{"id":"https://openalex.org/W2397539537","doi":"https://doi.org/10.1109/icassp.2016.7471662","title":"Integrated approach of feature extraction and sound source enhancement based on maximization of mutual information","display_name":"Integrated approach of feature extraction and sound source enhancement based on maximization of mutual information","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2397539537","doi":"https://doi.org/10.1109/icassp.2016.7471662","mag":"2397539537"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7471662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471662","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/A5101503856","display_name":"Yuma Koizumi","orcid":"https://orcid.org/0000-0003-3645-6213"},"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":"Yuma Koizumi","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Tokyo, 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":"Kenta Niwa","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069841141","display_name":"Yusuke Hioka","orcid":"https://orcid.org/0000-0003-3380-9677"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Yusuke Hioka","raw_affiliation_strings":["Department of Mechanical Engineering, University of Auckland, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of Auckland, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109046289","display_name":"Kazunori Kobayashi","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":"Kazunori Kobayashi","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037159539","display_name":"Hitoshi Ohmuro","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":"Hitoshi Ohmuro","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"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":0.70735855,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"73","issue":null,"first_page":"186","last_page":"190"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9923999905586243,"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/wiener-filter","display_name":"Wiener filter","score":0.7892073392868042},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.6981719136238098},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6595488786697388},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5918423533439636},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5897294878959656},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5572463274002075},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.5315403938293457},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4965739846229553},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4914475679397583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48673510551452637},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4703369736671448},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.4620482325553894},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.43081721663475037},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.42526185512542725},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.41390255093574524},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37483227252960205},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2707456350326538},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2634108066558838},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24179697036743164},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.18506720662117004},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16731932759284973},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06039348244667053}],"concepts":[{"id":"https://openalex.org/C18537770","wikidata":"https://www.wikidata.org/wiki/Q25523","display_name":"Wiener filter","level":2,"score":0.7892073392868042},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6981719136238098},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6595488786697388},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5918423533439636},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5897294878959656},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5572463274002075},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.5315403938293457},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4965739846229553},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4914475679397583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48673510551452637},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4703369736671448},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.4620482325553894},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.43081721663475037},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.42526185512542725},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.41390255093574524},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37483227252960205},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2707456350326538},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2634108066558838},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24179697036743164},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.18506720662117004},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16731932759284973},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06039348244667053},{"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2016.7471662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471662","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"},{"id":"pmh:oai:researchspace.auckland.ac.nz:2292/29826","is_oa":false,"landing_page_url":"http://hdl.handle.net/2292/29826","pdf_url":null,"source":{"id":"https://openalex.org/S7407055463","display_name":"ResearchSpace (University of Auckland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I154130895","host_organization_name":"University of Auckland","host_organization_lineage":["https://openalex.org/I154130895"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Item"},{"id":"pmh:oai:researchspace.auckland.ac.nz:2292/29827","is_oa":false,"landing_page_url":"https://hdl.handle.net/2292/29827","pdf_url":null,"source":{"id":"https://openalex.org/S7407055463","display_name":"ResearchSpace (University of Auckland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I154130895","host_organization_name":"University of Auckland","host_organization_lineage":["https://openalex.org/I154130895"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1497077389","https://openalex.org/W1543181969","https://openalex.org/W1548802052","https://openalex.org/W1594713653","https://openalex.org/W1663973292","https://openalex.org/W1983989471","https://openalex.org/W1995609724","https://openalex.org/W2005981242","https://openalex.org/W2018205510","https://openalex.org/W2035976437","https://openalex.org/W2066460453","https://openalex.org/W2083686669","https://openalex.org/W2089411275","https://openalex.org/W2089473323","https://openalex.org/W2101022567","https://openalex.org/W2112432964","https://openalex.org/W2130432819","https://openalex.org/W2133407574","https://openalex.org/W2156142001","https://openalex.org/W2159158911","https://openalex.org/W2174952685","https://openalex.org/W2260821657","https://openalex.org/W2332245298","https://openalex.org/W2397034747","https://openalex.org/W2413104649","https://openalex.org/W4205778870","https://openalex.org/W4237347751","https://openalex.org/W4247773827","https://openalex.org/W4249052411","https://openalex.org/W6632275837","https://openalex.org/W6677776580","https://openalex.org/W6680114957","https://openalex.org/W6692839695","https://openalex.org/W6715185404","https://openalex.org/W6987259296"],"related_works":["https://openalex.org/W2466816617","https://openalex.org/W2785601041","https://openalex.org/W2241417046","https://openalex.org/W2908598672","https://openalex.org/W2597403208","https://openalex.org/W4307206503","https://openalex.org/W2393900892","https://openalex.org/W4306760398","https://openalex.org/W2966246521","https://openalex.org/W2254945790"],"abstract_inverted_index":{"We":[0],"investigated":[1],"informative":[2,84],"acoustic":[3,79,85,122],"feature":[4,80],"extraction":[5,94],"based":[6],"on":[7,14,47,133],"dimension":[8,114],"reduction":[9,115,153],"for":[10,26,92,108,113],"collecting":[11],"target":[12,97],"sources":[13],"a":[15,20,48,89,106,110,134],"noisy":[16],"sports":[17,49,136],"field.":[18],"Although":[19],"Wiener":[21,37,74,126],"filter":[22,38,75],"is":[23,31,69,99],"often":[24],"used":[25,70],"sound":[27,159],"source":[28],"enhancement,":[29],"it":[30],"difficult":[32],"to":[33,71],"accurately":[34],"design":[35],"the":[36,45,57,63,73,96,118,125,141,151,157],"by":[39,76,116],"simply":[40],"using":[41,77,130],"spatial":[42],"cues":[43],"because":[44],"noise":[46,152],"field":[50],"(e.g.,":[51],"cheering":[52],"from":[53,56],"spectators)":[54],"arrives":[55],"same":[58],"direction":[59],"as":[60],"that":[61,140],"of":[62,95,149,156],"targeted":[64],"source.":[65],"A":[66],"statistical":[67],"approach":[68],"estimate":[72],"pre-trained":[78],"models.":[81],"However,":[82],"an":[83],"feature,":[86],"which":[87],"provides":[88],"powerful":[90],"clue":[91],"clear":[93],"source,":[98],"unknown.":[100],"For":[101],"this":[102],"study,":[103],"we":[104,138],"developed":[105],"method":[107,143],"optimizing":[109],"projection":[111],"matrix":[112],"maximizing":[117],"mutual":[119],"information":[120],"between":[121],"features":[123],"and":[124,154],"filter.":[127],"Through":[128],"experiments":[129],"two-directional":[131],"microphones":[132],"mock":[135],"field,":[137],"confirmed":[139],"proposed":[142],"outperformed":[144],"previous":[145],"methods":[146],"in":[147],"terms":[148],"both":[150],"quality":[155],"recovered":[158],"sources.":[160]},"counts_by_year":[{"year":2017,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}