{"id":"https://openalex.org/W2924693853","doi":"https://doi.org/10.1109/icaiic.2019.8668841","title":"Multi-Channel Audio Source Separation Using Azimuth-Frequency Analysis and Convolutional Neural Network","display_name":"Multi-Channel Audio Source Separation Using Azimuth-Frequency Analysis and Convolutional Neural Network","publication_year":2019,"publication_date":"2019-02-01","ids":{"openalex":"https://openalex.org/W2924693853","doi":"https://doi.org/10.1109/icaiic.2019.8668841","mag":"2924693853"},"language":"en","primary_location":{"id":"doi:10.1109/icaiic.2019.8668841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic.2019.8668841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","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/A5030648047","display_name":"Jung Min Moon","orcid":null},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jung Min Moon","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology (GIST), Gwangju, Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology (GIST), Gwangju, Korea","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109992735","display_name":"Chan Jun Chun","orcid":null},"institutions":[{"id":"https://openalex.org/I3019177047","display_name":"Korea Institute of Civil Engineering and Building Technology","ror":"https://ror.org/035enhp47","country_code":"KR","type":"government","lineage":["https://openalex.org/I2801339556","https://openalex.org/I3019177047","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chan Jun Chun","raw_affiliation_strings":["Construction Automation Research Center, Korea Institute of Civil Engineering and Building Technology (KICT), Goyang, Korea"],"affiliations":[{"raw_affiliation_string":"Construction Automation Research Center, Korea Institute of Civil Engineering and Building Technology (KICT), Goyang, Korea","institution_ids":["https://openalex.org/I3019177047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101735899","display_name":"Jun Ho Kim","orcid":"https://orcid.org/0000-0002-3672-0136"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jun Ho Kim","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology (GIST), Gwangju, Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology (GIST), Gwangju, Korea","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085604883","display_name":"Hong Kook Kim","orcid":"https://orcid.org/0000-0002-0105-6693"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong Kook Kim","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology (GIST), Gwangju, Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology (GIST), Gwangju, Korea","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100379957","display_name":"Tae Woo Kim","orcid":"https://orcid.org/0000-0002-9255-4355"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tae Woo Kim","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology (GIST), Gwangju, Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology (GIST), Gwangju, Korea","institution_ids":["https://openalex.org/I39534123"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5030648047"],"corresponding_institution_ids":["https://openalex.org/I39534123"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.01920952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"500","last_page":"503"},"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":0.998199999332428,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9959999918937683,"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/computer-science","display_name":"Computer science","score":0.7811204195022583},{"id":"https://openalex.org/keywords/azimuth","display_name":"Azimuth","score":0.7102869153022766},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.7033172845840454},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5528770685195923},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5137125253677368},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5001266002655029},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4335938096046448},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4317470192909241},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41876912117004395},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.4142167568206787},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40946200489997864},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.21885615587234497},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.1565842628479004},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13696759939193726},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11825782060623169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7811204195022583},{"id":"https://openalex.org/C159737794","wikidata":"https://www.wikidata.org/wiki/Q124274","display_name":"Azimuth","level":2,"score":0.7102869153022766},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.7033172845840454},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5528770685195923},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5137125253677368},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5001266002655029},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4335938096046448},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4317470192909241},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41876912117004395},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.4142167568206787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40946200489997864},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.21885615587234497},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.1565842628479004},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13696759939193726},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11825782060623169},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icaiic.2019.8668841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic.2019.8668841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","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":24,"referenced_works":["https://openalex.org/W1514524123","https://openalex.org/W1558630118","https://openalex.org/W1588397041","https://openalex.org/W1665214252","https://openalex.org/W1680797894","https://openalex.org/W1898061650","https://openalex.org/W2089473323","https://openalex.org/W2093225945","https://openalex.org/W2095705004","https://openalex.org/W2127851351","https://openalex.org/W2133319764","https://openalex.org/W2141125852","https://openalex.org/W2158698691","https://openalex.org/W2168010845","https://openalex.org/W2196753680","https://openalex.org/W2474177164","https://openalex.org/W2743672024","https://openalex.org/W2962785840","https://openalex.org/W6633463146","https://openalex.org/W6637242042","https://openalex.org/W6674330103","https://openalex.org/W6679852000","https://openalex.org/W6687624220","https://openalex.org/W6742827142"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W2136112003","https://openalex.org/W3132176577","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W2114974607","https://openalex.org/W3112881379","https://openalex.org/W2002298560","https://openalex.org/W2019256813"],"abstract_inverted_index":{"Since":[0],"MPEG-H":[1],"supports":[2],"not":[3],"only":[4,193],"channel-based":[5,23,45],"but":[6],"also":[7],"object-based":[8,25,48],"audio":[9,46,96,103,110,123],"content,":[10],"there":[11],"is":[12,52,105,145],"a":[13,16,69,80,108,121,134,180,190],"need":[14],"for":[15,43,133],"sound":[17,30,37],"source":[18,31,38],"separation":[19,32,39,150,177],"technique":[20],"that":[21,192],"converts":[22],"to":[24,47,54,71,119],"audio.":[26,49],"Among":[27],"the":[28,56,73,113,125,130,142,168],"various":[29],"techniques,":[33],"azimuth-frequency":[34],"(AF)":[35],"based":[36,78],"has":[40],"been":[41],"proposed":[42,169],"converting":[44],"Unfortunately,":[50],"it":[51],"difficult":[53],"set":[55,104],"optimal":[57,74],"azimuth":[58,75,126],"and":[59,76,91,127,152,163,176],"width":[60,77,128],"using":[61,112],"this":[62,65],"technique.":[63],"In":[64],"paper,":[66],"we":[67],"propose":[68],"method":[70,170,191],"determine":[72],"on":[79,88],"convolutional":[81],"neural":[82],"network":[83],"(CNN)":[84],"classifier.":[85,115],"First,":[86],"depending":[87],"numerous":[89],"azimuths":[90],"widths,":[92],"different":[93],"sets":[94],"of":[95,141,149],"signals":[97],"are":[98,137],"separated.":[99],"After":[100],"that,":[101],"each":[102],"categorized":[106],"into":[107],"specific":[109],"class":[111,136],"CNN":[114,143],"Then,":[116],"in":[117,147],"order":[118],"separate":[120],"desired":[122],"signal,":[124],"with":[129],"highest":[131],"similarity":[132],"given":[135],"selected.":[138],"The":[139],"performance":[140],"classifier":[144],"evaluated":[146],"terms":[148],"accuracy":[151,178],"objective":[153],"measures":[154],"such":[155],"as":[156,187,189],"signal-to-distortion":[157],"ratio":[158,161,165],"(SDR),":[159],"signal-to-interference":[160],"(SIR),":[162],"signal-to-artifacts":[164],"(SAR).":[166],"Consequently,":[167],"provides":[171],"higher":[172],"SDR,":[173],"SAR,":[174],"SIR,":[175],"than":[179],"minimum":[181],"variance":[182],"distortionless":[183],"response":[184],"(MVDR)":[185],"beamformer":[186],"well":[188],"uses":[194],"AF":[195],"analysis.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}