{"id":"https://openalex.org/W4416873918","doi":"https://doi.org/10.1109/ispa66905.2025.11259446","title":"Novel Training Paradigm and Ablation Study on Integrating Background Noise with Variable Accuracy for Noise-Aware Speech Enhancement","display_name":"Novel Training Paradigm and Ablation Study on Integrating Background Noise with Variable Accuracy for Noise-Aware Speech Enhancement","publication_year":2025,"publication_date":"2025-10-29","ids":{"openalex":"https://openalex.org/W4416873918","doi":"https://doi.org/10.1109/ispa66905.2025.11259446"},"language":"en","primary_location":{"id":"doi:10.1109/ispa66905.2025.11259446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispa66905.2025.11259446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 14th International Symposium on Image and Signal Processing and Analysis (ISPA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://biblio.ugent.be/publication/01KBFJT3F0C3BJMK5YR25NTP3N/file/01KBFJW3361SWZBD17GPB27KMR.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101709678","display_name":"Siyuan Song","orcid":"https://orcid.org/0009-0009-3103-686X"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Siyuan Song","raw_affiliation_strings":["Ghent University - imec,IDLab,Department of Electronics and Information Systems,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab,Department of Electronics and Information Systems,Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101890082","display_name":"Haixin Zhao","orcid":"https://orcid.org/0009-0005-3957-8859"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Haixin Zhao","raw_affiliation_strings":["Ghent University - imec,IDLab,Department of Electronics and Information Systems,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab,Department of Electronics and Information Systems,Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081844255","display_name":"Nilesh Madhu","orcid":"https://orcid.org/0000-0001-9131-3309"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Nilesh Madhu","raw_affiliation_strings":["Ghent University - imec,IDLab,Department of Electronics and Information Systems,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab,Department of Electronics and Information Systems,Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45413613,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"157","last_page":"162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9886999726295471,"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":0.9886999726295471,"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":0.006300000008195639,"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":0.7975999712944031},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.713699996471405},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.531000018119812},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5217000246047974},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.5041999816894531},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.45010000467300415},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4327000081539154},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3792000114917755}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7975999712944031},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7333999872207642},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.713699996471405},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.531000018119812},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5217000246047974},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.5041999816894531},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49410000443458557},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.45010000467300415},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4327000081539154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3889999985694885},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3792000114917755},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.34360000491142273},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C123745756","wikidata":"https://www.wikidata.org/wiki/Q1665949","display_name":"Interconnection","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26460000872612},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.2644999921321869}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ispa66905.2025.11259446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispa66905.2025.11259446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 14th International Symposium on Image and Signal Processing and Analysis (ISPA)","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:01KBFJT3F0C3BJMK5YR25NTP3N","is_oa":true,"landing_page_url":"https://biblio.ugent.be/publication/01KBFJT3F0C3BJMK5YR25NTP3N","pdf_url":"https://biblio.ugent.be/publication/01KBFJT3F0C3BJMK5YR25NTP3N/file/01KBFJW3361SWZBD17GPB27KMR.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"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":"ISBN: 9798331577551","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:archive.ugent.be:01KBFJT3F0C3BJMK5YR25NTP3N","is_oa":true,"landing_page_url":"https://biblio.ugent.be/publication/01KBFJT3F0C3BJMK5YR25NTP3N","pdf_url":"https://biblio.ugent.be/publication/01KBFJT3F0C3BJMK5YR25NTP3N/file/01KBFJW3361SWZBD17GPB27KMR.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"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":"ISBN: 9798331577551","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416873918.pdf","grobid_xml":"https://content.openalex.org/works/W4416873918.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2051428568","https://openalex.org/W2067295501","https://openalex.org/W2516342150","https://openalex.org/W2760103357","https://openalex.org/W2763188033","https://openalex.org/W2938737578","https://openalex.org/W2962707588","https://openalex.org/W2973016613","https://openalex.org/W3016163030","https://openalex.org/W3131332223","https://openalex.org/W3158551136","https://openalex.org/W3160005627","https://openalex.org/W3160129476","https://openalex.org/W3161480375","https://openalex.org/W3197042120","https://openalex.org/W4205139742","https://openalex.org/W4308824155","https://openalex.org/W4385245566","https://openalex.org/W4404577561"],"related_works":[],"abstract_inverted_index":{"Training":[0],"noise-aware":[1,53,60,112,128,148,208],"speech":[2,113,157,209],"enhancement":[3,37,114,158],"models":[4],"is":[5,21,144],"inherently":[6],"tricky":[7],"due":[8],"to":[9,23,29,86,108,165,179],"the":[10,14,36,56,75,124,127,133,136,142,147,154,173,176,189,192,199,205],"implicit":[11],"coupling":[12],"with":[13,91,132,153],"estimator":[15],"of":[16,46,58,94,126,135,175,191,204,207],"noise":[17,27,48,65,89,138],"characteristics.":[18],"Thereby,":[19],"it":[20],"difficult":[22],"simultaneously":[24],"investigate":[25],"robust":[26],"representations":[28,49],"encode":[30],"noise-related":[31],"information":[32],"while":[33],"independently":[34],"optimising":[35],"network":[38,215],"architecture":[39,54,216],"for":[40,62,201],"incorporating":[41],"noise-awareness.":[42],"The":[43],"systematic":[44,118,202],"effect":[45,57],"different":[47,59],"on":[50,151],"a":[51,63,81,110,117,221],"given":[52,64],"or":[55],"architectures":[61],"representation":[66],"can,":[67],"therefore,":[68],"not":[69],"be":[70],"easily":[71],"studied.":[72],"To":[73],"decouple":[74],"two":[76,226],"aspects,":[77],"we":[78,104,121,170],"first":[79],"propose":[80],"novel,":[82],"tunable":[83],"data-generation":[84,193],"paradigm":[85],"generate":[87],"reference":[88],"signals":[90],"varying":[92],"degrees":[93],"accuracy":[95,134],"-":[96,186],"reflecting":[97],"estimation":[98],"errors":[99],"expected":[100],"in":[101],"practice.":[102],"Next,":[103],"incorporate":[105],"this":[106,161],"framework":[107,129,149,164],"train":[109],"straightforward":[111],"model.":[115,159],"Through":[116],"ablation":[119],"study,":[120],"show":[122],"that":[123],"performance":[125],"steadily":[130],"improves":[131],"background":[137],"information.":[139],"Also,":[140],"when":[141],"noise-reference":[143],"minimally":[145],"informative,":[146],"performs":[150],"par":[152],"baseline":[155],"(noiseblind)":[156],"Applying":[160],"trained":[162,177],"noiseaware":[163],"realistic":[166],"and":[167,183,217],"real-world":[168],"captures,":[169],"further":[171],"demonstrate":[172],"generalisability":[174],"model":[178],"even":[180],"completely":[181],"unseen":[182],"mismatched":[184],"scenarios":[185],"convincingly":[187],"establishing":[188],"validity":[190],"paradigm.":[194],"This":[195],"work,":[196],"thereby,":[197],"paves":[198],"way":[200],"exploration":[203],"benefit":[206],"enhancement,":[210],"permitting":[211],"simultaneous":[212],"investigation":[213],"into":[214],"noiserepresentations,":[218],"without":[219],"imposing":[220],"limiting":[222],"interconnection":[223],"between":[224],"these":[225],"aspects.":[227]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-12-01T00:00:00"}