{"id":"https://openalex.org/W4414430316","doi":"https://doi.org/10.21437/interspeech.2025-2581","title":"Modality-Specific Speech Enhancement and Noise-Adaptive Fusion for Acoustic and Body-Conduction Microphone Framework","display_name":"Modality-Specific Speech Enhancement and Noise-Adaptive Fusion for Acoustic and Body-Conduction Microphone Framework","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4414430316","doi":"https://doi.org/10.21437/interspeech.2025-2581"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-2581","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.17336","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060592139","display_name":"Yunsik Kim","orcid":"https://orcid.org/0000-0002-0883-8786"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yunsik Kim","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5090560960","display_name":"Yoonyoung Chung","orcid":"https://orcid.org/0000-0001-8348-7042"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoonyoung Chung","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5060592139"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5741,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86433625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3833","last_page":"3837"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9907000064849854,"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":0.9861000180244446,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7874000072479248},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7802000045776367},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.5396999716758728},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5382000207901001},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4812999963760376},{"id":"https://openalex.org/keywords/noise-canceling-microphone","display_name":"Noise-canceling microphone","score":0.46380001306533813},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4546999931335449},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.45190000534057617}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7874000072479248},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7802000045776367},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6955000162124634},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.564300000667572},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.5396999716758728},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5382000207901001},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4812999963760376},{"id":"https://openalex.org/C36922181","wikidata":"https://www.wikidata.org/wiki/Q7047650","display_name":"Noise-canceling microphone","level":5,"score":0.46380001306533813},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4546999931335449},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.45190000534057617},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.41110000014305115},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3734999895095825},{"id":"https://openalex.org/C87133666","wikidata":"https://www.wikidata.org/wiki/Q1161699","display_name":"Dynamic range","level":2,"score":0.364300012588501},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.34040001034736633},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2669999897480011},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2556999921798706}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-2581","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.17336","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.17336","pdf_url":"https://arxiv.org/pdf/2508.17336","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.17336","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.17336","pdf_url":"https://arxiv.org/pdf/2508.17336","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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":{"Body-conduction":[0],"microphone":[1,40],"signals":[2,41],"(BMS)":[3],"bypass":[4],"airborne":[5],"sound,":[6],"providing":[7],"strong":[8],"noise":[9,46,91,111],"resistance.":[10],"However,":[11],"a":[12,31,65,72,83,129],"complementary":[13],"modality":[14],"is":[15],"required":[16],"to":[17,43,68,75,89],"compensate":[18],"for":[19],"the":[20,94,105],"inherent":[21],"loss":[22],"of":[23,97,132],"high-frequency":[24,49],"information.":[25],"In":[26],"this":[27],"study,":[28],"we":[29],"propose":[30],"novel":[32],"multi-modal":[33,53],"framework":[34],"that":[35,55,87,122],"combines":[36],"BMS":[37,70],"and":[38,48,71],"acoustic":[39],"(AMS)":[42],"achieve":[44],"both":[45],"suppression":[47],"reconstruction.":[50],"Unlike":[51],"conventional":[52],"approaches":[54],"simply":[56],"merge":[57],"features,":[58],"our":[59,123],"method":[60],"employs":[61],"two":[62],"specialized":[63],"networks:":[64],"mapping-based":[66],"model":[67,74],"enhance":[69],"masking-based":[73],"denoise":[76],"AMS.":[77],"These":[78],"networks":[79],"are":[80],"integrated":[81],"through":[82],"dynamic":[84],"fusion":[85],"mechanism":[86],"adapts":[88],"local":[90],"conditions,":[92],"ensuring":[93],"optimal":[95],"use":[96],"each":[98],"modality's":[99],"strengths.":[100],"We":[101],"performed":[102],"evaluations":[103],"on":[104],"TAPS":[106],"dataset,":[107],"augmented":[108],"with":[109],"DNS-2023":[110],"clips,":[112],"using":[113],"objective":[114],"speech":[115],"quality":[116],"metrics.":[117],"The":[118],"results":[119],"clearly":[120],"demonstrate":[121],"approach":[124],"outperforms":[125],"single-modal":[126],"solutions":[127],"in":[128],"wide":[130],"range":[131],"noisy":[133],"environments.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}