{"id":"https://openalex.org/W4406461266","doi":"https://doi.org/10.1109/slt61566.2024.10832332","title":"An Investigation of Incorporating Mamba For Speech Enhancement","display_name":"An Investigation of Incorporating Mamba For Speech Enhancement","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461266","doi":"https://doi.org/10.1109/slt61566.2024.10832332"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5030791258","display_name":"Rong Chao","orcid":"https://orcid.org/0000-0001-6930-959X"},"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":"Rong Chao","raw_affiliation_strings":["Academia Sinica"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037186260","display_name":"Hao\u2010Wen Cheng","orcid":"https://orcid.org/0000-0003-1940-7962"},"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":"Wen-Huang Cheng","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078641012","display_name":"Moreno La Quatra","orcid":"https://orcid.org/0000-0001-8838-064X"},"institutions":[{"id":"https://openalex.org/I246010334","display_name":"Universit\u00e0 degli Studi di Enna Kore","ror":"https://ror.org/04vd28p53","country_code":"IT","type":"education","lineage":["https://openalex.org/I246010334"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Moreno La Quatra","raw_affiliation_strings":["Kore University of Enna"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kore University of Enna","institution_ids":["https://openalex.org/I246010334"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659476","display_name":"Sabato Marco Siniscalchi","orcid":"https://orcid.org/0000-0002-0770-0507"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sabato Marco Siniscalchi","raw_affiliation_strings":["University of Palermo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Palermo","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020376803","display_name":"Chao-Han Huck Yang","orcid":"https://orcid.org/0000-0003-2879-8811"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao-Han Huck Yang","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071471469","display_name":"Szu\u2010Wei Fu","orcid":"https://orcid.org/0000-0002-3487-8212"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Szu-Wei Fu","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":19.5661,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.99682018,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"302","last_page":"308"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9911999702453613,"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/T13289","display_name":"Infant Health and Development","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5620124340057373},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4846080243587494}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5620124340057373},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4846080243587494}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt61566.2024.10832332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unipa.it:10447/673127","is_oa":false,"landing_page_url":"https://hdl.handle.net/10447/673127","pdf_url":null,"source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"info:eu-repo/semantics/bookPart"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2078528584","https://openalex.org/W2094721231","https://openalex.org/W2106244103","https://openalex.org/W2141998673","https://openalex.org/W2402901296","https://openalex.org/W2405774341","https://openalex.org/W2594607416","https://openalex.org/W2603567530","https://openalex.org/W2746457594","https://openalex.org/W2755891984","https://openalex.org/W2889442120","https://openalex.org/W2962866211","https://openalex.org/W2963045393","https://openalex.org/W2963341071","https://openalex.org/W2964058413","https://openalex.org/W3015219411","https://openalex.org/W3016447038","https://openalex.org/W3016912202","https://openalex.org/W3049226960","https://openalex.org/W3097945073","https://openalex.org/W3098805155","https://openalex.org/W3158779859","https://openalex.org/W3197912330","https://openalex.org/W4232282348","https://openalex.org/W4253928870","https://openalex.org/W4296069347","https://openalex.org/W4313442864","https://openalex.org/W4385807442","https://openalex.org/W4385822340","https://openalex.org/W4385822478","https://openalex.org/W4386044615","https://openalex.org/W4388107429","https://openalex.org/W4389326242","https://openalex.org/W4391582585","https://openalex.org/W4392904222","https://openalex.org/W4393300076","https://openalex.org/W4393943345","https://openalex.org/W4395447416","https://openalex.org/W4400877621","https://openalex.org/W6762114000","https://openalex.org/W6790758941","https://openalex.org/W6803444062","https://openalex.org/W6839235732","https://openalex.org/W6847363464","https://openalex.org/W6855957182","https://openalex.org/W6858642341","https://openalex.org/W6859298233","https://openalex.org/W6862687296","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/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"This":[0],"work":[1],"aims":[2],"to":[3,28,105],"investigate":[4],"the":[5,18,68,72,112],"use":[6],"of":[7,65,80],"a":[8,62,100,122],"recently":[9],"proposed,":[10],"attention-free,":[11],"scalable":[12],"state-space":[13],"model":[14],"(SSM),":[15],"Mamba,":[16],"for":[17],"speech":[19,127],"enhancement":[20],"(SE)":[21],"task.":[22],"In":[23],"particular,":[24],"we":[25],"employ":[26],"Mamba":[27],"deploy":[29],"different":[30,36],"regression-based":[31],"SE":[32,98,135],"models":[33],"(SEMamba)":[34],"with":[35,71,89,111],"configurations,":[37],"namely":[38],"basic,":[39],"advanced,":[40,73],"causal,":[41],"and":[42],"non-causal.":[43],"Furthermore,":[44],"loss":[45],"functions":[46],"either":[47],"based":[48],"on":[49,67],"signal-level":[50],"distances":[51],"or":[52],"metric-oriented":[53],"are":[54],"considered.":[55],"Experimental":[56],"evidence":[57],"shows":[58],"that":[59],"SEMamba":[60,86,117],"attains":[61],"competitive":[63,131],"PESQ":[64,79],"3.55":[66],"VoiceBank-DEMAND":[69],"dataset":[70],"non-causal":[74,114],"configuration.":[75],"A":[76],"new":[77],"state-of-the-art":[78],"3.69":[81],"is":[82,87,109],"also":[83],"reported":[84],"when":[85],"combined":[88],"Perceptual":[90],"Contrast":[91],"Stretching":[92],"(PCS).":[93],"Compared":[94],"against":[95,133],"Transformed-based":[96],"equivalent":[97],"solutions,":[99],"noticeable":[101],"FLOPs":[102],"reduction":[103],"up":[104],"$\\sim":[106],"12":[107],"\\%$":[108],"observed":[110],"advanced":[113],"configurations.":[115],"Finally,":[116],"can":[118],"be":[119],"used":[120],"as":[121],"pre-processing":[123],"step":[124],"before":[125],"automatic":[126],"recognition":[128],"(ASR),":[129],"showing":[130],"performance":[132],"recent":[134],"solutions.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":17},{"year":2025,"cited_by_count":45},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
