{"id":"https://openalex.org/W4416429139","doi":"https://doi.org/10.1109/access.2025.3635221","title":"Two-Stage Speech Enhancement Framework: Balancing Spectral Suppression and Compensation","display_name":"Two-Stage Speech Enhancement Framework: Balancing Spectral Suppression and Compensation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416429139","doi":"https://doi.org/10.1109/access.2025.3635221"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3635221","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3635221","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3635221","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109656171","display_name":"Hyeong Koh","orcid":"https://orcid.org/0009-0004-7890-2810"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeong Il Koh","raw_affiliation_strings":["Department of Medical and Biological Engineering, Graduate School, Kyungpook National University, Daegu, Republic of Korea","Department of Medical & Biological Engineering, Graduate School, Kyungpook National University, Daegu, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0004-7890-2810","affiliations":[{"raw_affiliation_string":"Department of Medical and Biological Engineering, Graduate School, Kyungpook National University, Daegu, Republic of Korea","institution_ids":["https://openalex.org/I31419693"]},{"raw_affiliation_string":"Department of Medical & Biological Engineering, Graduate School, Kyungpook National University, Daegu, Republic of Korea","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036804508","display_name":"Myoung Nam Kim","orcid":"https://orcid.org/0009-0006-4889-878X"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Myoung Nam Kim","raw_affiliation_strings":["Department of Biomedical Engineering, School of Medicine, Kyungpook National University, Daegu, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0006-4889-878X","affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering, School of Medicine, Kyungpook National University, Daegu, Republic of Korea","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001197940","display_name":"Sungdae Na","orcid":"https://orcid.org/0000-0002-9261-0492"},"institutions":[{"id":"https://openalex.org/I2801673063","display_name":"Kyungpook National University Hospital","ror":"https://ror.org/04qn0xg47","country_code":"KR","type":"healthcare","lineage":["https://openalex.org/I2801673063","https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungdae Na","raw_affiliation_strings":["Department of Biomedical Engineering, Kyungpook National University Hospital, Daegu, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-9261-0492","affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering, Kyungpook National University Hospital, Daegu, Republic of Korea","institution_ids":["https://openalex.org/I2801673063"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38053857,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"198347","last_page":"198357"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9952999949455261,"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":0.9952999949455261,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.001500000013038516,"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"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.0013000000035390258,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.8252999782562256},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6212999820709229},{"id":"https://openalex.org/keywords/compensation","display_name":"Compensation (psychology)","score":0.588699996471405},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5148000121116638},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.48179998993873596},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4611000120639801},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.46050000190734863},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.41179999709129333},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.4041999876499176}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.8252999782562256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7505999803543091},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6262999773025513},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6212999820709229},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.588699996471405},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5148000121116638},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.48179998993873596},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4611000120639801},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.46050000190734863},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.41179999709129333},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.4041999876499176},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.36959999799728394},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.3499000072479248},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C168110828","wikidata":"https://www.wikidata.org/wiki/Q1331626","display_name":"Spectral density","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C114996537","wikidata":"https://www.wikidata.org/wiki/Q4854529","display_name":"Colors of noise","level":3,"score":0.3089999854564667},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C2987345804","wikidata":"https://www.wikidata.org/wiki/Q583234","display_name":"Noise suppression","level":3,"score":0.30070000886917114},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2976999878883362},{"id":"https://openalex.org/C152822103","wikidata":"https://www.wikidata.org/wiki/Q7575207","display_name":"Spectral shape analysis","level":3,"score":0.2939999997615814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27480000257492065},{"id":"https://openalex.org/C89631360","wikidata":"https://www.wikidata.org/wiki/Q1428766","display_name":"Phase noise","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2596000134944916},{"id":"https://openalex.org/C81299745","wikidata":"https://www.wikidata.org/wiki/Q334269","display_name":"Transfer function","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3635221","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3635221","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:5cfde1856d154fe5a9724f3909a3a80a","is_oa":true,"landing_page_url":"https://doaj.org/article/5cfde1856d154fe5a9724f3909a3a80a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 198347-198357 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3635221","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3635221","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5440999454","display_name":null,"funder_award_id":"NRF-2022R1A2C2009716","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G7433591212","display_name":null,"funder_award_id":"RS-2023-00279169","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Speech":[0],"enhancement":[1],"(SE)":[2],"aims":[3],"to":[4,187],"preserve":[5],"speech":[6,20,43,49,80,91,185],"components":[7,21,63],"while":[8],"removing":[9],"noise":[10,46,56,62,82],"that":[11,39,70,99,148,171],"degrades":[12],"signal":[13],"quality.":[14],"However,":[15],"existing":[16,188],"methods":[17],"often":[18],"distort":[19],"by":[22,44,64,123],"over-suppressing":[23],"noise.":[24],"This":[25],"paper":[26],"proposes":[27],"a":[28,66,94],"two-stage":[29],"SE":[30,189],"framework":[31],"called":[32],"the":[33,52,55,85,90,110,113,126,129,133,137,141,153,163,172,180],"suppression":[34,57],"and":[35,48,74,106,132,165,178],"compensation":[36,116],"network":[37],"(SCNet)":[38],"estimates":[40,71],"high-quality":[41],"target":[42],"balancing":[45],"reduction":[47],"preservation.":[50],"In":[51,109],"first":[53],"stage,":[54,112],"module":[58,97,117],"(NS-Module)":[59],"removes":[60],"major":[61],"modeling":[65],"complex":[67],"mask":[68],"function":[69,143],"both":[72,104],"magnitude":[73],"phase":[75],"information.":[76],"The":[77,159],"NS-Module":[78],"distinguishes":[79],"from":[81,136],"based":[83],"on":[84,125,162],"regular":[86],"energy":[87],"distribution":[88],"of":[89,184],"spectrum,":[92],"utilizing":[93],"time-frequency":[95],"convolutional":[96],"(TFCM)":[98],"models":[100],"long-range":[101],"dependencies":[102],"across":[103],"time":[105],"frequency":[107],"dimensions.":[108],"second":[111],"spectral":[114,121,182],"detail":[115],"(SDC-Module)":[118],"restores":[119,179],"missing":[120],"details":[122],"focusing":[124],"difference":[127],"between":[128],"original":[130],"spectrum":[131,135],"enhanced":[134],"previous":[138],"stage.":[139],"Additionally,":[140],"loss":[142],"includes":[144],"an":[145,156],"asymmetric":[146],"component":[147],"penalizes":[149],"over-suppressed":[150],"spectra,":[151],"guiding":[152],"model":[154],"toward":[155],"optimal":[157],"balance.":[158],"experimental":[160],"results":[161],"DNS-Challenge":[164],"VoiceBank":[166],"+":[167],"DEMAND":[168],"datasets":[169],"demonstrate":[170],"proposed":[173],"method":[174],"more":[175],"effectively":[176],"captures":[177],"inherent":[181],"structure":[183],"compared":[186],"models.":[190]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-20T00:00:00"}