{"id":"https://openalex.org/W4392910302","doi":"https://doi.org/10.1109/icassp48485.2024.10447291","title":"Consistent and Relevant: Rethink the Query Embedding in General Sound Separation","display_name":"Consistent and Relevant: Rethink the Query Embedding in General Sound Separation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910302","doi":"https://doi.org/10.1109/icassp48485.2024.10447291"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447291","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":"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/A5103325935","display_name":"Yuanyuan Wang","orcid":"https://orcid.org/0000-0003-1367-0989"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyuan Wang","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048946763","display_name":"Hangting Chen","orcid":"https://orcid.org/0000-0002-4085-4364"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hangting Chen","raw_affiliation_strings":["Audio and Speech Signal Processing Oteam,Tencent AI Lab,China","Tencent AI Lab, Audio and Speech Signal Processing Oteam, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio and Speech Signal Processing Oteam,Tencent AI Lab,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Audio and Speech Signal Processing Oteam, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043555011","display_name":"Dongchao Yang","orcid":"https://orcid.org/0000-0002-8905-224X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dongchao Yang","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101338533","display_name":"Jianwei Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwei Yu","raw_affiliation_strings":["Audio and Speech Signal Processing Oteam,Tencent AI Lab,China","Tencent AI Lab, Audio and Speech Signal Processing Oteam, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio and Speech Signal Processing Oteam,Tencent AI Lab,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Audio and Speech Signal Processing Oteam, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106404246","display_name":"Chao Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Weng","raw_affiliation_strings":["Audio and Speech Signal Processing Oteam,Tencent AI Lab,China","Tencent AI Lab, Audio and Speech Signal Processing Oteam, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio and Speech Signal Processing Oteam,Tencent AI Lab,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Audio and Speech Signal Processing Oteam, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8343,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67276631,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"961","last_page":"965"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9954000115394592,"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":0.9940999746322632,"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":0.6686903238296509},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5714914798736572},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5519405007362366},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5230361223220825},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.46529945731163025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2976112961769104},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.28109967708587646},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11170980334281921},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11020117998123169},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.07773533463478088}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6686903238296509},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5714914798736572},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5519405007362366},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5230361223220825},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.46529945731163025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2976112961769104},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28109967708587646},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11170980334281921},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11020117998123169},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07773533463478088}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447291","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/G2603945996","display_name":null,"funder_award_id":"62076144","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2052666245","https://openalex.org/W2127851351","https://openalex.org/W2187089797","https://openalex.org/W2408744528","https://openalex.org/W2563534197","https://openalex.org/W2593116425","https://openalex.org/W2669032454","https://openalex.org/W2774707525","https://openalex.org/W2898963093","https://openalex.org/W2962753171","https://openalex.org/W2962935966","https://openalex.org/W2963452667","https://openalex.org/W2963751183","https://openalex.org/W2969034647","https://openalex.org/W2973109987","https://openalex.org/W3004910802","https://openalex.org/W3094550259","https://openalex.org/W3138516171","https://openalex.org/W3196974791","https://openalex.org/W3205743929","https://openalex.org/W4224914418","https://openalex.org/W4226151502","https://openalex.org/W4226442948","https://openalex.org/W4321232185","https://openalex.org/W4385823327","https://openalex.org/W6746914816","https://openalex.org/W6751512325","https://openalex.org/W6766938422"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2081900870","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2071676784","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2909726438"],"abstract_inverted_index":{"The":[0],"query-based":[1,20],"audio":[2,16,87],"separation":[3,21,33,53,77,97,125,141,166,186],"usually":[4],"employs":[5],"specific":[6],"queries":[7,95],"to":[8,26,37,40,56,78,119,161,164],"extract":[9],"target":[10],"sources":[11],"from":[12],"a":[13,68,80,110,114,148],"mixture":[14],"of":[15,43,83,138,185],"signals.":[17],"Currently,":[18],"most":[19],"models":[22,54],"need":[23],"additional":[24],"networks":[25],"obtain":[27],"query":[28,44,47,84,121,139,157],"embedding.":[29,45],"In":[30,62],"this":[31,63],"way,":[32],"model":[34,112,180],"is":[35,117,159],"optimized":[36,160],"be":[38,162],"adapted":[39],"the":[41,91,130,156,165,170,177,183,191],"distribution":[42,137],"However,":[46],"embedding":[48,72,158],"may":[49],"exhibit":[50],"mismatches":[51],"with":[52,113,147],"due":[55],"inconsistent":[57],"structures":[58],"and":[59,70,96,105,123,134,140,152,194],"independent":[60],"information.":[61,108],"paper,":[64],"we":[65],"present":[66],"CaRE-SEP,":[67],"consistent":[69,136],"relevant":[71,163],"network":[73,103,131,151],"for":[74],"general":[75],"sound":[76,124],"encourage":[79],"comprehensive":[81],"reconsideration":[82],"usage":[85],"in":[86,98],"separation.":[88],"CaRE-SEP":[89,146,179,196],"alleviates":[90],"potential":[92,192],"mismatch":[93,172,193],"between":[94],"two":[99],"aspects,":[100],"including":[101],"sharing":[102,106],"structure":[104],"feature":[107,171],"First,":[109],"Swin-Unet":[111],"shared":[115],"encoder":[116],"conducted":[118],"unify":[120],"encoding":[122],"into":[126],"one":[127],"model,":[128],"eliminating":[129],"architecture":[132],"difference":[133],"generating":[135],"features.":[142],"Second,":[143],"by":[144],"initializing":[145],"pretrained":[149],"classification":[150],"allowing":[153],"gradient":[154],"backpropagation,":[155],"feature,":[167],"further":[168],"alleviating":[169],"problem.":[173],"Experimental":[174],"results":[175],"indicate":[176],"proposed":[178],"substantially":[181],"improves":[182],"performance":[184],"tasks.":[187],"Moreover,":[188],"visualizations":[189],"validate":[190],"how":[195],"solves":[197],"it.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}