{"id":"https://openalex.org/W4415708977","doi":"https://doi.org/10.1109/icme59968.2025.11209217","title":"SPMamba: Leveraging Long-Sequence Modeling with State Space Models for Speech Separation","display_name":"SPMamba: Leveraging Long-Sequence Modeling with State Space Models for Speech Separation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708977","doi":"https://doi.org/10.1109/icme59968.2025.11209217"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5100399972","display_name":"Kai Li","orcid":"https://orcid.org/0000-0003-1560-0853"},"institutions":[{"id":"https://openalex.org/I144112489","display_name":"McGovern Institute for Brain Research","ror":"https://ror.org/05ymca674","country_code":"US","type":"facility","lineage":["https://openalex.org/I144112489","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Li","raw_affiliation_strings":["BNRist, THBI, IDG/McGovern Institute for Brain Research, Tsinghua University,Department of Computer Science and Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BNRist, THBI, IDG/McGovern Institute for Brain Research, Tsinghua University,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I144112489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101786825","display_name":"Guo Chen","orcid":"https://orcid.org/0000-0001-6359-1168"},"institutions":[{"id":"https://openalex.org/I144112489","display_name":"McGovern Institute for Brain Research","ror":"https://ror.org/05ymca674","country_code":"US","type":"facility","lineage":["https://openalex.org/I144112489","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guo Chen","raw_affiliation_strings":["BNRist, THBI, IDG/McGovern Institute for Brain Research, Tsinghua University,Department of Computer Science and Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BNRist, THBI, IDG/McGovern Institute for Brain Research, Tsinghua University,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I144112489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006425914","display_name":"Runxuan Yang","orcid":"https://orcid.org/0009-0004-2526-1909"},"institutions":[{"id":"https://openalex.org/I144112489","display_name":"McGovern Institute for Brain Research","ror":"https://ror.org/05ymca674","country_code":"US","type":"facility","lineage":["https://openalex.org/I144112489","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Runxuan Yang","raw_affiliation_strings":["BNRist, THBI, IDG/McGovern Institute for Brain Research, Tsinghua University,Department of Computer Science and Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BNRist, THBI, IDG/McGovern Institute for Brain Research, Tsinghua University,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I144112489"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xiaolin Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I144112489","display_name":"McGovern Institute for Brain Research","ror":"https://ror.org/05ymca674","country_code":"US","type":"facility","lineage":["https://openalex.org/I144112489","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaolin Hu","raw_affiliation_strings":["BNRist, THBI, IDG/McGovern Institute for Brain Research, Tsinghua University,Department of Computer Science and Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BNRist, THBI, IDG/McGovern Institute for Brain Research, Tsinghua University,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I144112489"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I144112489"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9735999703407288,"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":0.9735999703407288,"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":0.011599999852478504,"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/T10863","display_name":"Voice and Speech Disorders","score":0.0038999998942017555,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6600000262260437},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5942999720573425},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5564000010490417},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5092999935150146},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.47510001063346863},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.45969998836517334},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4180999994277954},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.37220001220703125},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.3529999852180481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7821999788284302},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6600000262260437},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5942999720573425},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5564000010490417},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5092999935150146},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.47510001063346863},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4749000072479248},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.45969998836517334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43529999256134033},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4180999994277954},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.37220001220703125},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3292999863624573},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31349998712539673},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3095000088214874},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.3003999888896942},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.2572000026702881}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127851351","https://openalex.org/W2153331367","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2952218014","https://openalex.org/W2962780374","https://openalex.org/W2964058413","https://openalex.org/W2972541922","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3042857426","https://openalex.org/W3163652268","https://openalex.org/W3205879560","https://openalex.org/W4224936432","https://openalex.org/W4283021642","https://openalex.org/W4372271367","https://openalex.org/W4375869299","https://openalex.org/W4375928773","https://openalex.org/W4402112499","https://openalex.org/W4410087476"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"CNN-based":[1],"speech":[2,21,56,174],"separation":[3,22,57,122,175],"models":[4,23,156],"face":[5,34],"local":[6],"receptive":[7],"field":[8],"limitations":[9],"and":[10,19,40,88,116,134,136],"cannot":[11],"effectively":[12,80],"capture":[13,94],"long":[14,46],"time":[15,87],"dependencies.":[16],"Although":[17],"LSTM":[18],"Transformer-based":[20],"can":[24],"avoid":[25],"this":[26,50],"problem,":[27],"their":[28],"high":[29],"complexity":[30],"causes":[31],"them":[32],"to":[33,93,112,152],"the":[35,65,82,86,102,106,110,132,141,164,170],"challenge":[36],"of":[37,166,173],"computational":[38,99,159],"resources":[39],"inference":[41],"efficiency":[42],"when":[43],"dealing":[44],"with":[45,74,97,157],"audio.":[47],"To":[48],"address":[49],"challenge,":[51],"we":[52],"introduce":[53],"an":[54],"innovative":[55],"method":[58],"called":[59],"SPMamba.":[60],"This":[61],"model":[62,81,111],"builds":[63],"upon":[64],"robust":[66],"TF-GridNet":[67],"architecture,":[68],"replacing":[69],"its":[70],"traditional":[71],"BLSTM":[72],"modules":[73,79,108],"bidirectional":[75,103],"Mamba":[76,107],"modules.":[77],"These":[78,161],"spatiotemporal":[83],"relationships":[84],"between":[85],"frequency":[89],"dimensions,":[90],"allowing":[91],"SPMamba":[92,148,167,183],"long-range":[95],"dependencies":[96],"linear":[98],"complexity.":[100,160],"Specifically,":[101],"processing":[104],"within":[105],"enables":[109],"utilize":[113],"both":[114],"past":[115],"future":[117],"contextual":[118],"information,":[119],"thereby":[120],"enhancing":[121],"performance.":[123],"Extensive":[124],"experiments":[125],"were":[126],"conducted":[127],"on":[128],"public":[129],"datasets,":[130],"including":[131],"WSJ0-2Mix":[133],"WHAM!":[135],"Libri2Mix,":[137],"as":[138,140],"well":[139],"newly":[142],"constructed":[143],"Echo2Mix":[144],"dataset,":[145],"demonstrated":[146],"that":[147],"achieved":[149],"superior":[150],"results":[151],"previous":[153],"state-of-the-art":[154],"(SOTA)":[155],"reduced":[158],"findings":[162],"highlight":[163],"effectiveness":[165],"in":[168,176],"addressing":[169],"intricate":[171],"challenges":[172],"complex":[177],"environments.":[178],"The":[179],"source":[180],"code":[181],"for":[182],"is":[184],"publicly":[185],"accessible":[186],"at":[187],"https://anonymous.4open.science/r/SPMamba-ICME/.":[188]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}