{"id":"https://openalex.org/W4410228217","doi":"https://doi.org/10.1109/wcnc61545.2025.10978346","title":"SpDiff: A Speech Sensing System with Diffusion Model Based on mm Wave Radar","display_name":"SpDiff: A Speech Sensing System with Diffusion Model Based on mm Wave Radar","publication_year":2025,"publication_date":"2025-03-24","ids":{"openalex":"https://openalex.org/W4410228217","doi":"https://doi.org/10.1109/wcnc61545.2025.10978346"},"language":"en","primary_location":{"id":"doi:10.1109/wcnc61545.2025.10978346","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wcnc61545.2025.10978346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Wireless Communications and Networking Conference (WCNC)","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/A5046866400","display_name":"Can Jin","orcid":"https://orcid.org/0000-0002-6028-336X"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Can Jin","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079775950","display_name":"Yulong Zhang","orcid":"https://orcid.org/0000-0002-7720-981X"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulong Zhang","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054407228","display_name":"Xuanheng Li","orcid":"https://orcid.org/0000-0003-2606-6932"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanheng Li","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073840185","display_name":"Yi Sun","orcid":"https://orcid.org/0000-0001-6086-5741"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Sun","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072058207","display_name":"Jie Wang","orcid":"https://orcid.org/0000-0002-0262-7945"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Wang","raw_affiliation_strings":["School of Information Science and Technology, Dalian Maritime University,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Dalian Maritime University,Dalian,China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016290340","display_name":"Yuguang Fang","orcid":"https://orcid.org/0000-0002-1079-3871"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuguang Fang","raw_affiliation_strings":["City University of Hong Kong,Department of Computer Science,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong,Department of Computer Science,Hong Kong,China","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"06"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9787999987602234,"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":0.9787999987602234,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6414826512336731},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5393447875976562},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.5267607569694519},{"id":"https://openalex.org/keywords/radar-systems","display_name":"Radar systems","score":0.47019872069358826},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41059333086013794},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.33828139305114746},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.2215856909751892},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.2011718451976776},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1334019899368286}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6414826512336731},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5393447875976562},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.5267607569694519},{"id":"https://openalex.org/C2984296375","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar systems","level":3,"score":0.47019872069358826},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41059333086013794},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.33828139305114746},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.2215856909751892},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.2011718451976776},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1334019899368286},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wcnc61545.2025.10978346","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wcnc61545.2025.10978346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Wireless Communications and Networking Conference (WCNC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8437808078","display_name":null,"funder_award_id":"62271100","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2953297989","https://openalex.org/W3085051942","https://openalex.org/W4284881846","https://openalex.org/W4294991805","https://openalex.org/W4312436332","https://openalex.org/W4312933868","https://openalex.org/W4322731291","https://openalex.org/W4361763861","https://openalex.org/W4372271879","https://openalex.org/W4386076005","https://openalex.org/W4390873749","https://openalex.org/W6855546619","https://openalex.org/W6871332040"],"related_works":["https://openalex.org/W760655932","https://openalex.org/W96662699","https://openalex.org/W156107400","https://openalex.org/W2353141829","https://openalex.org/W2083225881","https://openalex.org/W2362183774","https://openalex.org/W2370482908","https://openalex.org/W2910716297","https://openalex.org/W2363629559","https://openalex.org/W2481048288"],"abstract_inverted_index":{"Voice":[0],"control":[1],"has":[2],"become":[3],"an":[4,187],"indispensable":[5],"interaction":[6],"method":[7,73,82],"in":[8,25,173],"smart":[9],"devices.":[10],"Compared":[11],"to":[12,44,100,112,161],"traditional":[13],"microphones,":[14],"mm":[15,76],"Wave":[16,77],"radar":[17,128,140],"offers":[18],"a":[19,69,119,152,163],"promising":[20],"solution":[21],"for":[22],"speech":[23,53,61,71,97,115,142,174,179],"sensing":[24,72],"noisy":[26],"environments.":[27],"However,":[28],"most":[29],"current":[30],"research":[31],"relies":[32],"on":[33,75,90],"single-view":[34],"information,":[35],"such":[36],"as":[37,130],"vocal":[38,93,106],"cord":[39],"vibrations":[40],"or":[41],"lip":[42],"movements,":[43],"classify":[45],"speech,":[46],"which":[47,125],"overlooks":[48],"important":[49],"details":[50],"like":[51],"timbre,":[52],"rate,":[54],"and":[55,109,141,157,190,198],"intonation,":[56],"limiting":[57],"the":[58,85,91,101,105,135,147,177],"application":[59],"of":[60,104,195],"sensing.":[62],"To":[63,145],"address":[64],"these":[65],"issues,":[66],"we":[67,117,150],"develop":[68],"high-quality":[70,114],"based":[74,89],"radar,":[78],"named":[79],"SpDiff.":[80],"This":[81],"accurately":[83,133],"localizes":[84],"vocalizing":[86],"target":[87],"and,":[88],"human":[92],"mechanism,":[94],"extracts":[95],"multi-view":[96,127],"features":[98],"according":[99],"movement":[102],"characteristics":[103],"cords,":[107],"lips,":[108],"face.":[110],"Additionally,":[111],"generate":[113],"signals,":[116],"design":[118],"conditional":[120,131],"latent":[121],"diffusion":[122],"model":[123],"(CLDM),":[124],"uses":[126],"information":[129],"guidance,":[132],"capturing":[134],"complex":[136],"mapping":[137],"relationships":[138],"between":[139],"signal":[143],"distributions.":[144],"evaluate":[146],"SpDiff":[148,169],"method,":[149],"build":[151],"mmWave":[153],"system":[154],"using":[155],"IWR1443Boost":[156],"recruit":[158],"14":[159],"volunteers":[160],"construct":[162],"dataset.":[164],"Experimental":[165],"results":[166],"show":[167],"that":[168],"achieves":[170],"high":[171],"standards":[172],"sensing,":[175],"with":[176],"generated":[178],"directly":[180],"input":[181],"into":[182],"existing":[183],"recognition":[184],"models,":[185],"achieving":[186],"average":[188],"character":[189],"word":[191],"error":[192],"rate":[193],"(CER/WER)":[194],"only":[196],"2.33%":[197],"3.05%.":[199]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
