","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","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":"T. Nakatani","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7658,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70794488,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"i","issue":null,"first_page":"604","last_page":"608"},"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":0.9987999796867371,"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":0.9962999820709229,"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-enhancement","display_name":"Speech enhancement","score":0.8424030542373657},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7020339965820312},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6992002725601196},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6565002202987671},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6551526784896851},{"id":"https://openalex.org/keywords/wiener-filter","display_name":"Wiener filter","score":0.6106412410736084},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.597030758857727},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5814351439476013},{"id":"https://openalex.org/keywords/noise-canceling-microphone","display_name":"Noise-canceling microphone","score":0.5395935773849487},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.5174329876899719},{"id":"https://openalex.org/keywords/noise-power","display_name":"Noise power","score":0.5029022097587585},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.44078493118286133},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4338929057121277},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.36951279640197754},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.27037936449050903},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2692162096500397},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.2254217565059662},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10553613305091858},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10374018549919128},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08718028664588928}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.8424030542373657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7020339965820312},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6992002725601196},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6565002202987671},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6551526784896851},{"id":"https://openalex.org/C18537770","wikidata":"https://www.wikidata.org/wiki/Q25523","display_name":"Wiener filter","level":2,"score":0.6106412410736084},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.597030758857727},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5814351439476013},{"id":"https://openalex.org/C36922181","wikidata":"https://www.wikidata.org/wiki/Q7047650","display_name":"Noise-canceling microphone","level":5,"score":0.5395935773849487},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.5174329876899719},{"id":"https://openalex.org/C203234222","wikidata":"https://www.wikidata.org/wiki/Q2133519","display_name":"Noise power","level":3,"score":0.5029022097587585},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.44078493118286133},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4338929057121277},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.36951279640197754},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.27037936449050903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2692162096500397},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2254217565059662},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10553613305091858},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10374018549919128},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08718028664588928},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7471746","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W35070573","https://openalex.org/W284174822","https://openalex.org/W1506558619","https://openalex.org/W1996837089","https://openalex.org/W2000431869","https://openalex.org/W2005981242","https://openalex.org/W2008806652","https://openalex.org/W2020420943","https://openalex.org/W2066460453","https://openalex.org/W2093225945","https://openalex.org/W2098634964","https://openalex.org/W2099655464","https://openalex.org/W2126597753","https://openalex.org/W2130108834","https://openalex.org/W2139737683","https://openalex.org/W2139780359","https://openalex.org/W2149693148","https://openalex.org/W2159158911","https://openalex.org/W2406153107","https://openalex.org/W2914048585","https://openalex.org/W4249052411","https://openalex.org/W6601391444","https://openalex.org/W6610336499","https://openalex.org/W6680788575","https://openalex.org/W6713359132","https://openalex.org/W6890361730"],"related_works":["https://openalex.org/W1577562165","https://openalex.org/W2109356272","https://openalex.org/W2348931051","https://openalex.org/W2393227939","https://openalex.org/W2385432413","https://openalex.org/W79124394","https://openalex.org/W2389562147","https://openalex.org/W2379497378","https://openalex.org/W2602348424","https://openalex.org/W2062661142"],"abstract_inverted_index":{"We":[0,61],"propose":[1],"a":[2,82],"technique":[3,95],"of":[4,11,45],"multi-channel":[5],"speech":[6,16,34,64],"enhancement":[7,17],"based":[8],"on":[9],"integration":[10],"beamforming":[12],"and":[13,35,69,80],"statistical":[14],"model-based":[15],"to":[18,76],"clearly":[19],"extract":[20],"the":[21,42,46,70,93,98,104],"target":[22],"speech,":[23],"even":[24],"in":[25,67,74],"very":[26],"noisy":[27],"environments.":[28],"Conventional":[29],"microphone":[30,106],"array-based":[31],"techniques":[32],"estimate":[33],"noise":[36,59,71,89],"power":[37],"spectral":[38],"densities":[39],"(PSDs)":[40],"from":[41],"spatial":[43],"cues":[44],"sound":[47],"sources;":[48],"however,":[49],"their":[50],"estimation":[51],"errors":[52],"dramatically":[53],"increase":[54],"when":[55],"there":[56],"are":[57],"many":[58],"sources.":[60],"integrated":[62],"clean":[63],"models":[65,79],"trained":[66],"advance":[68],"PSDs":[72],"estimated":[73],"beamspace":[75],"compose":[77],"observation":[78],"designed":[81],"precise":[83],"Wiener":[84],"filter.":[85],"Experiments":[86],"under":[87],"adverse":[88],"conditions":[90],"showed":[91],"that":[92],"proposed":[94],"significantly":[96],"improved":[97],"signal-to-noise":[99],"ratios":[100],"(SNRs)":[101],"compared":[102],"with":[103],"conventional":[105],"array":[107],"processing":[108],"technique.":[109]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}