{"id":"https://openalex.org/W7129004500","doi":"https://doi.org/10.48550/arxiv.2602.12986","title":"A two-step approach for speech enhancement in low-SNR scenarios using cyclostationary beamforming and DNNs","display_name":"A two-step approach for speech enhancement in low-SNR scenarios using cyclostationary beamforming and DNNs","publication_year":2026,"publication_date":"2026-02-13","ids":{"openalex":"https://openalex.org/W7129004500","doi":"https://doi.org/10.48550/arxiv.2602.12986"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.12986","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.12986","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2602.12986","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126096833","display_name":"Giovanni Bologni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bologni, Giovanni","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123579971","display_name":"Nicol\u00e1s Arrieta Larraza","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Larraza, Nicol\u00e1s Arrieta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126094995","display_name":"Richard Heusdens","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heusdens, Richard","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5011148355","display_name":"Richard C. Hendriks","orcid":"https://orcid.org/0000-0001-8297-0251"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hendriks, Richard C.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.002899999963119626,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.002199999988079071,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cyclostationary-process","display_name":"Cyclostationary process","score":0.8197000026702881},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7279999852180481},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6692000031471252},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5960999727249146},{"id":"https://openalex.org/keywords/adaptive-beamformer","display_name":"Adaptive beamformer","score":0.4133000075817108},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.3971000015735626},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.3869999945163727},{"id":"https://openalex.org/keywords/aliasing","display_name":"Aliasing","score":0.385699987411499},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.38199999928474426},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.37610000371932983}],"concepts":[{"id":"https://openalex.org/C178351263","wikidata":"https://www.wikidata.org/wiki/Q3922399","display_name":"Cyclostationary process","level":3,"score":0.8197000026702881},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7279999852180481},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6949999928474426},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6692000031471252},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6028000116348267},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5960999727249146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42089998722076416},{"id":"https://openalex.org/C33378366","wikidata":"https://www.wikidata.org/wiki/Q4680719","display_name":"Adaptive beamformer","level":3,"score":0.4133000075817108},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3971000015735626},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C4069607","wikidata":"https://www.wikidata.org/wiki/Q868732","display_name":"Aliasing","level":3,"score":0.385699987411499},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.38199999928474426},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37610000371932983},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C173642442","wikidata":"https://www.wikidata.org/wiki/Q1253346","display_name":"Decimation","level":3,"score":0.33160001039505005},{"id":"https://openalex.org/C114996537","wikidata":"https://www.wikidata.org/wiki/Q4854529","display_name":"Colors of noise","level":3,"score":0.3287999927997589},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C168110828","wikidata":"https://www.wikidata.org/wiki/Q1331626","display_name":"Spectral density","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3010999858379364},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28790000081062317},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.27889999747276306},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.27570000290870667},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.262800008058548},{"id":"https://openalex.org/C2777121530","wikidata":"https://www.wikidata.org/wiki/Q7512739","display_name":"Signal subspace","level":4,"score":0.2623000144958496},{"id":"https://openalex.org/C188414643","wikidata":"https://www.wikidata.org/wiki/Q3001183","display_name":"Harmonics","level":3,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.12986","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.12986","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2602.12986","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.12986","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.41620707511901855,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"Neural":[1],"Networks":[2],"(DNNs)":[3],"often":[4],"struggle":[5],"to":[6,60,65,73],"suppress":[7,61],"noise":[8,24,59,119],"at":[9,128],"low":[10,129],"signal-to-noise":[11],"ratios":[12],"(SNRs).":[13],"This":[14],"paper":[15],"addresses":[16],"speech":[17],"enhancement":[18,67],"in":[19,82],"scenarios":[20],"dominated":[21,115],"by":[22,116],"harmonic":[23,62,172],"and":[25,68,92,99,112],"proposes":[26],"a":[27,49,83,90,100,132,159],"framework":[28],"that":[29,154],"integrates":[30],"cyclostationarity-aware":[31],"preprocessing":[32,50,137],"with":[33,135],"lightweight":[34,93],"DNN-based":[35],"denoising.":[36],"A":[37],"cyclic":[38],"minimum":[39],"power":[40],"distortionless":[41],"response":[42],"(cMPDR)":[43],"spectral":[44,55],"beamformer":[45],"is":[46,80,162],"used":[47],"as":[48,158],"block.":[51],"It":[52],"exploits":[53],"the":[54,74,139,142],"correlations":[56],"of":[57,141],"cyclostationary":[58],"components":[63],"prior":[64,161],"learning-based":[66],"does":[69],"not":[70],"require":[71],"modifications":[72],"DNN":[75,88,125],"architecture.":[76],"The":[77],"proposed":[78],"pipeline":[79],"evaluated":[81],"single-channel":[84],"setting":[85],"using":[86],"two":[87],"architectures:":[89],"simple":[91],"convolutional":[94],"recurrent":[95],"neural":[96],"network":[97,106],"(CRNN),":[98],"state-of-the-art":[101],"model,":[102],"namely":[103],"ultra-low":[104],"complexity":[105],"(ULCNet).":[107],"Experiments":[108],"on":[109,146],"synthetic":[110],"data":[111],"real-world":[113],"recordings":[114],"rotating":[117],"machinery":[118],"demonstrate":[120],"consistent":[121],"improvements":[122],"over":[123],"end-to-end":[124],"baselines,":[126],"particularly":[127],"SNRs.":[130],"Remarkably,":[131],"parameter-efficient":[133],"CRNN":[134],"cMPDR":[136],"surpasses":[138],"performance":[140],"larger":[143],"ULCNet":[144],"operating":[145],"raw":[147],"or":[148],"Wiener-filtered":[149],"inputs.":[150],"These":[151],"results":[152],"indicate":[153],"explicitly":[155],"incorporating":[156],"cyclostationarity":[157],"signal":[160],"more":[163],"effective":[164],"than":[165],"increasing":[166],"model":[167],"capacity":[168],"alone":[169],"for":[170],"suppressing":[171],"interference.":[173]},"counts_by_year":[],"updated_date":"2026-08-16T07:02:28.622633","created_date":"2026-02-17T00:00:00"}