{"id":"https://openalex.org/W4372260051","doi":"https://doi.org/10.1109/icassp49357.2023.10095266","title":"Target Sound Extraction with Variable Cross-Modality Clues","display_name":"Target Sound Extraction with Variable Cross-Modality Clues","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260051","doi":"https://doi.org/10.1109/icassp49357.2023.10095266"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5090224430","display_name":"Chenda Li","orcid":"https://orcid.org/0000-0003-0299-9914"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Chenda Li","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering","Microsoft, Redmond, WA, USA","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053009352","display_name":"Yao Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yao Qian","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering","Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345092","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0002-9011-7928"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100408281","display_name":"Dongmei Wang","orcid":"https://orcid.org/0000-0002-6930-0066"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongmei Wang","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101635405","display_name":"Shujie Liu","orcid":"https://orcid.org/0009-0008-2599-6752"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shujie Liu","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089195158","display_name":"Michael Zeng","orcid":"https://orcid.org/0000-0001-5302-5883"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Zeng","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"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/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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7299708127975464},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5903871655464172},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5702002048492432},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.528408408164978},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.525102972984314},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5119282007217407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47280874848365784},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.44686099886894226},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4291662871837616},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4245093762874603},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08797863125801086}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7299708127975464},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5903871655464172},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5702002048492432},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.528408408164978},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.525102972984314},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5119282007217407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47280874848365784},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.44686099886894226},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4291662871837616},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4245093762874603},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08797863125801086},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7699999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1991139021","https://openalex.org/W2221409856","https://openalex.org/W2593116425","https://openalex.org/W2734774145","https://openalex.org/W2891833136","https://openalex.org/W2916103538","https://openalex.org/W2945761034","https://openalex.org/W2952218014","https://openalex.org/W2964171275","https://openalex.org/W2973062255","https://openalex.org/W2973231102","https://openalex.org/W2978017171","https://openalex.org/W2990594533","https://openalex.org/W2990666817","https://openalex.org/W2998657200","https://openalex.org/W3000358149","https://openalex.org/W3004910802","https://openalex.org/W3012897083","https://openalex.org/W3015636705","https://openalex.org/W3016361963","https://openalex.org/W3094550259","https://openalex.org/W3094893721","https://openalex.org/W3096408984","https://openalex.org/W3097450720","https://openalex.org/W3099330747","https://openalex.org/W3103434036","https://openalex.org/W3138516171","https://openalex.org/W3151851237","https://openalex.org/W3182657421","https://openalex.org/W3206706278","https://openalex.org/W4224871700","https://openalex.org/W4225327445","https://openalex.org/W4288054834","https://openalex.org/W4296070419","https://openalex.org/W4297841626","https://openalex.org/W4312711418","https://openalex.org/W4312909419","https://openalex.org/W4385245566","https://openalex.org/W6751512325","https://openalex.org/W6768851824","https://openalex.org/W6775369996"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4206178588","https://openalex.org/W3094491777","https://openalex.org/W3214715529","https://openalex.org/W4287635093"],"abstract_inverted_index":{"Automatic":[0],"target":[1,41,65],"sound":[2,21,42,47,84],"extraction":[3],"(TSE)":[4],"is":[5,113],"a":[6,20,26,33,37,46,81,83,88,93,100,124,155],"machine":[7],"learning":[8],"approach":[9],"to":[10,19,62,117],"mimic":[11],"the":[12,52,60,64,77,106,109,162],"human":[13],"auditory":[14],"perception":[15],"capability":[16],"of":[17,23,28,40,71,158],"attending":[18],"source":[22],"interest":[24],"from":[25],"mixture":[27],"sources.":[29],"It":[30],"often":[31],"uses":[32],"model":[34,61,97,150],"conditioned":[35],"on":[36,130],"fixed":[38],"form":[39],"clues,":[43],"such":[44],"as":[45],"class":[48],"label,":[49],"which":[50,55,160],"limits":[51],"ways":[53],"in":[54,76],"users":[56],"can":[57,151],"interact":[58],"with":[59,154],"specify":[63],"sounds.":[66],"To":[67],"leverage":[68],"variable":[69],"number":[70,157],"clues":[72,107,159],"cross":[73],"modalities":[74],"available":[75],"inference":[78],"phase,":[79],"including":[80],"video,":[82],"event":[85],"class,":[86],"and":[87,134,140,165],"text":[89],"caption,":[90],"we":[91,122],"propose":[92],"unified":[94],"transformer-based":[95],"TSE":[96,149,163],"architecture,":[98],"where":[99],"multi-clue":[101],"attention":[102],"module":[103],"integrates":[104],"all":[105],"across":[108],"modalities.":[110],"Since":[111],"there":[112],"no":[114],"off-the-shelf":[115],"benchmark":[116],"evaluate":[118],"our":[119,147],"proposed":[120,148],"approach,":[121],"build":[123],"dataset":[125],"<sup":[126],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[127],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[128],"based":[129],"public":[131],"corpora,":[132],"Audioset":[133],"AudioCaps.":[135],"Experimental":[136],"results":[137],"for":[138],"seen":[139],"unseen":[141],"target-sound":[142],"evaluation":[143],"sets":[144],"show":[145],"that":[146],"effectively":[152],"deal":[153],"varying":[156],"improves":[161],"performance":[164],"robustness":[166],"against":[167],"partially":[168],"compromised":[169],"clues.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}