{"id":"https://openalex.org/W3215319506","doi":"https://doi.org/10.1109/isocc53507.2021.9613899","title":"Components Analysis on Audio Signal Mixtures","display_name":"Components Analysis on Audio Signal Mixtures","publication_year":2021,"publication_date":"2021-10-06","ids":{"openalex":"https://openalex.org/W3215319506","doi":"https://doi.org/10.1109/isocc53507.2021.9613899","mag":"3215319506"},"language":"en","primary_location":{"id":"doi:10.1109/isocc53507.2021.9613899","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isocc53507.2021.9613899","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 18th International SoC Design Conference (ISOCC)","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/A5100673637","display_name":"Chanhee Lee","orcid":"https://orcid.org/0000-0002-4824-5934"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Chanhee Lee","raw_affiliation_strings":["Department of Electrical Engineering, Postech, Pohang, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Postech, Pohang, Republic of Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102778093","display_name":"Sangho Yoon","orcid":"https://orcid.org/0000-0002-7479-5876"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sangho Yoon","raw_affiliation_strings":["Department of Electrical Engineering, Postech, Pohang, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Postech, Pohang, Republic of Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044543389","display_name":"Seokhyeong Kang","orcid":"https://orcid.org/0000-0003-3015-1806"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seokhyeong Kang","raw_affiliation_strings":["Department of Electrical Engineering, Postech, Pohang, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Postech, Pohang, Republic of Korea","institution_ids":["https://openalex.org/I123900574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100673637"],"corresponding_institution_ids":["https://openalex.org/I123900574"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1582397,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"363","last_page":"364"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9843999743461609,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7962417006492615},{"id":"https://openalex.org/keywords/sliding-window-protocol","display_name":"Sliding window protocol","score":0.7559365630149841},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6339048147201538},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5864242911338806},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5838332772254944},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5591113567352295},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5511965155601501},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5373887419700623},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5051928162574768},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4741458594799042},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.462084025144577},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4563806653022766},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4118542969226837},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.18527698516845703},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07471221685409546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7962417006492615},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.7559365630149841},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6339048147201538},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5864242911338806},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5838332772254944},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5591113567352295},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5511965155601501},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5373887419700623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5051928162574768},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4741458594799042},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.462084025144577},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4563806653022766},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4118542969226837},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.18527698516845703},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07471221685409546},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/isocc53507.2021.9613899","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isocc53507.2021.9613899","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 18th International SoC Design Conference (ISOCC)","raw_type":"proceedings-article"},{"id":"pmh:oai:oasis.postech.ac.kr:2014.oak/109685","is_oa":false,"landing_page_url":"https://oasis.postech.ac.kr/handle/2014.oak/109685","pdf_url":null,"source":{"id":"https://openalex.org/S4306401965","display_name":"Open Access System for Information Sharing (Pohang University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123900574","host_organization_name":"Pohang University of Science and Technology","host_organization_lineage":["https://openalex.org/I123900574"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2052666245","https://openalex.org/W2621347402","https://openalex.org/W2967774691","https://openalex.org/W2972247414","https://openalex.org/W2972425456","https://openalex.org/W3101786243"],"related_works":["https://openalex.org/W3014558862","https://openalex.org/W2381286523","https://openalex.org/W2289868279","https://openalex.org/W4315836293","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W2970176078","https://openalex.org/W2098934641","https://openalex.org/W1975359510","https://openalex.org/W2088690926"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,11,17,28,39,51,56,68,73,77,85,101,119],"novel":[4],"multi-label":[5,90,123],"noise":[6,24],"classification":[7,25,91,124,158],"algorithm":[8],"that":[9,88,103,111],"uses":[10,27],"convolutional":[12,29],"neural":[13,30,53,58],"network":[14,54,59],"and":[15,169],"applies":[16,89,118],"sliding":[18,120],"window":[19,121],"for":[20,162,166,172],"classification.":[21],"The":[22,134,157],"existing":[23],"method":[26,87],"network,":[31],"in":[32,92,130,153],"which":[33],"the":[34,44,107,112,116,127,138,142,146],"input":[35,143],"audio":[36,98,108,173],"must":[37],"have":[38,67],"fixed":[40],"time":[41,94,132,155],"length.":[42],"On":[43],"other":[45],"hand,":[46],"time-variant":[47],"networks":[48],"such":[49,81],"as":[50],"time-delay":[52],"or":[55],"recurrent":[57],"can":[60],"use":[61],"any":[62],"length":[63],"of":[64,70,141,149,174],"time,":[65],"but":[66],"limitation":[69],"classifying":[71],"only":[72],"single":[74],"label":[75,152],"within":[76],"short":[78],"time.":[79],"Considering":[80],"shortcomings,":[82],"we":[83],"propose":[84],"windowing":[86],"overlapping":[93],"windows.":[95],"For":[96],"an":[97],"stream":[99,109],"with":[100,122],"duration":[102],"is":[104],"longer":[105],"than":[106],"inputs":[110],"model":[113,117,135],"trained":[114],"with,":[115],"to":[125],"detect":[126],"corresponding":[128],"classes":[129,140],"each":[131,150,154],"sequence.":[133,156],"then":[136],"identifies":[137],"final":[139],"by":[144],"considering":[145],"confidence":[147],"scores":[148],"output":[151],"accuracy":[159],"was":[160],"94.17%":[161],"single-label":[163],"audio,":[164,168],"85.21%":[165],"two-class":[167],"averaged":[170],"86.39%":[171],"various":[175],"durations.":[176]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
