{"id":"https://openalex.org/W4403126377","doi":"https://doi.org/10.1109/iwaenc61483.2024.10694014","title":"Monaural Speech Enhancement on Drone via Adapter Based Transfer Learning","display_name":"Monaural Speech Enhancement on Drone via Adapter Based Transfer Learning","publication_year":2024,"publication_date":"2024-09-09","ids":{"openalex":"https://openalex.org/W4403126377","doi":"https://doi.org/10.1109/iwaenc61483.2024.10694014"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc61483.2024.10694014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10694014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100387362","display_name":"Xingyu Chen","orcid":"https://orcid.org/0009-0004-2060-5127"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["AU","US"],"is_corresponding":false,"raw_author_name":"Xingyu Chen","raw_affiliation_strings":["Australian National University,Audio and Acoustic Signal Processing Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University,Audio and Acoustic Signal Processing Group","institution_ids":["https://openalex.org/I118347636","https://openalex.org/I4210121626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044203844","display_name":"Hanwen Bi","orcid":"https://orcid.org/0000-0002-0327-5523"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["AU","US"],"is_corresponding":false,"raw_author_name":"Hanwen Bi","raw_affiliation_strings":["Australian National University,Audio and Acoustic Signal Processing Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University,Audio and Acoustic Signal Processing Group","institution_ids":["https://openalex.org/I118347636","https://openalex.org/I4210121626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113336014","display_name":"Wei-Ting Lai","orcid":"https://orcid.org/0000-0003-4143-7914"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["AU","US"],"is_corresponding":false,"raw_author_name":"Wei-Ting Lai","raw_affiliation_strings":["Australian National University,Audio and Acoustic Signal Processing Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University,Audio and Acoustic Signal Processing Group","institution_ids":["https://openalex.org/I118347636","https://openalex.org/I4210121626"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100608217","display_name":"Fei Ma","orcid":"https://orcid.org/0000-0002-3911-7121"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["AU","US"],"is_corresponding":false,"raw_author_name":"Fei Ma","raw_affiliation_strings":["Australian National University,Audio and Acoustic Signal Processing Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University,Audio and Acoustic Signal Processing Group","institution_ids":["https://openalex.org/I118347636","https://openalex.org/I4210121626"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6686,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.85493764,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"85","last_page":"89"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9933000206947327,"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":0.9933000206947327,"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/T11448","display_name":"Face recognition and analysis","score":0.97079998254776,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9358000159263611,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/adapter","display_name":"Adapter (computing)","score":0.7366889119148254},{"id":"https://openalex.org/keywords/drone","display_name":"Drone","score":0.7250579595565796},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6740875244140625},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.5593608021736145},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4751726984977722},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43160197138786316},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29799339175224304},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.11639225482940674},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.048683345317840576}],"concepts":[{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.7366889119148254},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.7250579595565796},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6740875244140625},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.5593608021736145},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4751726984977722},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43160197138786316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29799339175224304},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.11639225482940674},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.048683345317840576},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwaenc61483.2024.10694014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10694014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W2036647862","https://openalex.org/W2066986520","https://openalex.org/W2146324387","https://openalex.org/W2291877678","https://openalex.org/W2516001803","https://openalex.org/W2553033130","https://openalex.org/W2796538318","https://openalex.org/W2889442120","https://openalex.org/W2889583142","https://openalex.org/W2900160352","https://openalex.org/W3003293188","https://openalex.org/W3081138412","https://openalex.org/W3096408984","https://openalex.org/W4200552942","https://openalex.org/W4224917453","https://openalex.org/W4225905067","https://openalex.org/W4323338563","https://openalex.org/W6738045163","https://openalex.org/W6759579507"],"related_works":["https://openalex.org/W4229448053","https://openalex.org/W4247925126","https://openalex.org/W2036157531","https://openalex.org/W4327774218","https://openalex.org/W2056406069","https://openalex.org/W2059768187","https://openalex.org/W4312858960","https://openalex.org/W4386036939","https://openalex.org/W4379143281","https://openalex.org/W2401567014"],"abstract_inverted_index":{"Monaural":[0],"Speech":[1],"enhancement":[2],"on":[3,81],"drones":[4],"is":[5,111],"challenging":[6,41],"because":[7],"the":[8,11,40,57,76,86,89,101],"ego-noise":[9],"from":[10],"rotating":[12],"motors":[13],"and":[14],"propellers":[15],"leads":[16],"to":[17,54,71,116],"extremely":[18],"low":[19],"signal-to-noise":[20],"ratios":[21],"at":[22],"onboard":[23],"microphones.":[24],"Although":[25],"recent":[26],"masking-based":[27],"deep":[28],"neural":[29],"network":[30],"methods":[31],"excel":[32],"in":[33,39],"monaural":[34],"speech":[35,107],"enhancement,":[36],"they":[37],"struggle":[38],"drone":[42,47,61,82,121],"noise":[43,48,83],"scenario.":[44],"Furthermore,":[45],"existing":[46],"datasets":[49],"are":[50,79],"limited,":[51],"causing":[52],"models":[53,118],"overfit.":[55],"Considering":[56],"harmonic":[58],"nature":[59],"of":[60,88],"noise,":[62],"this":[63],"paper":[64],"proposes":[65],"a":[66,112],"frequency":[67],"domain":[68],"bottleneck":[69],"adapter":[70],"enable":[72],"transfer":[73],"learning.":[74],"Specifically,":[75],"adapter\u2019s":[77],"parameters":[78,87],"trained":[80],"while":[84],"retaining":[85],"pre-trained":[90],"Frequency":[91],"Recurrent":[92,94],"Convolutional":[93],"Network":[95],"(FRCRN)":[96],"fixed.":[97],"Evaluation":[98],"results":[99],"demonstrate":[100],"proposed":[102],"method":[103],"can":[104],"effectively":[105],"enhance":[106],"quality.":[108],"Moreover,":[109],"it":[110],"more":[113],"efficient":[114],"alternative":[115],"fine-tuning":[117],"for":[119],"various":[120],"types,":[122],"which":[123],"requires":[124],"substantial":[125],"computational":[126],"resources.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}