{"id":"https://openalex.org/W4307475373","doi":"https://doi.org/10.1145/3526113.3545685","title":"DualVoice: Speech Interaction that Discriminates between Normal and Whispered Voice Input","display_name":"DualVoice: Speech Interaction that Discriminates between Normal and Whispered Voice Input","publication_year":2022,"publication_date":"2022-10-28","ids":{"openalex":"https://openalex.org/W4307475373","doi":"https://doi.org/10.1145/3526113.3545685"},"language":"en","primary_location":{"id":"doi:10.1145/3526113.3545685","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3526113.3545685","pdf_url":null,"source":null,"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 35th Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2208.10499","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082649952","display_name":"Jun Rekimoto","orcid":"https://orcid.org/0000-0002-3629-2514"},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Jun Rekimoto","raw_affiliation_strings":["The University of Tokyo, Japan and Sony CSL Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Japan and Sony CSL Kyoto, Japan","institution_ids":["https://openalex.org/I4210122684","https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5082649952"],"corresponding_institution_ids":["https://openalex.org/I4210122684","https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":1.1105,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.81780099,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.8519531488418579},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7654561996459961},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6461990475654602},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5698058605194092},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.4803144335746765},{"id":"https://openalex.org/keywords/voice-command-device","display_name":"Voice command device","score":0.47423145174980164},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4415081739425659},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4117076098918915}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8519531488418579},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7654561996459961},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6461990475654602},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5698058605194092},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.4803144335746765},{"id":"https://openalex.org/C178718744","wikidata":"https://www.wikidata.org/wiki/Q2350070","display_name":"Voice command device","level":2,"score":0.47423145174980164},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4415081739425659},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4117076098918915},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3526113.3545685","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3526113.3545685","pdf_url":null,"source":null,"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 35th Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2208.10499","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.10499","pdf_url":"https://arxiv.org/pdf/2208.10499","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2208.10499","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.10499","pdf_url":"https://arxiv.org/pdf/2208.10499","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6600000262260437,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W12678886","https://openalex.org/W96541173","https://openalex.org/W177407077","https://openalex.org/W198720948","https://openalex.org/W1494198834","https://openalex.org/W1904948456","https://openalex.org/W1969139822","https://openalex.org/W2008120082","https://openalex.org/W2022047569","https://openalex.org/W2127141656","https://openalex.org/W2187089797","https://openalex.org/W2437658533","https://openalex.org/W2499854530","https://openalex.org/W2516855573","https://openalex.org/W2768731046","https://openalex.org/W2793257307","https://openalex.org/W2896457183","https://openalex.org/W2896622783","https://openalex.org/W2897318954","https://openalex.org/W2899771611","https://openalex.org/W2900011961","https://openalex.org/W2941048526","https://openalex.org/W2962795274","https://openalex.org/W2972471621","https://openalex.org/W2980282514","https://openalex.org/W2980880049","https://openalex.org/W3036601975","https://openalex.org/W3081492798","https://openalex.org/W3101631197","https://openalex.org/W3102538494","https://openalex.org/W3105124182","https://openalex.org/W3113594615","https://openalex.org/W3161865163","https://openalex.org/W3178117716","https://openalex.org/W3197642003","https://openalex.org/W3209059054","https://openalex.org/W4214540501","https://openalex.org/W4287813586","https://openalex.org/W4289666046","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2184127972","https://openalex.org/W642007152","https://openalex.org/W2556771176","https://openalex.org/W2343205865","https://openalex.org/W2008120082","https://openalex.org/W2525874696","https://openalex.org/W2810519502","https://openalex.org/W2341426843","https://openalex.org/W2131711534","https://openalex.org/W2187296505"],"abstract_inverted_index":{"Interactions":[0],"based":[1],"on":[2],"automatic":[3],"speech":[4,12,83,135,159,191],"recognition":[5,136],"(ASR)":[6],"have":[7],"become":[8],"widely":[9],"used,":[10],"with":[11],"input":[13,38,59,93,143,175],"being":[14,31],"increasingly":[15],"utilized":[16],"to":[17,27,36,44,52,144,180],"create":[18],"documents.":[19],"However,":[20],"as":[21,72],"there":[22],"is":[23,64,137],"no":[24],"easy":[25],"way":[26],"distinguish":[28],"between":[29],"commands":[30,63,90],"issued":[32],"and":[33,46,56,62,98,163,184],"text":[34,73,142,174,192],"required":[35],"be":[37,53,70,92,126,188],"in":[39,94,100,128,152,190],"speech,":[40,162],"misrecognitions":[41],"are":[42,199],"difficult":[43],"identify":[45],"correct,":[47],"meaning":[48],"that":[49],"documents":[50],"need":[51],"manually":[54],"edited":[55],"corrected.":[57],"The":[58,104,123],"of":[60,132,172],"symbols":[61],"also":[65,200],"challenging":[66],"because":[67],"these":[68,77],"may":[69],"misrecognized":[71],"letters.":[74],"To":[75],"address":[76],"problems,":[78],"this":[79,153],"study":[80],"proposes":[81],"a":[82,95,101,115,119,129,173],"interaction":[84],"method":[85,106,124],"called":[86],"DualVoice,":[87],"by":[88],"which":[89],"can":[91,125,187],"whispered":[96,161,185],"voice":[97,186],"letters":[99],"normal":[102,158,183],"voice.":[103],"proposed":[105],"does":[107],"not":[108],"require":[109],"any":[110],"specialized":[111],"hardware":[112],"other":[113],"than":[114],"regular":[116],"microphone,":[117],"enabling":[118],"complete":[120],"hands-free":[121],"interaction.":[122],"used":[127,189],"wide":[130],"range":[131],"situations":[133],"where":[134],"already":[138],"available,":[139],"ranging":[140],"from":[141,160],"mobile/wearable":[145],"computing.":[146],"Two":[147],"neural":[148],"networks":[149],"were":[150],"designed":[151],"study,":[154],"one":[155],"for":[156,166],"discriminating":[157],"the":[164],"second":[165],"recognizing":[167],"whisper":[168],"speech.":[169],"A":[170],"prototype":[171],"system":[176],"was":[177],"then":[178],"developed":[179],"show":[181],"how":[182],"input.":[193],"Other":[194],"potential":[195],"applications":[196],"using":[197],"DualVoice":[198],"discussed.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2022-11-02T00:00:00"}