{"id":"https://openalex.org/W4415433649","doi":"https://doi.org/10.21437/interspeech.2025-108","title":"xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement","display_name":"xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433649","doi":"https://doi.org/10.21437/interspeech.2025-108"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-108","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://vbn.aau.dk/ws/files/793477189/kuhne25_interspeech.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111396335","display_name":"Nikolai Lund K\u00fchne","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Nikolai Lund K\u00fchne","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023894109","display_name":"Jan \u00d8stergaard","orcid":"https://orcid.org/0000-0002-3724-6114"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan \u00d8stergaard","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101679595","display_name":"Jesper Jensen","orcid":"https://orcid.org/0000-0003-1478-622X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jesper Jensen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5090108098","display_name":"Zheng\u2010Hua Tan","orcid":"https://orcid.org/0000-0001-6856-8928"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng-Hua Tan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5111396335"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.8348,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94046888,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5148","last_page":"5152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9887999892234802,"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/T13289","display_name":"Infant Health and Development","score":0.9646999835968018,"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/speech-enhancement","display_name":"Speech enhancement","score":0.6948999762535095},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5439000129699707},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5358999967575073},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4652999937534332},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.42750000953674316},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.41990000009536743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.729200005531311},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6948999762535095},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6592000126838684},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5439000129699707},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5358999967575073},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4652999937534332},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.42750000953674316},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.41990000009536743},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3919999897480011},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3903000056743622},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2838999927043915},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.27810001373291016},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.26460000872612}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-108","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/acec6f8b-9cff-420b-b6d5-33531f3c5d7e","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/acec6f8b-9cff-420b-b6d5-33531f3c5d7e","pdf_url":"https://vbn.aau.dk/ws/files/793477189/kuhne25_interspeech.pdf","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"K\u00fchne, N, \u00d8stergaard, J, Jensen, J & Tan, Z-H 2025, xLSTM-SENet : xLSTM for Single-Channel Speech Enhancement. in Interspeech 2025. The International Speech Communication Association (ISCA), INTERSPEECH , pp. 5148-5152, Interspeech 2025, Rotterdam, Netherlands, 17/08/2025. https://doi.org/10.21437/Interspeech.2025-108","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:publications/acec6f8b-9cff-420b-b6d5-33531f3c5d7e","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/acec6f8b-9cff-420b-b6d5-33531f3c5d7e","pdf_url":"https://vbn.aau.dk/ws/files/793477189/kuhne25_interspeech.pdf","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"K\u00fchne, N, \u00d8stergaard, J, Jensen, J & Tan, Z-H 2025, xLSTM-SENet : xLSTM for Single-Channel Speech Enhancement. in Interspeech 2025. The International Speech Communication Association (ISCA), INTERSPEECH , pp. 5148-5152, Interspeech 2025, Rotterdam, Netherlands, 17/08/2025. https://doi.org/10.21437/Interspeech.2025-108","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415433649.pdf","grobid_xml":"https://content.openalex.org/works/W4415433649.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"attention-based":[1],"architectures,":[2],"such":[3,13,93],"as":[4,14,94],"Conformers,":[5],"excel":[6],"in":[7,77],"speech":[8,42,52,78],"enhancement,":[9],"they":[10],"face":[11],"challenges":[12],"scalability":[15],"with":[16],"respect":[17],"to":[18,100],"input":[19],"sequence":[20],"length.":[21],"In":[22],"contrast,":[23],"the":[24,48,81,118],"recently":[25],"proposed":[26],"Extended":[27],"Long":[28],"Short-Term":[29],"Memory":[30],"(xLSTM)":[31],"architecture":[32],"offers":[33],"linear":[34],"scalability.":[35],"However,":[36],"xLSTM-based":[37,50,105],"models":[38],"remain":[39],"unexplored":[40],"for":[41],"enhancement.":[43],"This":[44],"paper":[45],"introduces":[46],"xLSTM-SENet,":[47],"first":[49],"single-channel":[51],"enhancement":[53,79],"system.":[54],"A":[55],"direct":[56],"comparative":[57],"analysis":[58],"reveals":[59],"that":[60],"xLSTM-and":[61],"notably,":[62],"even":[63],"LSTM-can":[64],"match":[65],"or":[66],"outperform":[67],"state-of-the-art":[68,109],"Mamba-":[69,110],"and":[70,97,111],"Conformer-based":[71,112],"systems":[72,113],"across":[73],"various":[74],"model":[75],"sizes":[76],"on":[80,117],"VoiceBank+Demand":[82],"dataset.":[83,120],"Through":[84],"ablation":[85],"studies,":[86],"we":[87],"identify":[88],"key":[89],"architectural":[90],"design":[91],"choices":[92],"exponential":[95],"gating":[96],"bidirectionality":[98],"contributing":[99],"its":[101],"effectiveness.":[102],"Our":[103],"best":[104],"model,":[106],"xLSTM-SENet2,":[107],"outperforms":[108],"of":[114],"similar":[115],"complexity":[116],"Voicebank+DEMAND":[119]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-24T00:00:00"}