{"id":"https://openalex.org/W2921133836","doi":"https://doi.org/10.23919/apsipa.2018.8659613","title":"Effective Sound Source Separation Using Single Voice Activity Segments for Binaural Sound","display_name":"Effective Sound Source Separation Using Single Voice Activity Segments for Binaural Sound","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2921133836","doi":"https://doi.org/10.23919/apsipa.2018.8659613","mag":"2921133836"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659613","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659613","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5102846620","display_name":"Wataru Noguchi","orcid":"https://orcid.org/0000-0002-0250-4128"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"Osaka University","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Wataru Noguchi","raw_affiliation_strings":["Osaka University, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001195104","display_name":"Arata Kawamura","orcid":"https://orcid.org/0000-0002-5430-7433"},"institutions":[{"id":"https://openalex.org/I168356945","display_name":"Kyoto Sangyo University","ror":"https://ror.org/05t70xh16","country_code":"JP","type":"education","lineage":["https://openalex.org/I168356945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Arata Kawamura","raw_affiliation_strings":["Kyoto Sangyo University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto Sangyo University, Kyoto, Japan","institution_ids":["https://openalex.org/I168356945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112435538","display_name":"Youji Iiguni","orcid":"https://orcid.org/0009-0000-9888-1800"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"Osaka University","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Youji Iiguni","raw_affiliation_strings":["Osaka University, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102846620"],"corresponding_institution_ids":["https://openalex.org/I98285908"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20168402,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"279","last_page":"284"},"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":0.9990000128746033,"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":0.9987000226974487,"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/binaural-recording","display_name":"Binaural recording","score":0.9035451412200928},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.7246512770652771},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.6602323055267334},{"id":"https://openalex.org/keywords/sound-localization","display_name":"Sound localization","score":0.6450330018997192},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6120438575744629},{"id":"https://openalex.org/keywords/precedence-effect","display_name":"Precedence effect","score":0.5541837215423584},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.536102294921875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5321074724197388},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.41034823656082153},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12141704559326172}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.9035451412200928},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.7246512770652771},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.6602323055267334},{"id":"https://openalex.org/C68236139","wikidata":"https://www.wikidata.org/wiki/Q765652","display_name":"Sound localization","level":2,"score":0.6450330018997192},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6120438575744629},{"id":"https://openalex.org/C82600853","wikidata":"https://www.wikidata.org/wiki/Q2115271","display_name":"Precedence effect","level":3,"score":0.5541837215423584},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.536102294921875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5321074724197388},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.41034823656082153},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12141704559326172}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659613","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659613","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1548802052","https://openalex.org/W2031583051","https://openalex.org/W2089594462","https://openalex.org/W4241874243","https://openalex.org/W4244494905","https://openalex.org/W4247773827"],"related_works":["https://openalex.org/W2539207221","https://openalex.org/W2003665656","https://openalex.org/W1482972934","https://openalex.org/W2242743481","https://openalex.org/W2622611424","https://openalex.org/W2902925131","https://openalex.org/W2624483394","https://openalex.org/W2317500761","https://openalex.org/W2809056180","https://openalex.org/W4372260199"],"abstract_inverted_index":{"Binaural":[0,23],"sound":[1,9,24,46,68,84,102,119],"is":[2,25,62,132],"well":[3],"known":[4],"as":[5],"a":[6,12,42,66],"three":[7],"dimensional":[8],"which":[10,78],"achieves":[11],"virtual":[13],"reality":[14,20],"of":[15,21,128,137],"sound,":[16],"or":[17],"an":[18,49],"augmented":[19],"sound.":[22],"characterized":[26],"by":[27,64,104],"ILD":[28,56,90,113,138],"(Interaural":[29,34],"Level":[30],"Difference)":[31],"and":[32,57,91,114,139],"IPD":[33,92,115,140],"Phase":[35],"Difference).":[36],"In":[37],"this":[38],"paper,":[39],"we":[40,109],"propose":[41],"method":[43,61,71,88,131],"to":[44,121],"separate":[45],"sources":[47,103,120],"from":[48,93,134],"observed":[50],"mixture":[51],"signal,":[52],"without":[53],"losing":[54],"respective":[55],"IPD.":[58],"The":[59,86,126],"proposed":[60,87,130],"established":[63],"improving":[65],"conventional":[67,107],"source":[69],"separation":[70],"based":[72],"on":[73,116],"single":[74,83,95],"voice":[75,96],"activity":[76,97],"detection":[77],"detects":[79],"segments":[80],"including":[81],"only":[82],"source.":[85],"estimates":[89],"the":[94,101,106,111,117,123,129],"segments.":[98],"After":[99],"separating":[100],"using":[105],"method,":[108],"give":[110],"estimated":[112],"separated":[118],"refine":[122],"binaural":[124,142],"characteristics.":[125],"effectiveness":[127],"clarified":[133],"estimation":[135],"results":[136],"for":[141],"sounds.":[143]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}