{"id":"https://openalex.org/W4392903103","doi":"https://doi.org/10.1109/icassp48485.2024.10447525","title":"Improving Target Sound Extraction with Timestamp Knowledge Distillation","display_name":"Improving Target Sound Extraction with Timestamp Knowledge Distillation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903103","doi":"https://doi.org/10.1109/icassp48485.2024.10447525"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5113361569","display_name":"Dail Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Dail Kim","raw_affiliation_strings":["Hanyang University,Department of Artificial Intelligence,Seoul,Republic of Korea","Department of Artificial Intelligence, Hanyang University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Artificial Intelligence,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Hanyang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109692706","display_name":"Min-Sang Baek","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Min-Sang Baek","raw_affiliation_strings":["Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","Department of Electronic Engineering, Hanyang University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]},{"raw_affiliation_string":"Department of Electronic Engineering, Hanyang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049167445","display_name":"Yungyeo Kim","orcid":"https://orcid.org/0009-0008-9858-453X"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yungyeo Kim","raw_affiliation_strings":["Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","Department of Electronic Engineering, Hanyang University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]},{"raw_affiliation_string":"Department of Electronic Engineering, Hanyang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002418613","display_name":"Joon\u2010Hyuk Chang","orcid":"https://orcid.org/0000-0003-2610-2323"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon-Hyuk Chang","raw_affiliation_strings":["Hanyang University,Department of Artificial Intelligence,Seoul,Republic of Korea","Department of Artificial Intelligence, Hanyang University, Seoul, Republic of Korea","Department of Electronic Engineering, Hanyang University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Artificial Intelligence,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Hanyang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4575257"]},{"raw_affiliation_string":"Department of Electronic Engineering, Hanyang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113361569"],"corresponding_institution_ids":["https://openalex.org/I4575257"],"apc_list":null,"apc_paid":null,"fwci":1.4495,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.80011624,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1396","last_page":"1400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/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/T11349","display_name":"Music Technology and Sound Studies","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/timestamp","display_name":"Timestamp","score":0.9628591537475586},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7442494034767151},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.5716542601585388},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5206736326217651},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.50583815574646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48584529757499695},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.42384272813796997},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35142672061920166},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34915775060653687},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32589191198349},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.16489055752754211}],"concepts":[{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.9628591537475586},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7442494034767151},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.5716542601585388},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5206736326217651},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.50583815574646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48584529757499695},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.42384272813796997},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35142672061920166},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34915775060653687},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32589191198349},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.16489055752754211},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3034753964","display_name":null,"funder_award_id":"grant","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G342704958","display_name":null,"funder_award_id":"funded","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G377792351","display_name":null,"funder_award_id":"RS-2023-00302424","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G462239167","display_name":null,"funder_award_id":"RS-2023-00302424","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G515828364","display_name":null,"funder_award_id":"No. RS-","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2173379916","https://openalex.org/W2512865187","https://openalex.org/W2964058413","https://openalex.org/W2981816492","https://openalex.org/W2988200020","https://openalex.org/W3008987902","https://openalex.org/W3095263845","https://openalex.org/W3095799548","https://openalex.org/W3160972914","https://openalex.org/W3197762568","https://openalex.org/W3207860153","https://openalex.org/W4224871700","https://openalex.org/W4224914418","https://openalex.org/W4225281800","https://openalex.org/W4297841626","https://openalex.org/W4310873168","https://openalex.org/W4372271367","https://openalex.org/W4372348953","https://openalex.org/W6631190155","https://openalex.org/W6638523607","https://openalex.org/W6685316698","https://openalex.org/W6752516136","https://openalex.org/W6753583920"],"related_works":["https://openalex.org/W2060561905","https://openalex.org/W1417711376","https://openalex.org/W2032260263","https://openalex.org/W1986883493","https://openalex.org/W2469862403","https://openalex.org/W2166378262","https://openalex.org/W2035891203","https://openalex.org/W4379524643","https://openalex.org/W2011027677","https://openalex.org/W2996999409"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,72],"propose":[4,108],"a":[5,135],"timestamp":[6,56,70,114],"knowledge":[7,14,57,115],"distillation":[8,15],"(TKD)":[9],"method":[10],"that":[11,55,79,111,145],"adopts":[12],"privileged":[13,91],"to":[16,37,63,98,104,126,162],"enhance":[17],"the":[18,39,65,74,81,87,94,109,113,117,127,146,149,153,157,163],"performance":[19,160],"of":[20,41,58,83],"deep":[21],"neural":[22],"network":[23],"(DNN)-based":[24],"target":[25,42,84],"sound":[26,43],"extraction":[27],"(TSE).":[28],"While":[29],"previous":[30],"studies":[31,53],"have":[32],"mainly":[33],"used":[34],"n-hot":[35],"vectors":[36],"indicate":[38,80],"type":[40],"events":[44],"(SEs),":[45],"which":[46],"are":[47,96],"termed":[48],"weak":[49],"labels":[50,77],"(WLs),":[51],"recent":[52],"demonstrated":[54],"SEs":[59,85],"is":[60],"meaningful":[61],"information":[62],"improve":[64],"TSE":[66,150],"performance.":[67],"To":[68],"utilize":[69],"knowledge,":[71],"use":[73],"oracle":[75],"strong":[76],"(OSLs)":[78],"occurrence":[82],"in":[86,100],"audio":[88],"clip":[89],"as":[90],"information.":[92],"However,":[93],"OSLs":[95,125,147],"difficult":[97],"gain":[99],"real-world":[101],"applications":[102],"compared":[103,161],"WLs.":[105,168],"We":[106],"thus":[107],"TKD":[110,154],"transfers":[112],"from":[116],"teacher":[118],"model":[119,129],"trained":[120,130,165],"using":[121,131],"both":[122],"WLs":[123,133],"and":[124],"student":[128,158],"only":[132,166],"via":[134],"loss":[136],"function.":[137],"Experimental":[138],"results":[139],"across":[140],"multiple":[141],"DNN":[142],"architectures":[143],"confirmed":[144],"enhanced":[148],"significantly.":[151],"Moreover,":[152],"notably":[155],"improved":[156],"model\u2019s":[159],"baseline":[164],"with":[167]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-14T08:43:22.919905","created_date":"2025-10-10T00:00:00"}