{"id":"https://openalex.org/W4385965602","doi":"https://doi.org/10.1145/3610873","title":"Radio2Text","display_name":"Radio2Text","publication_year":2023,"publication_date":"2023-09-27","ids":{"openalex":"https://openalex.org/W4385965602","doi":"https://doi.org/10.1145/3610873"},"language":"en","primary_location":{"id":"doi:10.1145/3610873","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610873","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610873","source":{"id":"https://openalex.org/S4210219751","display_name":"Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies","issn_l":"2474-9567","issn":["2474-9567"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3610873","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057284689","display_name":"Running Zhao","orcid":"https://orcid.org/0000-0003-2496-3429"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Running Zhao","raw_affiliation_strings":["The University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0003-2496-3429","affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101626324","display_name":"Jiangtao Yu","orcid":"https://orcid.org/0009-0004-3964-5874"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangtao Yu","raw_affiliation_strings":["Shanghai Qi Zhi Institute, Shanghai, China and IIIS, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-3964-5874","affiliations":[{"raw_affiliation_string":"Shanghai Qi Zhi Institute, Shanghai, China and IIIS, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I4210122302","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hang Zhao","orcid":"https://orcid.org/0000-0003-1928-7841"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Zhao","raw_affiliation_strings":["IIIS, Tsinghua University, Beijing, China and Shanghai Qi Zhi Institute, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1928-7841","affiliations":[{"raw_affiliation_string":"IIIS, Tsinghua University, Beijing, China and Shanghai Qi Zhi Institute, Shanghai, China","institution_ids":["https://openalex.org/I4210122302","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077317339","display_name":"Edith C.\u2010H. Ngai","orcid":"https://orcid.org/0000-0002-3454-8731"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Edith C.H. Ngai","raw_affiliation_strings":["The University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-3454-8731","affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5057284689"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":3.7444,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.94516049,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"7","issue":"3","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991999864578247,"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":0.9944999814033508,"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":0.8302927017211914},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6604917049407959},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6435329914093018},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6178605556488037},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.45549023151397705},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.42629432678222656},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.41717293858528137},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3375723958015442},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.26535701751708984},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11466464400291443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8302927017211914},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6604917049407959},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6435329914093018},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6178605556488037},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.45549023151397705},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42629432678222656},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.41717293858528137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3375723958015442},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26535701751708984},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11466464400291443},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3610873","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610873","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610873","source":{"id":"https://openalex.org/S4210219751","display_name":"Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies","issn_l":"2474-9567","issn":["2474-9567"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2308.08125","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.08125","pdf_url":"https://arxiv.org/pdf/2308.08125","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3610873","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610873","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610873","source":{"id":"https://openalex.org/S4210219751","display_name":"Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies","issn_l":"2474-9567","issn":["2474-9567"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385965602.pdf","grobid_xml":"https://content.openalex.org/works/W4385965602.grobid-xml"},"referenced_works_count":80,"referenced_works":["https://openalex.org/W210359992","https://openalex.org/W569478347","https://openalex.org/W753847829","https://openalex.org/W1438441013","https://openalex.org/W1494198834","https://openalex.org/W1690739335","https://openalex.org/W1710082047","https://openalex.org/W1821462560","https://openalex.org/W1828163288","https://openalex.org/W1977985044","https://openalex.org/W1991139021","https://openalex.org/W2025621754","https://openalex.org/W2088881802","https://openalex.org/W2127141656","https://openalex.org/W2163922914","https://openalex.org/W2168961642","https://openalex.org/W2461924673","https://openalex.org/W2526425061","https://openalex.org/W2560674852","https://openalex.org/W2561238782","https://openalex.org/W2750784772","https://openalex.org/W2797583228","https://openalex.org/W2799062425","https://openalex.org/W2827033964","https://openalex.org/W2872172641","https://openalex.org/W2931586361","https://openalex.org/W2939432428","https://openalex.org/W2942810103","https://openalex.org/W2952787292","https://openalex.org/W2952992734","https://openalex.org/W2953297989","https://openalex.org/W2962780374","https://openalex.org/W2962866211","https://openalex.org/W2963250244","https://openalex.org/W2963454081","https://openalex.org/W2968303571","https://openalex.org/W2970454332","https://openalex.org/W2972324944","https://openalex.org/W2978017171","https://openalex.org/W3015315932","https://openalex.org/W3015830103","https://openalex.org/W3015974384","https://openalex.org/W3016022729","https://openalex.org/W3036601975","https://openalex.org/W3040360205","https://openalex.org/W3085139254","https://openalex.org/W3087859191","https://openalex.org/W3096702180","https://openalex.org/W3097777922","https://openalex.org/W3106588323","https://openalex.org/W3106861388","https://openalex.org/W3107949730","https://openalex.org/W3109500059","https://openalex.org/W3161873870","https://openalex.org/W3175987492","https://openalex.org/W3209059054","https://openalex.org/W4281851959","https://openalex.org/W4283204284","https://openalex.org/W4283204589","https://openalex.org/W4283211061","https://openalex.org/W4283219755","https://openalex.org/W4283391228","https://openalex.org/W4284881846","https://openalex.org/W4288057696","https://openalex.org/W4288057735","https://openalex.org/W4293665662","https://openalex.org/W4297779827","https://openalex.org/W4300011764","https://openalex.org/W4300973271","https://openalex.org/W4306179797","https://openalex.org/W4312309807","https://openalex.org/W4319837251","https://openalex.org/W4322731291","https://openalex.org/W4378105483","https://openalex.org/W4385245566","https://openalex.org/W4385248623","https://openalex.org/W4386242195","https://openalex.org/W4386243293","https://openalex.org/W4387007263","https://openalex.org/W6854641661"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W2355833770","https://openalex.org/W1985458517","https://openalex.org/W3031039437","https://openalex.org/W183202219","https://openalex.org/W3095877357","https://openalex.org/W2072565696","https://openalex.org/W2050451745","https://openalex.org/W2378903222"],"abstract_inverted_index":{"Millimeter":[0],"wave":[1],"(mmWave)":[2],"based":[3,64,138],"speech":[4,15,52,177],"recognition":[5,53,157,213],"provides":[6,167],"more":[7],"possibility":[8],"for":[9,49,83,211],"audio-related":[10],"applications,":[11],"such":[12],"as":[13],"conference":[14],"transcription":[16],"and":[17,27,169,175,204],"eavesdropping.":[18],"However,":[19],"considering":[20],"the":[21,45,81,92,105,110,117,121,125,148,160,163,181,184,212],"practicality":[22],"in":[23],"real":[24],"scenarios,":[25],"latency":[26],"recognizable":[28],"vocabulary":[29,57,216],"size":[30,58],"are":[31],"two":[32],"critical":[33],"factors":[34],"that":[35,70,108,172,193],"cannot":[36],"be":[37],"overlooked.":[38],"In":[39,159],"this":[40],"paper,":[41],"we":[42,103,133],"propose":[43,104,134],"Radio2Text,":[44],"first":[46],"mmWave-based":[47],"system":[48],"streaming":[50,68,84,95,127,165,187],"automatic":[51],"(ASR)":[54],"with":[55,86],"a":[56,66,87,135,198,205,215],"exceeding":[59],"13,000":[60,220],"words.":[61,221],"Radio2Text":[62,195],"is":[63,71],"on":[65,139,156],"tailored":[67,126,185],"Transformer":[69,123,128,166],"capable":[72],"of":[73,77,94,112,151,183,202,209,214,218],"effectively":[74],"learning":[75],"representations":[76],"speech-related":[78],"features,":[79],"paving":[80],"way":[82],"ASR":[85],"large":[88],"vocabulary.":[89],"To":[90],"alleviate":[91],"deficiency":[93],"networks":[96],"unable":[97],"to":[98,116,124,146,179],"access":[99],"entire":[100],"future":[101],"inputs,":[102],"Guidance":[106],"Initialization":[107],"facilitates":[109],"transfer":[111],"feature":[113,168],"knowledge":[114,140],"related":[115],"global":[118],"context":[119],"from":[120],"non-streaming":[122],"through":[129],"weight":[130],"inheritance.":[131],"Further,":[132],"cross-modal":[136,144,161],"structure":[137],"distillation":[141],"(KD),":[142],"named":[143],"KD,":[145,162],"mitigate":[147],"negative":[149],"effect":[150],"low":[152],"quality":[153],"mmWave":[154],"signals":[155],"performance.":[158],"audio":[164],"response":[170],"guidance":[171],"inherit":[173],"fruitful":[174],"accurate":[176],"information":[178],"supervise":[180],"training":[182],"radio":[186],"Transformer.":[188],"The":[189],"experimental":[190],"results":[191],"show":[192],"our":[194],"can":[196],"achieve":[197],"character":[199],"error":[200,207],"rate":[201,208],"5.7%":[203],"word":[206],"9.4%":[210],"consisting":[217],"over":[219]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2023-08-18T00:00:00"}
