{"id":"https://openalex.org/W3213319487","doi":"https://doi.org/10.1145/3485730.3485945","title":"Wavoice","display_name":"Wavoice","publication_year":2021,"publication_date":"2021-11-11","ids":{"openalex":"https://openalex.org/W3213319487","doi":"https://doi.org/10.1145/3485730.3485945","mag":"3213319487"},"language":"en","primary_location":{"id":"doi:10.1145/3485730.3485945","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3485730.3485945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th 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/A5100381088","display_name":"Tiantian Liu","orcid":"https://orcid.org/0000-0002-4706-8817"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tiantian Liu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024947839","display_name":"Ming Gao","orcid":"https://orcid.org/0000-0002-1075-0564"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Gao","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078406349","display_name":"Feng Lin","orcid":"https://orcid.org/0000-0001-5240-5200"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Lin","raw_affiliation_strings":["Zhejiang University, Hangzhou, China and Key Laboratory of Blockchain and Cyberspace Governance of Zhejiang Province, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China and Key Laboratory of Blockchain and Cyberspace Governance of Zhejiang Province, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407094","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0003-0906-445X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072485378","display_name":"Zhongjie Ba","orcid":"https://orcid.org/0000-0003-0921-8869"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongjie Ba","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023885705","display_name":"Jinsong Han","orcid":"https://orcid.org/0000-0001-5064-1955"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinsong Han","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035679293","display_name":"Wenyao Xu","orcid":"https://orcid.org/0000-0001-6444-9411"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenyao Xu","raw_affiliation_strings":["University at Buffalo, the State University of New York, Buffalo, New York, USA"],"affiliations":[{"raw_affiliation_string":"University at Buffalo, the State University of New York, Buffalo, New York, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105297718","display_name":"Kui Ren","orcid":"https://orcid.org/0000-0002-1969-2591"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kui Ren","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100381088"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":9.2599,"has_fulltext":false,"cited_by_count":82,"citation_normalized_percentile":{"value":0.98703122,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"97","last_page":"110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9997000098228455,"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":0.9991999864578247,"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":0.832409679889679},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7454162836074829},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6317079067230225},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5620363354682922},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5305925607681274},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.48516184091567993},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4327208697795868},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42454105615615845},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3445778489112854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3337792754173279},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0959496796131134}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.832409679889679},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7454162836074829},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6317079067230225},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5620363354682922},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5305925607681274},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.48516184091567993},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4327208697795868},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42454105615615845},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3445778489112854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3337792754173279},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0959496796131134},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3485730.3485945","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3485730.3485945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1495679096","https://openalex.org/W1581253957","https://openalex.org/W2010189898","https://openalex.org/W2057243093","https://openalex.org/W2104717865","https://openalex.org/W2110322414","https://openalex.org/W2138194976","https://openalex.org/W2156279557","https://openalex.org/W2156775872","https://openalex.org/W2158409990","https://openalex.org/W2193413348","https://openalex.org/W2213420530","https://openalex.org/W2242685705","https://openalex.org/W2289912446","https://openalex.org/W2327501763","https://openalex.org/W2496632708","https://openalex.org/W2611961900","https://openalex.org/W2750499125","https://openalex.org/W2765955268","https://openalex.org/W2793044632","https://openalex.org/W2895655906","https://openalex.org/W2900292050","https://openalex.org/W2914111477","https://openalex.org/W2932030740","https://openalex.org/W2943554574","https://openalex.org/W2951288507","https://openalex.org/W2953190524","https://openalex.org/W2953297989","https://openalex.org/W2962920357","https://openalex.org/W2963321191","https://openalex.org/W2964539095","https://openalex.org/W2972498864","https://openalex.org/W2973616902","https://openalex.org/W2990714382","https://openalex.org/W2998161426","https://openalex.org/W3006643904","https://openalex.org/W3009950332","https://openalex.org/W3015679345","https://openalex.org/W3018353706","https://openalex.org/W3018805456","https://openalex.org/W3019180776","https://openalex.org/W3088639796","https://openalex.org/W3098782124","https://openalex.org/W3109009614","https://openalex.org/W3109995084","https://openalex.org/W3131937470","https://openalex.org/W3137420496","https://openalex.org/W3140645045","https://openalex.org/W3142831896","https://openalex.org/W4232841423","https://openalex.org/W4234552385"],"related_works":["https://openalex.org/W1977167953","https://openalex.org/W107154053","https://openalex.org/W2122030153","https://openalex.org/W2499802997","https://openalex.org/W4255044973","https://openalex.org/W2112059504","https://openalex.org/W2727729836","https://openalex.org/W1960256358","https://openalex.org/W2162449135","https://openalex.org/W642007152"],"abstract_inverted_index":{"With":[0],"the":[1,15,34,43,61,93,106,126,149,184],"advance":[2],"in":[3,22,136,156,180],"automatic":[4],"speech":[5,47,65,138,166],"recognition,":[6],"voice":[7,38,72,109],"user":[8,39,113],"interface":[9],"has":[10],"gained":[11],"popularity":[12],"recently.":[13],"Since":[14],"COVID-19":[16],"pandemic,":[17],"VUI":[18],"is":[19,89],"increasingly":[20],"preferred":[21],"online":[23],"communication":[24],"due":[25,41],"to":[26,42],"its":[27],"non-contact.":[28],"Additionally,":[29],"various":[30,146],"ambient":[31],"noise":[32],"impedes":[33],"public":[35],"applications":[36],"of":[37,45,159,186],"interfaces":[40],"requirement":[44],"audio-only":[46,165],"recognition":[48,66,151,167],"methods":[49,168],"for":[50,130],"a":[51,83,157],"high":[52],"signal-to-noise":[53],"ratio.":[54],"In":[55],"this":[56],"paper,":[57],"we":[58,91,119],"present":[59],"Wavoice,":[60],"first":[62],"noise-resistant":[63,108],"multi-modal":[64,131],"system":[67],"that":[68,90],"fuses":[69],"two":[70,122],"distinct":[71],"sensing":[73],"modalities,":[74],"i.e.,":[75],"millimeter-wave":[76],"(mmWave)":[77],"signals":[78,81,132],"and":[79,98,112,134,174],"audio":[80,99],"from":[82,115],"microphone,":[84],"together.":[85],"One":[86],"key":[87],"contribution":[88],"model":[92],"inherent":[94],"correlation":[95],"between":[96],"mmWave":[97],"signals.":[100],"Based":[101],"on":[102,121],"it,":[103],"Wavoice":[104,162],"facilitates":[105],"real-time":[107],"activity":[110],"detection":[111],"targeting":[114],"multiple":[116],"speakers.":[117],"Furthermore,":[118],"elaborate":[120],"novel":[123],"modules":[124],"into":[125],"neural":[127],"attention":[128],"mechanism":[129],"fusion,":[133],"result":[135],"accurate":[137],"recognition.":[139],"Extensive":[140],"experiments":[141],"verify":[142],"Wavoice's":[143],"effectiveness":[144],"under":[145],"conditions":[147],"with":[148,169],"character":[150,171],"error":[152,172,176],"rate":[153,173],"below":[154],"1%":[155],"range":[158],"7":[160],"meters.":[161],"outperforms":[163],"existing":[164],"lower":[170],"word":[175],"rate.":[177],"The":[178],"evaluation":[179],"complex":[181],"scenes":[182],"validates":[183],"robustness":[185],"Wavoice.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":26},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":9}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2021-11-22T00:00:00"}