{"id":"https://openalex.org/W4416250918","doi":"https://doi.org/10.1109/waspaa66052.2025.11230983","title":"Long-Context Modeling Networks for Monaural Speech Enhancement: A Comparative Study","display_name":"Long-Context Modeling Networks for Monaural Speech Enhancement: A Comparative Study","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416250918","doi":"https://doi.org/10.1109/waspaa66052.2025.11230983"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5042675934","display_name":"Qiquan Zhang","orcid":"https://orcid.org/0000-0001-5089-6317"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qiquan Zhang","raw_affiliation_strings":["The University of New South Wales,Sydney,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of New South Wales,Sydney,Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102993135","display_name":"Moran Chen","orcid":"https://orcid.org/0000-0002-4818-369X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Moran Chen","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012273069","display_name":"Zuojian Song","orcid":"https://orcid.org/0009-0006-4162-3046"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zeyang Song","raw_affiliation_strings":["National University of Singapore,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091096053","display_name":"Hexin Liu","orcid":"https://orcid.org/0000-0002-3998-9229"},"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":"Hexin Liu","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362465","display_name":"Xiangyu Zhang","orcid":"https://orcid.org/0000-0003-2138-4608"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiangyu Zhang","raw_affiliation_strings":["The University of New South Wales,Sydney,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of New South Wales,Sydney,Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen Research Institute of Big Data,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen Research Institute of Big Data,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9794999957084656,"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":0.9794999957084656,"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/T11448","display_name":"Face recognition and analysis","score":0.007799999788403511,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.002899999963119626,"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/monaural","display_name":"Monaural","score":0.6022999882698059},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5622000098228455},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5440000295639038},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5175999999046326},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.40549999475479126},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.3668999969959259}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6977999806404114},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6449000239372253},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.6022999882698059},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5622000098228455},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5440000295639038},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5175999999046326},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40389999747276306},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.3668999969959259},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.336899995803833},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3197000026702881},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.3061999976634979},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2777999937534332},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C104122410","wikidata":"https://www.wikidata.org/wiki/Q1416406","display_name":"Network model","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320317364","display_name":"BD","ror":"https://ror.org/048vrgr14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1494198834","https://openalex.org/W1506438021","https://openalex.org/W1897240248","https://openalex.org/W2038484192","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2144404214","https://openalex.org/W2159202424","https://openalex.org/W2291877678","https://openalex.org/W2396174604","https://openalex.org/W2515728195","https://openalex.org/W2516001803","https://openalex.org/W2914067823","https://openalex.org/W2950962438","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2971417062","https://openalex.org/W3017350693","https://openalex.org/W3024436989","https://openalex.org/W3026111682","https://openalex.org/W3095820034","https://openalex.org/W3097777922","https://openalex.org/W3097945073","https://openalex.org/W3158779859","https://openalex.org/W4200483526","https://openalex.org/W4221162870","https://openalex.org/W4253928870","https://openalex.org/W4295934635","https://openalex.org/W4296069339","https://openalex.org/W4312271884","https://openalex.org/W4372265870","https://openalex.org/W4380434618","https://openalex.org/W4384080510","https://openalex.org/W4385245566","https://openalex.org/W4385807442","https://openalex.org/W4388979610","https://openalex.org/W4392904390","https://openalex.org/W4402112499","https://openalex.org/W4404783499","https://openalex.org/W4405974256","https://openalex.org/W4406322685","https://openalex.org/W4410087476","https://openalex.org/W4411203684"],"related_works":[],"abstract_inverted_index":{"Advanced":[0],"long-context":[1],"modeling":[2,53],"backbone":[3],"networks,":[4],"such":[5],"as":[6,55],"Transformer,":[7,81],"Conformer,":[8,82],"and":[9,21,42,54,72,77,84,94,99,106,113],"Mamba,":[10,83],"have":[11],"demonstrated":[12],"state-of-the-art":[13],"performance":[14,103],"in":[15,51,69],"speech":[16,31,70,119],"enhancement.":[17],"However,":[18],"a":[19,29,39,56,74,88],"systematic":[20],"comprehensive":[22,75],"comparative":[23],"study":[24],"of":[25,45,67,79],"these":[26],"backbones":[27,86],"within":[28,87],"unified":[30,89],"enhancement":[32],"framework":[33],"remains":[34],"lacking.":[35],"In":[36,60],"addition,":[37],"xLSTM,":[38],"more":[40],"recent":[41],"efficient":[43],"variant":[44],"LSTM,":[46],"has":[47],"shown":[48],"promising":[49],"results":[50],"language":[52],"general-purpose":[57],"vision":[58],"backbone.":[59],"this":[61],"paper,":[62],"we":[63],"investigate":[64],"the":[65,80,125],"capability":[66],"xLSTM":[68,85,98,122],"enhancement,":[71],"conduct":[73],"comparison":[76],"analysis":[78],"framework,":[90],"considering":[91],"both":[92],"causal":[93],"noncausal":[95],"configurations.":[96],"Overall,":[97],"Mamba":[100,108],"achieve":[101],"better":[102],"than":[104],"Transformer":[105],"Conformer.":[107],"demonstrates":[109],"significantly":[110],"superior":[111],"training":[112],"inference":[114],"efficiency,":[115],"particularly":[116],"for":[117],"long":[118],"inputs,":[120],"whereas":[121],"suffers":[123],"from":[124],"slowest":[126],"processing":[127],"speed.":[128]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}