{"id":"https://openalex.org/W7134857896","doi":"https://doi.org/10.48550/arxiv.2603.07471","title":"Towards Lightweight Adaptation of Speech Enhancement Models in Real-World Environments","display_name":"Towards Lightweight Adaptation of Speech Enhancement Models in Real-World Environments","publication_year":2026,"publication_date":"2026-03-08","ids":{"openalex":"https://openalex.org/W7134857896","doi":"https://doi.org/10.48550/arxiv.2603.07471"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2603.07471","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011611391","display_name":"Longbiao Cheng","orcid":"https://orcid.org/0000-0002-0635-1480"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Longbiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128665265","display_name":"Shih-Chii Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Shih-Chii","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29704764,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9897000193595886,"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":0.9897000193595886,"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":0.0027000000700354576,"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":0.002300000051036477,"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/speech-enhancement","display_name":"Speech enhancement","score":0.7807999849319458},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.703499972820282},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.6333000063896179},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5680000185966492},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5062000155448914},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4648999869823456},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.33090001344680786},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.3278999924659729}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.781000018119812},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7807999849319458},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.703499972820282},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.6333000063896179},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6105999946594238},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5680000185966492},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5062000155448914},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4648999869823456},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.320499986410141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31060001254081726},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C2986800882","wikidata":"https://www.wikidata.org/wiki/Q7168187","display_name":"Performance enhancement","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.29019999504089355},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C2988494973","wikidata":"https://www.wikidata.org/wiki/Q179448","display_name":"Noise immunity","level":3,"score":0.2734000086784363},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.25540000200271606},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25270000100135803},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2603.07471","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2603.07471","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.07471","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"pmh:doi:10.48550/arxiv.2603.07471","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"studies":[1],"have":[2],"shown":[3],"that":[4,55,92],"post-deployment":[5],"adaptation":[6,41,142],"can":[7],"improve":[8],"the":[9,85,100],"robustness":[10],"of":[11,99,143],"speech":[12,144],"enhancement":[13,145],"models":[14,146],"in":[15,42],"unseen":[16],"noise":[17,77],"conditions.":[18,150],"However,":[19],"existing":[20],"methods":[21],"often":[22],"incur":[23],"prohibitive":[24],"computational":[25],"and":[26,50,79,132],"memory":[27],"costs,":[28],"limiting":[29],"their":[30],"suitability":[31],"for":[32,139],"on-device":[33,141],"deployment.":[34],"In":[35],"this":[36],"work,":[37],"we":[38],"investigate":[39],"model":[40],"realistic":[43],"settings":[44],"with":[45,60,130],"dynamic":[46],"acoustic":[47,149],"scene":[48,70],"changes":[49],"propose":[51],"a":[52,57],"lightweight":[53,140],"framework":[54,123],"augments":[56],"frozen":[58],"backbone":[59],"low-rank":[61],"adapters":[62],"updated":[63],"via":[64],"self-supervised":[65],"training.":[66],"Experiments":[67],"on":[68],"sequential":[69],"evaluations":[71],"spanning":[72],"111":[73],"environments":[74],"across":[75],"37":[76],"types":[78],"three":[80],"signal-to-noise":[81],"ratio":[82],"ranges,":[83],"including":[84],"challenging":[86],"[-8,":[87],"0]":[88],"dB":[89,109],"range,":[90],"show":[91],"our":[93,122],"method":[94],"updates":[95,115],"fewer":[96],"than":[97],"1%":[98],"base":[101],"model's":[102],"parameters":[103],"while":[104],"achieving":[105],"an":[106],"average":[107],"1.51":[108],"SI-SDR":[110],"improvement":[111],"within":[112],"only":[113],"20":[114],"per":[116],"scene.":[117],"Compared":[118],"to":[119],"state-of-the-art":[120],"approaches,":[121],"achieves":[124],"competitive":[125],"or":[126],"superior":[127],"perceptual":[128],"quality":[129],"smoother":[131],"more":[133],"stable":[134],"convergence,":[135],"demonstrating":[136],"its":[137],"practicality":[138],"under":[147],"real-world":[148]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-03-11T00:00:00"}