{"id":"https://openalex.org/W4406859710","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848922","title":"SMoLnet-T: An Efficient Complex-spectral Mapping Speech Enhancement Approach with Frame-wise CNN and Spectral Combination Transformer for Drone Audition","display_name":"SMoLnet-T: An Efficient Complex-spectral Mapping Speech Enhancement Approach with Frame-wise CNN and Spectral Combination Transformer for Drone Audition","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406859710","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848922"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10848922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5049850307","display_name":"Zhi-Wei Tan","orcid":"https://orcid.org/0000-0001-9921-011X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhi-Wei Tan","raw_affiliation_strings":["Nanyang Technological University,School of Electrical and Electronic Engineering,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Electrical and Electronic Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010202250","display_name":"Andy W. H. Khong","orcid":"https://orcid.org/0000-0002-0708-4791"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Andy W. H. Khong","raw_affiliation_strings":["Nanyang Technological University,School of Electrical and Electronic Engineering and Lee Kong Chian School of Medicine,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Electrical and Electronic Engineering and Lee Kong Chian School of Medicine,Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.4171,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62993253,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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":0.9987000226974487,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.974399983882904,"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/T11698","display_name":"Underwater Acoustics Research","score":0.9517999887466431,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/drone","display_name":"Drone","score":0.8820148706436157},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.728516697883606},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7093367576599121},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6052448153495789},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.539841890335083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4282549023628235},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3358643651008606},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1442798674106598},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11612054705619812},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09820669889450073}],"concepts":[{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.8820148706436157},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.728516697883606},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7093367576599121},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6052448153495789},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.539841890335083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4282549023628235},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3358643651008606},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1442798674106598},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11612054705619812},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09820669889450073},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"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/apsipaasc63619.2025.10848922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.4000000059604645}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307110","display_name":"Delta","ror":"https://ror.org/03g9c1e75"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W2153167244","https://openalex.org/W2516001803","https://openalex.org/W2566088759","https://openalex.org/W2900007948","https://openalex.org/W2952218014","https://openalex.org/W2964058413","https://openalex.org/W2964089206","https://openalex.org/W2998774371","https://openalex.org/W3010672229","https://openalex.org/W3011183480","https://openalex.org/W3096893582","https://openalex.org/W3163652268","https://openalex.org/W4205221070","https://openalex.org/W4225270270","https://openalex.org/W4296069339","https://openalex.org/W4323338563","https://openalex.org/W4381785800","https://openalex.org/W4385245566","https://openalex.org/W4389252578","https://openalex.org/W6601150824","https://openalex.org/W6631190155","https://openalex.org/W6696085341","https://openalex.org/W6738884980","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W4229448053","https://openalex.org/W4247925126","https://openalex.org/W4327774218","https://openalex.org/W2059768187","https://openalex.org/W4312858960","https://openalex.org/W4386036939","https://openalex.org/W4379143281","https://openalex.org/W2605096541","https://openalex.org/W3200286695","https://openalex.org/W4212885606"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,73],"for":[2,49,72],"drone":[3,87],"audition":[4],"applications":[5],"is":[6,70],"challenging":[7],"due":[8],"to":[9,42,55],"the":[10,65,89],"low":[11],"SNR":[12,109],"with":[13,30,81,95],"large":[14,76],"spectra":[15],"feature":[16],"overlap":[17],"and":[18,33,63,100],"limited":[19],"computing":[20],"resources.":[21],"We":[22],"propose":[23],"SMoLnetT,":[24],"a":[25,58,75,85],"complex":[26],"spectral":[27,35,44,68],"mapping":[28],"approach":[29],"frame-wise":[31],"CNN":[32,41],"newly-formulated":[34],"combination":[36,66],"transformers.":[37,51],"SMoLnet-T":[38,92],"incorporates":[39],"dilated":[40],"extract":[43],"maps":[45,69],"of":[46,61,67,91],"high-frequency":[47],"resolution":[48],"its":[50],"This":[52],"allows":[53],"it":[54],"focus":[56],"on":[57],"higher":[59],"level":[60],"abstraction":[62],"determine":[64],"crucial":[71],"across":[74],"temporal":[77],"context.":[78],"Experiment":[79],"results":[80],"noise":[82],"recorded":[83],"from":[84],"hovering":[86],"highlight":[88],"efficacy":[90],"over":[93],"DPTNet":[94],"significantly":[96],"lower":[97],"computational":[98],"requirements":[99],"speech":[101,106],"distortion":[102],"while":[103],"achieving":[104],"improved":[105],"intelligibility":[107],"under":[108],"<":[110],"\u221223":[111],"dB.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}