{"id":"https://openalex.org/W4410067995","doi":"https://doi.org/10.1145/3715014.3724074","title":"Non-Intrusive Speaker Diarization via mmWave Sensing","display_name":"Non-Intrusive Speaker Diarization via mmWave Sensing","publication_year":2025,"publication_date":"2025-05-04","ids":{"openalex":"https://openalex.org/W4410067995","doi":"https://doi.org/10.1145/3715014.3724074"},"language":"en","primary_location":{"id":"doi:10.1145/3715014.3724074","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3715014.3724074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM Conference on Embedded Networked Sensor Systems","raw_type":"proceedings-article"},"type":"article","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/A5080222280","display_name":"S. Wang","orcid":"https://orcid.org/0000-0001-8895-8800"},"institutions":[{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaoying Wang","raw_affiliation_strings":["Computer Science, Florida State University, Tallahassee, Florida, USA"],"raw_orcid":"https://orcid.org/0000-0001-8895-8800","affiliations":[{"raw_affiliation_string":"Computer Science, Florida State University, Tallahassee, Florida, USA","institution_ids":["https://openalex.org/I103163165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046318408","display_name":"Hansong Zhou","orcid":"https://orcid.org/0000-0002-0423-9604"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hansong Zhou","raw_affiliation_strings":["FSU, Tallahassee, Florida, USA"],"raw_orcid":"https://orcid.org/0000-0002-0423-9604","affiliations":[{"raw_affiliation_string":"FSU, Tallahassee, Florida, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062293019","display_name":"Yukun Yuan","orcid":"https://orcid.org/0000-0003-2027-7085"},"institutions":[{"id":"https://openalex.org/I177097968","display_name":"University of Tennessee at Chattanooga","ror":"https://ror.org/00nqb1v70","country_code":"US","type":"education","lineage":["https://openalex.org/I177097968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yukun Yuan","raw_affiliation_strings":["University of Tennessee at Chattanooga, Chattanooga, TN, USA"],"raw_orcid":"https://orcid.org/0000-0003-2027-7085","affiliations":[{"raw_affiliation_string":"University of Tennessee at Chattanooga, Chattanooga, TN, USA","institution_ids":["https://openalex.org/I177097968"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028985568","display_name":"Xiaonan Zhang","orcid":"https://orcid.org/0000-0002-5913-6987"},"institutions":[{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaonan Zhang","raw_affiliation_strings":["Florida State University, Tallahassee, Florida, USA"],"raw_orcid":"https://orcid.org/0000-0002-5913-6987","affiliations":[{"raw_affiliation_string":"Florida State University, Tallahassee, Florida, USA","institution_ids":["https://openalex.org/I103163165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.08932451,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"694","last_page":"695"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9915000200271606,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9751999974250793,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.7949708104133606},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7189271450042725},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47357258200645447},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.39428409934043884}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7949708104133606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7189271450042725},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47357258200645447},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.39428409934043884}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3715014.3724074","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3715014.3724074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM Conference on Embedded Networked Sensor Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2081074144","https://openalex.org/W2140831887","https://openalex.org/W2963470929","https://openalex.org/W4385965602"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,52],"refers":[2],"to":[3,37,40,68],"identifying":[4],"who":[5],"speaks":[6],"what":[7],"in":[8,14,94,100],"a":[9,49,83],"conversation.":[10],"It":[11],"is":[12],"critical":[13],"sensitive":[15],"settings":[16],"like":[17],"psychological":[18],"counseling":[19],"and":[20,34,78],"legal":[21],"consultations.":[22],"However,":[23],"traditional":[24],"approaches,":[25],"such":[26],"as":[27],"microphone":[28],"or":[29],"video,":[30],"raise":[31],"privacy":[32],"concerns":[33],"cause":[35],"discomfort":[36],"participants":[38],"due":[39],"their":[41],"noticeable":[42],"deployment.":[43],"To":[44],"address":[45],"this,":[46],"we":[47],"propose":[48],"non-intrusive":[50],"speaker":[51],"system":[53,89],"via":[54],"mmWave":[55],"sensing.":[56],"Our":[57,88],"approach":[58],"leverages":[59],"the":[60],"spatial":[61],"diversity":[62],"of":[63],"signals":[64,77],"from":[65],"multiple":[66],"objects":[67,76],"distinguish":[69],"speakers.":[70,103],"Specifically,":[71],"it":[72],"isolates":[73],"speech-induced":[74],"vibrating":[75],"extracts":[79],"speaker-related":[80],"features":[81],"through":[82],"two-stage":[84],"feature":[85],"extraction":[86],"process.":[87],"achieves":[90],"over":[91],"93%":[92],"accuracy":[93],"real-world":[95],"scenarios,":[96],"demonstrating":[97],"its":[98],"effectiveness":[99],"reliably":[101],"distinguishing":[102]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}