{"id":"https://openalex.org/W4409356263","doi":"https://doi.org/10.1109/lsp.2025.3560237","title":"Speech Conv-Mamba: Selective Structured State Space Model With Temporal Dilated Convolution for Efficient Speech Separation","display_name":"Speech Conv-Mamba: Selective Structured State Space Model With Temporal Dilated Convolution for Efficient Speech Separation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409356263","doi":"https://doi.org/10.1109/lsp.2025.3560237"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3560237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3560237","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/A5032068623","display_name":"Debang Liu","orcid":"https://orcid.org/0000-0002-7411-9683"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Debang Liu","raw_affiliation_strings":["School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425383","display_name":"Tianqi Zhang","orcid":"https://orcid.org/0000-0002-9116-040X"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianqi Zhang","raw_affiliation_strings":["School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113097577","display_name":"Ying Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Wei","raw_affiliation_strings":["School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011911524","display_name":"Chen Yi","orcid":"https://orcid.org/0000-0002-2844-5787"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Yi","raw_affiliation_strings":["School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026658144","display_name":"Mads Gr\u00e6sb\u00f8ll Christensen","orcid":"https://orcid.org/0000-0003-3586-7969"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Mads Gr\u00e6sb\u00f8ll Christensen","raw_affiliation_strings":["Audio Analysis Lab, CREATE, Aalborg University, Aalborg, Denmark"],"affiliations":[{"raw_affiliation_string":"Audio Analysis Lab, CREATE, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5032068623"],"corresponding_institution_ids":["https://openalex.org/I10535382"],"apc_list":null,"apc_paid":null,"fwci":5.4326,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.94871413,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"2015","last_page":"2019"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9976000189781189,"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/T11309","display_name":"Music and Audio Processing","score":0.9555000066757202,"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/convolution","display_name":"Convolution (computer science)","score":0.6927440762519836},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5560483336448669},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5279349684715271},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5245766043663025},{"id":"https://openalex.org/keywords/overlap\u2013add-method","display_name":"Overlap\u2013add method","score":0.4670259952545166},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24342387914657593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2299937903881073},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.14324524998664856},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.09506216645240784},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08237510919570923}],"concepts":[{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6927440762519836},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5560483336448669},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5279349684715271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5245766043663025},{"id":"https://openalex.org/C181002996","wikidata":"https://www.wikidata.org/wiki/Q1611641","display_name":"Overlap\u2013add method","level":5,"score":0.4670259952545166},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24342387914657593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2299937903881073},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.14324524998664856},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.09506216645240784},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08237510919570923},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.0},{"id":"https://openalex.org/C76563020","wikidata":"https://www.wikidata.org/wiki/Q4817582","display_name":"Fractional Fourier transform","level":4,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2025.3560237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3560237","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:pure.atira.dk:publications/e40c5ac9-d0ac-4ea1-b693-541d381713ec","is_oa":false,"landing_page_url":"https://vbn.aau.dk/da/publications/e40c5ac9-d0ac-4ea1-b693-541d381713ec","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Liu, D, Zhang, T, Wei, Y, Yi, C & Christensen, M G 2025, 'Speech Conv-Mamba : Selective Structured State Space Model With Temporal Dilated Convolution for Efficient Speech Separation', IEEE Signal Processing Letters, vol. 32, pp. 2015-2019. https://doi.org/10.1109/LSP.2025.3560237","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1677182931","https://openalex.org/W1991139021","https://openalex.org/W2013608223","https://openalex.org/W2015143272","https://openalex.org/W2127851351","https://openalex.org/W2143169494","https://openalex.org/W2510642588","https://openalex.org/W2550143307","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962785940","https://openalex.org/W2962866211","https://openalex.org/W2962935966","https://openalex.org/W3015199127","https://openalex.org/W3025800305","https://openalex.org/W3042857426","https://openalex.org/W3095717210","https://openalex.org/W3096893582","https://openalex.org/W3163652268","https://openalex.org/W4375869299","https://openalex.org/W4385245566","https://openalex.org/W4392904741","https://openalex.org/W4393238158","https://openalex.org/W4403152483","https://openalex.org/W6631190155","https://openalex.org/W6746023985","https://openalex.org/W6749029207","https://openalex.org/W6755977528","https://openalex.org/W6760897771","https://openalex.org/W6803444062","https://openalex.org/W6803594737","https://openalex.org/W6810325043","https://openalex.org/W6859298233","https://openalex.org/W6860720708","https://openalex.org/W6860915106","https://openalex.org/W6862087182","https://openalex.org/W6875940788"],"related_works":["https://openalex.org/W2267589039","https://openalex.org/W2369791303","https://openalex.org/W4372260258","https://openalex.org/W2133280289","https://openalex.org/W2360069155","https://openalex.org/W2759540840","https://openalex.org/W2169963286","https://openalex.org/W4254230825","https://openalex.org/W2919798019","https://openalex.org/W2159795102"],"abstract_inverted_index":{"As":[0],"a":[1,30,43],"selective":[2],"state":[3],"space":[4],"model,":[5,34],"Mamba":[6,22,41,71],"exhibits":[7],"outstanding":[8],"performance":[9],"and":[10,51,57,70,86,99,122],"efficiency":[11],"in":[12,17],"sequence":[13],"modeling":[14],"tasks.":[15],"Therefore,":[16],"this":[18,38],"paper,":[19],"we":[20,64],"use":[21],"as":[23],"the":[24,49,74,84,91],"fundamental":[25],"network":[26,46,53,76],"component":[27],"to":[28,47,72],"construct":[29],"novel":[31],"speech":[32,61],"separation":[33,75,78,103],"Speech":[35,94],"Conv-Mamba.":[36],"Specifically,":[37],"model":[39,93,115],"embeds":[40],"within":[42],"U-shaped":[44],"convolutional":[45],"build":[48],"encoder":[50],"decoder":[52],"for":[54,77],"high-dimensional":[55],"representation":[56],"waveform":[58],"reconstruction":[59],"of":[60,101,113],"signals.":[62],"Additionally,":[63],"stack":[65],"multiple":[66],"temporal":[67],"dilated":[68],"convolutions":[69],"create":[73],"task.":[79],"Our":[80],"comparative":[81],"experiments":[82],"on":[83,105],"GRID2Mix":[85],"Libri2Mix":[87],"datasets":[88,107],"demonstrate":[89],"that":[90],"proposed":[92],"Conv-Mamba,":[95],"which":[96],"achieves":[97],"98%":[98],"89%":[100],"SepFormer's":[102],"accuracy":[104],"two":[106],"using":[108],"only":[109],"9%":[110],"(2.4":[111],"M)":[112],"its":[114],"size,":[116],"provides":[117],"much":[118],"less":[119],"computational":[120],"complexity":[121],"training":[123],"cost.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}