{"id":"https://openalex.org/W4409640780","doi":"https://doi.org/10.1109/lsp.2025.3562949","title":"UniArray: Unified Spectral-Spatial Modeling for Array-Geometry-Agnostic Speech Separation","display_name":"UniArray: Unified Spectral-Spatial Modeling for Array-Geometry-Agnostic Speech Separation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409640780","doi":"https://doi.org/10.1109/lsp.2025.3562949"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3562949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3562949","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5101543632","display_name":"Weiguang Chen","orcid":"https://orcid.org/0000-0002-7945-3197"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiguang Chen","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-7945-3197","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junjie Zhang","orcid":"https://orcid.org/0009-0009-4381-8156"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Zhang","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0009-4381-8156","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018463611","display_name":"Jielong Yang","orcid":"https://orcid.org/0000-0001-5853-6316"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jielong Yang","raw_affiliation_strings":["School of Internet of Things Engineering, Jiangnan University, Wuxi, China"],"raw_orcid":"https://orcid.org/0000-0001-5853-6316","affiliations":[{"raw_affiliation_string":"School of Internet of Things Engineering, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6257-7399","affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100681425","display_name":"Xionghu Zhong","orcid":"https://orcid.org/0000-0002-7533-2347"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xionghu Zhong","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-7533-2347","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03529513,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"2164","last_page":"2168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962000250816345,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962000250816345,"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/T10860","display_name":"Speech and Audio Processing","score":0.9952999949455261,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.961899995803833,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5750080347061157},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5245947241783142},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.41278672218322754},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3804590404033661},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3682071268558502}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5750080347061157},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5245947241783142},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.41278672218322754},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3804590404033661},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3682071268558502},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2025.3562949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3562949","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/217370","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/217370","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6399999856948853}],"awards":[{"id":"https://openalex.org/G3967457896","display_name":"\u57fa\u4e8e\u5206\u5e03\u5f0f\u9ea6\u514b\u98ce\u9635\u5217\u7f51\u7edc\u7684\u4e00\u4f53\u5316\u591a\u58f0\u6e90\u68c0\u6d4b\u3001\u8ddf\u8e2a\u4e0e\u4fe1\u53f7\u5206\u79bb\u7814\u7a76","funder_award_id":"61971186","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"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":39,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1989314204","https://openalex.org/W2089586791","https://openalex.org/W2141998673","https://openalex.org/W2221409856","https://openalex.org/W2263133179","https://openalex.org/W2726515241","https://openalex.org/W2734774145","https://openalex.org/W2964058413","https://openalex.org/W2987559325","https://openalex.org/W3015199127","https://openalex.org/W3015372568","https://openalex.org/W3015780472","https://openalex.org/W3016257794","https://openalex.org/W3094893851","https://openalex.org/W3094897602","https://openalex.org/W3096893582","https://openalex.org/W3097966334","https://openalex.org/W3163652268","https://openalex.org/W3163912061","https://openalex.org/W3197801171","https://openalex.org/W3205004157","https://openalex.org/W3205115292","https://openalex.org/W3205567090","https://openalex.org/W3207360934","https://openalex.org/W4223583411","https://openalex.org/W4224936432","https://openalex.org/W4285170242","https://openalex.org/W4296068772","https://openalex.org/W4372259962","https://openalex.org/W4372271367","https://openalex.org/W4385822396","https://openalex.org/W4385823047","https://openalex.org/W4386763644","https://openalex.org/W4391621214","https://openalex.org/W4392902932","https://openalex.org/W4392904504","https://openalex.org/W4392910826","https://openalex.org/W4408354310"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2077498359"],"abstract_inverted_index":{"Array-geometry-agnostic":[0],"speech":[1],"separation":[2,9],"(AGA-SS)":[3],"aims":[4],"to":[5,29,55,127,136],"develop":[6],"an":[7],"effective":[8,44],"method":[10],"regardless":[11],"of":[12,46,76],"the":[13,43,70,134,140,151],"microphone":[14,82],"array":[15,179],"geometry.":[16],"Conventional":[17],"methods":[18,167],"rely":[19],"on":[20,138],"permutation-free":[21],"operations,":[22],"such":[23],"as":[24],"summation":[25],"or":[26,41],"attention":[27],"mechanisms,":[28],"capture":[30],"spatial":[31,47,122],"information.":[32],"However,":[33],"these":[34,60],"approaches":[35],"often":[36],"incur":[37],"high":[38],"computational":[39,158],"costs":[40],"disrupt":[42],"use":[45],"information":[48],"during":[49],"intra-":[50],"and":[51,89,92,111,120,129,153,172,177],"inter-channel":[52],"interactions,":[53],"leading":[54],"suboptimal":[56],"performance.":[57],"To":[58],"address":[59],"issues,":[61],"we":[62],"propose":[63],"UniArray,":[64],"a":[65,80,86,93,115,121],"novel":[66],"approach":[67],"that":[68,163],"abandons":[69],"conventional":[71],"interleaving":[72],"manner.":[73],"UniArray":[74,164],"consists":[75],"three":[77],"key":[78],"components:":[79],"virtual":[81],"estimation":[83],"(VME)":[84],"module,":[85,91],"feature":[87,109,117,148],"extraction":[88,110,118],"fusion":[90,112],"hierarchical":[94,144],"dual-path":[95,145],"separator.":[96],"The":[97,108,143],"VME":[98],"ensures":[99],"robust":[100],"performance":[101],"across":[102,174],"arrays":[103],"with":[104],"varying":[105],"channel":[106],"numbers.":[107],"module":[113,119,126],"leverages":[114],"spectral":[116],"dictionary":[123],"learning":[124],"(SDL)":[125],"extract":[128],"fuse":[130],"frequency-bin-level":[131],"features,":[132],"allowing":[133],"separator":[135,146],"focus":[137],"using":[139],"fused":[141],"features.":[142],"models":[147],"dependencies":[149],"along":[150],"time":[152],"frequency":[154],"axes":[155],"while":[156],"maintaining":[157],"efficiency.":[159],"Experimental":[160],"results":[161],"show":[162],"outperforms":[165],"state-of-the-art":[166],"in":[168],"SI-SDRi,":[169],"WB-PESQ,":[170],"NB-PESQ,":[171],"STOI":[173],"both":[175],"seen":[176],"unseen":[178],"geometries.":[180]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}