{"id":"https://openalex.org/W4408354331","doi":"https://doi.org/10.1109/icassp49660.2025.10890412","title":"Leveraging Joint Spectral and Spatial Learning with MAMBA for Multichannel Speech Enhancement","display_name":"Leveraging Joint Spectral and Spatial Learning with MAMBA for Multichannel Speech Enhancement","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354331","doi":"https://doi.org/10.1109/icassp49660.2025.10890412"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890412","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":"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/A5113382917","display_name":"Wenze Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wenze Ren","raw_affiliation_strings":["National Taiwan University,Graduate Institute of Communication Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Graduate Institute of Communication Engineering","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082226990","display_name":"Haibin Wu","orcid":"https://orcid.org/0000-0002-2453-3691"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Haibin Wu","raw_affiliation_strings":["National Taiwan University,Graduate Institute of Communication Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Graduate Institute of Communication Engineering","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105411292","display_name":"Yi\u2010Cheng Lin","orcid":"https://orcid.org/0009-0005-0969-631X"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Cheng Lin","raw_affiliation_strings":["National Taiwan University,Graduate Institute of Communication Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Graduate Institute of Communication Engineering","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051463746","display_name":"Xuanjun Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Xuanjun Chen","raw_affiliation_strings":["National Taiwan University,Graduate Institute of Communication Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Graduate Institute of Communication Engineering","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030791258","display_name":"Rong Chao","orcid":"https://orcid.org/0000-0001-6930-959X"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Rong Chao","raw_affiliation_strings":["National Taiwan University,Department of Computer Science and Information Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Department of Computer Science and Information Engineering","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071855826","display_name":"Kuo-Hsuan Hung","orcid":"https://orcid.org/0009-0007-0974-4873"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuo-Hsuan Hung","raw_affiliation_strings":["National Taiwan University,Department of Biomedical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Department of Biomedical Engineering","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012212264","display_name":"You-Jin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"You-Jin Li","raw_affiliation_strings":["National Taiwan University,Graduate Institute of Communication Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Graduate Institute of Communication Engineering","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023844498","display_name":"Wen-Yuan Ting","orcid":null},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wen-Yuan Ting","raw_affiliation_strings":["Academia Sinica,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Academia Sinica,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Academia Sinica,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9991000294685364,"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":0.9991000294685364,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9441999793052673,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.920799970626831,"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/joint","display_name":"Joint (building)","score":0.7308929562568665},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7022397518157959},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6424436569213867},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5276203155517578},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3623207211494446},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10191890597343445},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.08629578351974487}],"concepts":[{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7308929562568665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7022397518157959},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6424436569213867},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5276203155517578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3623207211494446},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10191890597343445},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.08629578351974487},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890412","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2127851351","https://openalex.org/W2141998673","https://openalex.org/W2405774341","https://openalex.org/W2923728956","https://openalex.org/W2962866211","https://openalex.org/W2975955714","https://openalex.org/W3015791598","https://openalex.org/W3096408984","https://openalex.org/W3160085755","https://openalex.org/W4296068772","https://openalex.org/W4312219134","https://openalex.org/W4313442864","https://openalex.org/W4372267870","https://openalex.org/W4385822821","https://openalex.org/W4392904014","https://openalex.org/W4399939359","https://openalex.org/W4406461266","https://openalex.org/W4408354310","https://openalex.org/W6770796734","https://openalex.org/W6803444062","https://openalex.org/W6839235732","https://openalex.org/W6859298233","https://openalex.org/W6863679278"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"In":[0],"multichannel":[1,125],"speech":[2,126],"enhancement,":[3,127],"effectively":[4],"capturing":[5],"spatial":[6,37,90,105,120],"and":[7,33,36,76,88,94,106,121,130],"spectral":[8,35,96,107,122,150],"information":[9,91],"across":[10],"different":[11],"microphones":[12],"is":[13],"crucial":[14],"for":[15],"noise":[16],"reduction.":[17],"Traditional":[18],"methods,":[19],"such":[20],"as":[21],"CNN":[22],"or":[23],"LSTM,":[24],"attempt":[25],"to":[26,85,103],"model":[27,64],"the":[28,61,117,137],"temporal":[29,48],"dynamics":[30],"of":[31,71,119],"full-band":[32,87,95],"sub-band":[34,93],"features.":[38],"However,":[39],"these":[40,57],"approaches":[41],"face":[42],"limitations":[43],"in":[44,51,124,148],"fully":[45],"modeling":[46,104,118,149],"complex":[47],"dependencies,":[49],"especially":[50],"dynamic":[52],"acoustic":[53],"environments.":[54],"To":[55],"overcome":[56],"challenges,":[58],"we":[59,141],"modify":[60],"current":[62],"advanced":[63],"McNet":[65,129],"by":[66],"introducing":[67],"an":[68],"improved":[69],"version":[70],"Mamba,":[72],"a":[73,99],"state-space":[74],"model,":[75],"further":[77],"propose":[78],"MCMamba.":[79],"MCMamba":[80,114],"has":[81],"been":[82],"completely":[83],"reengineered":[84],"integrate":[86],"narrow-band":[89],"with":[92],"features,":[97],"providing":[98],"more":[100],"comprehensive":[101],"approach":[102],"information.":[108,151],"Our":[109],"experimental":[110],"results":[111],"demonstrate":[112],"that":[113,143],"significantly":[115],"improves":[116],"features":[123],"outperforming":[128],"achieving":[131],"very":[132],"promis-":[133],"ing":[134],"performance":[135],"on":[136],"CHiME-3":[138],"dataset.":[139],"Additionally,":[140],"find":[142],"Mamba":[144],"performs":[145],"exceptionally":[146],"well":[147]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
