{"id":"https://openalex.org/W4408355579","doi":"https://doi.org/10.1109/icassp49660.2025.10887870","title":"InfoMin-based Query Embedding Optimization For Query-based Universal Sound Separation","display_name":"InfoMin-based Query Embedding Optimization For Query-based Universal Sound Separation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355579","doi":"https://doi.org/10.1109/icassp49660.2025.10887870"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887870","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":"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/A5100422304","display_name":"Zhen Wang","orcid":"https://orcid.org/0000-0002-1695-4517"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhen Wang","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology,Harbin,China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101508830","display_name":"Jiqing Han","orcid":"https://orcid.org/0000-0002-4297-4300"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiqing Han","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology,Harbin,China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100459582","display_name":"Liwen Zhang","orcid":"https://orcid.org/0000-0001-8457-2943"},"institutions":[{"id":"https://openalex.org/I15089104","display_name":"China Aerospace Science and Industry Corporation (China)","ror":"https://ror.org/0523vvf33","country_code":"CN","type":"company","lineage":["https://openalex.org/I15089104"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liwen Zhang","raw_affiliation_strings":["Intelligent Science and Technology Academy of CASIC,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Intelligent Science and Technology Academy of CASIC,Beijing,China","institution_ids":["https://openalex.org/I15089104"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028199953","display_name":"Youcheng Zhang","orcid":"https://orcid.org/0000-0002-3386-9728"},"institutions":[{"id":"https://openalex.org/I15089104","display_name":"China Aerospace Science and Industry Corporation (China)","ror":"https://ror.org/0523vvf33","country_code":"CN","type":"company","lineage":["https://openalex.org/I15089104"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youcheng Zhang","raw_affiliation_strings":["Intelligent Science and Technology Academy of CASIC,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Intelligent Science and Technology Academy of CASIC,Beijing,China","institution_ids":["https://openalex.org/I15089104"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100422304"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05865855,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9991000294685364,"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":0.9991000294685364,"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":0.9979000091552734,"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":0.9926999807357788,"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/query-optimization","display_name":"Query optimization","score":0.8625005483627319},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7650086879730225},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.7594135999679565},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.6334151029586792},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6211249232292175},{"id":"https://openalex.org/keywords/query-by-example","display_name":"Query by Example","score":0.6143519878387451},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.6097159385681152},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.514346718788147},{"id":"https://openalex.org/keywords/rdf-query-language","display_name":"RDF query language","score":0.48777633905410767},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.3995082378387451},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.359414666891098},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2186146378517151},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.15144452452659607}],"concepts":[{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.8625005483627319},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7650086879730225},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.7594135999679565},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.6334151029586792},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6211249232292175},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.6143519878387451},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.6097159385681152},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.514346718788147},{"id":"https://openalex.org/C96956885","wikidata":"https://www.wikidata.org/wiki/Q6138701","display_name":"RDF query language","level":5,"score":0.48777633905410767},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.3995082378387451},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.359414666891098},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2186146378517151},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.15144452452659607}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887870","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2094721231","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2593116425","https://openalex.org/W2760103357","https://openalex.org/W2962715207","https://openalex.org/W2988200020","https://openalex.org/W3094550259","https://openalex.org/W3160972914","https://openalex.org/W3161934504","https://openalex.org/W4205689591","https://openalex.org/W4225300878","https://openalex.org/W4225327445","https://openalex.org/W4226151502","https://openalex.org/W4297841626","https://openalex.org/W4323064860","https://openalex.org/W4372260051","https://openalex.org/W4375869413","https://openalex.org/W4375928773","https://openalex.org/W4379797396","https://openalex.org/W4385756463","https://openalex.org/W4386075686","https://openalex.org/W4391021590","https://openalex.org/W4392903555","https://openalex.org/W6632698320","https://openalex.org/W6753583920","https://openalex.org/W6777179611","https://openalex.org/W6784499681","https://openalex.org/W6852871851"],"related_works":["https://openalex.org/W2096359267","https://openalex.org/W4256058599","https://openalex.org/W2572349046","https://openalex.org/W2392799717","https://openalex.org/W2146885082","https://openalex.org/W3125756434","https://openalex.org/W2026738364","https://openalex.org/W2013069866","https://openalex.org/W2538384344","https://openalex.org/W2970853428"],"abstract_inverted_index":{"The":[0],"query-based":[1],"universal":[2],"sound":[3,16],"separation":[4,13,32,43,106],"(QUSS)":[5],"has":[6],"been":[7],"addressed,":[8],"aiming":[9],"to":[10,92],"perform":[11],"the":[12,29,35,71,78,94,102,105,118],"of":[14,24,31,37,97,104],"specific":[15],"sources":[17],"based":[18],"on":[19,28,42],"a":[20],"given":[21],"query.":[22],"Most":[23],"existed":[25],"methods":[26],"focus":[27],"improvement":[30],"models,":[33],"ignoring":[34],"influence":[36],"category-conditioned":[38],"query":[39,55,63,98],"embedding":[40,56,99],"distribution":[41],"performance.":[44],"To":[45],"address":[46],"this":[47],"issue,":[48],"we":[49,76],"propose":[50,77],"an":[51],"optimization":[52],"method":[53,113],"for":[54],"that":[57,111],"reduces":[58],"mutual":[59],"information":[60,68],"(MI)":[61],"between":[62],"embeddings":[64],"while":[65],"keeping":[66],"task-related":[67],"intact,":[69],"named":[70],"InfoMin":[72],"principle.":[73],"In":[74],"addition,":[75],"Frequency-varying":[79],"Feature-wise":[80],"Linear":[81],"Modulation":[82],"(FFiLM),":[83],"which":[84],"leverages":[85],"frequency":[86],"band":[87],"differences":[88],"in":[89],"acoustic":[90],"events":[91],"enhance":[93],"modulation":[95],"capability":[96],"and":[100],"improve":[101],"performance":[103],"model.":[107],"Experimental":[108],"results":[109],"show":[110],"our":[112],"achieves":[114],"considerable":[115],"improvements":[116],"over":[117],"existing":[119],"SoTA":[120],"method.":[121]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}