{"id":"https://openalex.org/W7225637235","doi":"https://doi.org/10.17586/0021-3454-2026-69-10-903-910","title":"Speech signal quality enhancement based on Mamba and xLSTM architectures","display_name":"Speech signal quality enhancement based on Mamba and xLSTM architectures","publication_year":2026,"publication_date":"2026-11-08","ids":{"openalex":"https://openalex.org/W7225637235","doi":"https://doi.org/10.17586/0021-3454-2026-69-10-903-910"},"language":"en","primary_location":{"id":"doi:10.17586/0021-3454-2026-69-10-903-910","doi":"https://doi.org/10.17586/0021-3454-2026-69-10-903-910","is_oa":true,"landing_page_url":"https://doi.org/10.17586/0021-3454-2026-69-10-903-910","pdf_url":null,"source":{"id":"https://openalex.org/S4306539233","display_name":"\u0418\u0437\u0432\u0435\u0441\u0442\u0438\u044f \u0432\u044b\u0441\u0448\u0438\u0445 \u0443\u0447\u0435\u0431\u043d\u044b\u0445 \u0437\u0430\u0432\u0435\u0434\u0435\u043d\u0438\u0439. \u041f\u0440\u0438\u0431\u043e\u0440\u043e\u0441\u0442\u0440\u043e\u0435\u043d\u0438\u0435","issn_l":"0021-3454","issn":["0021-3454","2500-0381"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["russia-white-list-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Instrument Engineering","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.17586/0021-3454-2026-69-10-903-910","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161344228","display_name":"D. V. Ivanko","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1313323035","display_name":"Russian Academy of Sciences","ror":"https://ror.org/05qrfxd25","country_code":"RU","type":"government","lineage":["https://openalex.org/I1313323035"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"D. V. Ivanko","raw_affiliation_strings":["St. Petersburg Federal Research Center of the RAS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"St. Petersburg Federal Research Center of the RAS","institution_ids":["https://openalex.org/I1313323035"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5161344228"],"corresponding_institution_ids":["https://openalex.org/I1313323035"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"69","issue":"10","first_page":"903","last_page":"910"},"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":0.00019999999494757503,"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/T11019","display_name":"Image Enhancement Techniques","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"speech enhancement","score":0.9940000176429749},{"id":"https://openalex.org/keywords/speech-intelligibility","display_name":"speech intelligibility","score":0.6959999799728394},{"id":"https://openalex.org/keywords/acoustic-noise","display_name":"acoustic noise","score":0.7319999933242798},{"id":"https://openalex.org/keywords/mamba","display_name":"Mamba","score":0.7990000247955322},{"id":"https://openalex.org/keywords/xlstm","display_name":"xLSTM","score":0.9900000095367432},{"id":"https://openalex.org/keywords/voicebank-demand","display_name":"VoiceBank-DEMAND","score":0.8569999933242798},{"id":"https://openalex.org/keywords/speech-quality-metrics","display_name":"speech quality metrics","score":0.5770000219345093},{"id":"https://openalex.org/keywords/neural-network-comparison","display_name":"neural network comparison","score":0.3160000145435333}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.8773999810218811},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6504999995231628},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6456000208854675},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6365000009536743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6259999871253967},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.36660000681877136},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.35359999537467957},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3337000012397766},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3034000098705292},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.29809999465942383},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C168110828","wikidata":"https://www.wikidata.org/wiki/Q1331626","display_name":"Spectral density","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.25119999051094055},{"id":"https://openalex.org/C2983668108","wikidata":"https://www.wikidata.org/wiki/Q280453","display_name":"Spectral analysis","level":3,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.17586/0021-3454-2026-69-10-903-910","doi":"https://doi.org/10.17586/0021-3454-2026-69-10-903-910","is_oa":true,"landing_page_url":"https://doi.org/10.17586/0021-3454-2026-69-10-903-910","pdf_url":null,"source":{"id":"https://openalex.org/S4306539233","display_name":"\u0418\u0437\u0432\u0435\u0441\u0442\u0438\u044f \u0432\u044b\u0441\u0448\u0438\u0445 \u0443\u0447\u0435\u0431\u043d\u044b\u0445 \u0437\u0430\u0432\u0435\u0434\u0435\u043d\u0438\u0439. \u041f\u0440\u0438\u0431\u043e\u0440\u043e\u0441\u0442\u0440\u043e\u0435\u043d\u0438\u0435","issn_l":"0021-3454","issn":["0021-3454","2500-0381"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["russia-white-list-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Instrument Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.17586/0021-3454-2026-69-10-903-910","doi":"https://doi.org/10.17586/0021-3454-2026-69-10-903-910","is_oa":true,"landing_page_url":"https://doi.org/10.17586/0021-3454-2026-69-10-903-910","pdf_url":null,"source":{"id":"https://openalex.org/S4306539233","display_name":"\u0418\u0437\u0432\u0435\u0441\u0442\u0438\u044f \u0432\u044b\u0441\u0448\u0438\u0445 \u0443\u0447\u0435\u0431\u043d\u044b\u0445 \u0437\u0430\u0432\u0435\u0434\u0435\u043d\u0438\u0439. \u041f\u0440\u0438\u0431\u043e\u0440\u043e\u0441\u0442\u0440\u043e\u0435\u043d\u0438\u0435","issn_l":"0021-3454","issn":["0021-3454","2500-0381"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["russia-white-list-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Instrument Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W3090496396","https://openalex.org/W3197729725","https://openalex.org/W4321375307","https://openalex.org/W4380434618","https://openalex.org/W4385807442","https://openalex.org/W4388430648","https://openalex.org/W4389326242","https://openalex.org/W4392908343","https://openalex.org/W4406461266","https://openalex.org/W4415092563","https://openalex.org/W4415433286","https://openalex.org/W4415433649","https://openalex.org/W4415795940"],"related_works":["https://openalex.org/W4415433649","https://openalex.org/W4416250918","https://openalex.org/W4408355634","https://openalex.org/W4402402364","https://openalex.org/W7204536941","https://openalex.org/W4406461266","https://openalex.org/W7143671090","https://openalex.org/W7213545368","https://openalex.org/W7123237215","https://openalex.org/W4396519789"],"abstract_inverted_index":{"Improving":[0],"the":[1,5,12,22,71,84,115,119,123,133],"quality":[2,105],"\u2014":[3,7],"specifically":[4],"intelligibility":[6,94],"of":[8,14,24,31,114,139,145,155],"speech":[9,34,168],"signals":[10],"in":[11,21,112,137,149],"presence":[13],"acoustic":[15],"noise":[16],"remains":[17],"a":[18,48,54,60,151,161],"key":[19],"challenge":[20],"field":[23],"digital":[25],"signal":[26,169],"processing.":[27],"A":[28],"comparative":[29,153],"analysis":[30],"neural":[32],"network-based":[33],"enhancement":[35],"methods":[36],"utilizing":[37,62],"Mamba":[38,57,156],"and":[39,59,66,103,157],"xLSTM":[40,63,158],"architectures":[41,159],"is":[42],"presented.":[43],"Three":[44],"configurations":[45],"are":[46,68],"implemented:":[47],"baseline":[49],"model":[50,86,121],"based":[51],"on":[52],"MP-SENet,":[53],"version":[55,61],"incorporating":[56],"blocks,":[58],"blocks.":[64],"Training":[65],"testing":[67],"conducted":[69],"using":[70],"VoiceBank+DEMAND":[72],"dataset,":[73],"with":[74],"performance":[75,89],"evaluated":[76],"through":[77],"objective":[78],"metrics.":[79],"Experimental":[80],"results":[81],"indicate":[82],"that":[83],"xLSTM-based":[85],"demonstrates":[87],"superior":[88],"across":[90],"most":[91],"metrics,":[92],"including":[93],"(ESTOI":[95],"=":[96,101,107],"0.868),":[97],"spectral":[98],"accuracy":[99],"(MCD":[100],"1.98),":[102],"perceptual":[104],"(DNSMOS":[106],"3.201),":[108],"trailing":[109],"only":[110],"MP-SENet":[111],"terms":[113,138],"PESQ":[116],"score.":[117],"While":[118],"Mamba-based":[120],"features":[122],"fewest":[124],"parameters":[125],"(1.3":[126],"million),":[127],"it":[128],"consistently":[129],"underperforms":[130],"compared":[131],"to":[132],"other":[134],"two":[135],"approaches":[136],"reconstruction":[140],"quality.":[141,170],"The":[142],"scientific":[143],"novelty":[144],"this":[146],"work":[147],"lies":[148],"conducting":[150],"comprehensive":[152],"study":[154],"within":[160],"unified":[162],"experimental":[163],"framework,":[164],"aimed":[165],"at":[166],"enhancing":[167]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}