{"id":"https://openalex.org/W4408356285","doi":"https://doi.org/10.1109/icassp49660.2025.10890178","title":"Cross-attention Inspired Selective State Space Models for Target Sound Extraction","display_name":"Cross-attention Inspired Selective State Space Models for Target Sound Extraction","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408356285","doi":"https://doi.org/10.1109/icassp49660.2025.10890178"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890178","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/A5101031235","display_name":"Donghang Wu","orcid":"https://orcid.org/0009-0004-3597-8284"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Donghang Wu","raw_affiliation_strings":["Peking University,State Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Peking University,State Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383445","display_name":"Yiwen Wang","orcid":"https://orcid.org/0000-0002-1878-6182"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwen Wang","raw_affiliation_strings":["Peking University,State Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Peking University,State Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111110989","display_name":"Xihong Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xihong Wu","raw_affiliation_strings":["Peking University,State Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Peking University,State Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103080532","display_name":"Tianshu Qu","orcid":"https://orcid.org/0000-0001-6256-2031"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianshu Qu","raw_affiliation_strings":["Peking University,State Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Peking University,State Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101031235"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":7.6696,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.97220516,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"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":0.9898999929428101,"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":0.9898999929428101,"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":0.9871000051498413,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9790999889373779,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6933856010437012},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4745531678199768},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.456760436296463},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4547116756439209},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.45118245482444763},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.406225323677063},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40389424562454224},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2954460680484772},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12267914414405823},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1085425317287445}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6933856010437012},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4745531678199768},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.456760436296463},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4547116756439209},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.45118245482444763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.406225323677063},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40389424562454224},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2954460680484772},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12267914414405823},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1085425317287445},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890178","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":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.6200000047683716}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324787","display_name":"Peking University","ror":"https://ror.org/02v51f717"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2808631503","https://openalex.org/W2951130829","https://openalex.org/W2973062255","https://openalex.org/W3016361963","https://openalex.org/W3096893582","https://openalex.org/W3160972914","https://openalex.org/W4310873168","https://openalex.org/W4372259900","https://openalex.org/W4372348953","https://openalex.org/W4385245566","https://openalex.org/W4390394145","https://openalex.org/W4399939359","https://openalex.org/W4401023616","https://openalex.org/W4402112499","https://openalex.org/W4402117039","https://openalex.org/W6752516136","https://openalex.org/W6753583920","https://openalex.org/W6755207826","https://openalex.org/W6788135285","https://openalex.org/W6803444062","https://openalex.org/W6859298233","https://openalex.org/W6860915106","https://openalex.org/W6862476165"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W2025747832","https://openalex.org/W3020957235","https://openalex.org/W2056769785","https://openalex.org/W611303608","https://openalex.org/W4313595395","https://openalex.org/W2312783472","https://openalex.org/W2909748163"],"abstract_inverted_index":{"The":[0,115],"Transformer":[1],"model,":[2],"particularly":[3],"its":[4,28,74],"cross-attention":[5,84,152],"module,":[6],"is":[7,70],"widely":[8],"used":[9],"for":[10,92],"feature":[11],"fusion":[12],"in":[13,39,60,66,154],"target":[14,67,93,161],"sound":[15,68,94,162],"extraction":[16,69,163],"which":[17,96],"extracts":[18],"the":[19,44,83,98,108,112,123,130,134,137,142,148,151,166,169],"signal":[20],"of":[21,102,117,150,168],"interest":[22],"based":[23],"on":[24],"given":[25,109],"clues.":[26],"Despite":[27],"effectiveness,":[29],"this":[30,87],"approach":[31],"suffers":[32],"from":[33,158],"low":[34],"computational":[35,58],"efficiency.":[36],"Recent":[37],"advancements":[38],"state":[40],"space":[41],"models,":[42],"notably":[43],"latest":[45],"work":[46],"Mamba,":[47],"have":[48],"shown":[49],"comparable":[50],"performance":[51],"to":[52,73,76,104,122,132,140,147],"Transformer-based":[53],"methods":[54,164],"while":[55],"significantly":[56],"reducing":[57],"complexity":[59],"various":[61],"tasks.":[62],"However,":[63],"Mamba\u2019s":[64],"applicability":[65],"limited":[71],"due":[72],"inability":[75],"capture":[77],"dependencies":[78,106],"between":[79,107],"different":[80],"sequences":[81],"as":[82],"does.":[85],"In":[86],"paper,":[88],"we":[89],"propose":[90],"CrossMamba":[91],"extraction,":[95],"leverages":[97],"hidden":[99],"attention":[100],"mechanism":[101,153],"Mamba":[103,118],"compute":[105],"clues":[110],"and":[111,126,136,144],"audio":[113,138],"mixture.":[114],"calculation":[116],"can":[119],"be":[120],"divided":[121],"query,":[124],"key":[125,143],"value.":[127],"We":[128],"utilize":[129],"clue":[131],"generate":[133],"query":[135],"mixture":[139],"derive":[141],"value,":[145],"adhering":[146],"principle":[149],"Transformers.":[155],"Experimental":[156],"results":[157],"two":[159],"representative":[160],"validate":[165],"efficacy":[167],"proposed":[170],"CrossMamba.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}