{"id":"https://openalex.org/W4408352286","doi":"https://doi.org/10.1109/icassp49660.2025.10890145","title":"Multichannel-to-Multichannel Target Sound Extraction Using Direction and Timestamp Clues","display_name":"Multichannel-to-Multichannel Target Sound Extraction Using Direction and Timestamp Clues","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352286","doi":"https://doi.org/10.1109/icassp49660.2025.10890145"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890145","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890145","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5107369407","display_name":"Dayun Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dayun Choi","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,School of Electrical Engineering,Daejeon,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,School of Electrical Engineering,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017443019","display_name":"Jungwoo Choi","orcid":"https://orcid.org/0000-0003-3988-6331"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jung-Woo Choi","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,School of Electrical Engineering,Daejeon,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,School of Electrical Engineering,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9958999752998352,"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":0.9814000129699707,"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/timestamp","display_name":"Timestamp","score":0.8484840393066406},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.677597165107727},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.47350671887397766},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4701041579246521},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4215746223926544},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2748819589614868},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.18944743275642395}],"concepts":[{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.8484840393066406},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.677597165107727},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.47350671887397766},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4701041579246521},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4215746223926544},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2748819589614868},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.18944743275642395},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890145","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890145","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W1989314204","https://openalex.org/W2128974165","https://openalex.org/W2143169494","https://openalex.org/W2763188033","https://openalex.org/W2771361008","https://openalex.org/W2963446712","https://openalex.org/W2964058413","https://openalex.org/W3015679215","https://openalex.org/W3016094953","https://openalex.org/W3016257794","https://openalex.org/W3095263845","https://openalex.org/W3134695619","https://openalex.org/W4224871700","https://openalex.org/W4224914418","https://openalex.org/W4288054834","https://openalex.org/W4296069305","https://openalex.org/W4310873168","https://openalex.org/W4311516808","https://openalex.org/W4321608474","https://openalex.org/W4372259805","https://openalex.org/W4372259962","https://openalex.org/W4372260051","https://openalex.org/W4372348953","https://openalex.org/W4385756463","https://openalex.org/W4387835382","https://openalex.org/W4388755868","https://openalex.org/W4388895115","https://openalex.org/W4392903103","https://openalex.org/W4392908986","https://openalex.org/W4392911133","https://openalex.org/W4395471087","https://openalex.org/W4402112351","https://openalex.org/W4403126605","https://openalex.org/W4403917834","https://openalex.org/W4404317174","https://openalex.org/W4404609224","https://openalex.org/W6753583920","https://openalex.org/W6855917767"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,15,26,64,99],"multichannel-to-multichannel":[3],"target":[4,12,28,65],"sound":[5,19,22,66,101],"extraction":[6,23,37,72,138],"(M2M-TSE)":[7],"framework":[8,96],"for":[9,71,118],"separating":[10],"multichannel":[11,16,53,61,100,119,137],"signals":[13,62,120,124],"from":[14,122],"mixture":[17],"of":[18,63,85,125],"sources.":[20],"Target":[21],"(TSE)":[24],"isolates":[25],"specific":[27],"signal":[29,102],"using":[30],"user-provided":[31],"clues,":[32],"typically":[33],"focusing":[34],"on":[35,104],"single-channel":[36],"with":[38],"class":[39],"labels":[40],"or":[41,77,83],"temporal":[42,78],"activation":[43],"maps.":[44],"However,":[45],"to":[46,59,149],"preserve":[47],"and":[48],"utilize":[49],"spatial":[50,76,157],"information":[51],"in":[52,128,144],"audio":[54,123],"signals,":[55],"it":[56,148],"is":[57],"essential":[58],"extract":[60],"source.":[67],"Moreover,":[68],"the":[69,115,136,145],"clue":[70],"can":[73,112],"also":[74],"include":[75],"cues":[79],"like":[80],"direction-of-arrival":[81],"(DoA)":[82],"timestamps":[84],"source":[86],"activation.":[87],"To":[88],"address":[89],"these":[90],"challenges,":[91],"we":[92,133],"present":[93],"an":[94],"M2M":[95],"that":[97,108,135],"extracts":[98],"based":[103],"spatio-temporal":[105],"clues.We":[106],"demonstrate":[107],"our":[109],"transformer-based":[110],"architecture":[111],"successively":[113],"accomplish":[114],"M2M-TSE":[116],"task":[117,139],"synthesized":[121],"diverse":[126],"classes":[127],"different":[129],"room":[130],"environments.":[131],"Furthermore,":[132],"show":[134],"introduces":[140],"sufficient":[141],"inductive":[142],"bias":[143],"DNN,":[146],"allowing":[147],"directly":[150],"handle":[151],"DoA":[152],"clues":[153],"without":[154],"utilizing":[155],"hand-crafted":[156],"features.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
