{"id":"https://openalex.org/W4225122476","doi":"https://doi.org/10.1145/3491101.3519700","title":"DualVoice: A Speech Interaction Method Using Whisper-Voice as Commands","display_name":"DualVoice: A Speech Interaction Method Using Whisper-Voice as Commands","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225122476","doi":"https://doi.org/10.1145/3491101.3519700"},"language":"en","primary_location":{"id":"doi:10.1145/3491101.3519700","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3491101.3519700","pdf_url":null,"source":{"id":"https://openalex.org/S4363607762","display_name":"CHI Conference on Human Factors in Computing Systems Extended Abstracts","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CHI Conference on Human Factors in Computing Systems Extended Abstracts","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/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"],"raw_orcid":null,"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":2,"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":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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":0.8769506812095642},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7909343242645264},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6760664582252502},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5086570382118225},{"id":"https://openalex.org/keywords/voice-command-device","display_name":"Voice command device","score":0.48133787512779236},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.47309640049934387},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4405830204486847},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4372623562812805},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4301515519618988},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42659056186676025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32493120431900024},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.05680546164512634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8769506812095642},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7909343242645264},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6760664582252502},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5086570382118225},{"id":"https://openalex.org/C178718744","wikidata":"https://www.wikidata.org/wiki/Q2350070","display_name":"Voice command device","level":2,"score":0.48133787512779236},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.47309640049934387},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4405830204486847},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4372623562812805},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4301515519618988},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42659056186676025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32493120431900024},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.05680546164512634},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3491101.3519700","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3491101.3519700","pdf_url":null,"source":{"id":"https://openalex.org/S4363607762","display_name":"CHI Conference on Human Factors in Computing Systems Extended Abstracts","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CHI Conference on Human Factors in Computing Systems Extended Abstracts","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1063213209","display_name":null,"funder_award_id":"JPMJMS2012","funder_id":"https://openalex.org/F4320338247","funder_display_name":"Moonshot Research and Development Program"}],"funders":[{"id":"https://openalex.org/F4320338247","display_name":"Moonshot Research and Development Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2437658533","https://openalex.org/W2768731046","https://openalex.org/W2896622783","https://openalex.org/W3161865163"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W4253660971","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2069501481","https://openalex.org/W1909292483","https://openalex.org/W2052688117","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W596245619"],"abstract_inverted_index":{"Applications":[0],"based":[1],"on":[2],"speech":[3,10,68,120,134],"recognition":[4,121],"have":[5],"become":[6],"widely":[7],"used,":[8],"and":[9,50,82,108,138],"input":[11,48,77],"is":[12,21,44,122],"increasingly":[13],"being":[14],"utilized":[15],"to":[16,24,33,47],"create":[17],"documents.":[18],"However,":[19],"it":[20,31,109],"still":[22],"difficult":[23,46],"correct":[25],"misrecognition":[26],"by":[27,36],"speech,":[28,137],"which":[29,74],"makes":[30],"necessary":[32],"re-edit":[34],"documents":[35],"other":[37,97],"means":[38],"such":[39],"as":[40,57],"manual":[41],"input.":[42],"It":[43],"also":[45],"symbols":[49],"commands":[51,75],"because":[52],"these":[53,63],"may":[54],"be":[55,111],"misrecognized":[56],"text":[58],"letters.":[59],"To":[60],"deal":[61],"with":[62],"problems,":[64],"we":[65],"propose":[66],"a":[67,79,85,99,104,114],"interaction":[69],"method":[70,90],"called":[71],"DualVoice":[72],"in":[73,78,84,113],"are":[76],"whispered":[80,136],"voice":[81],"letters":[83],"normal":[86,133],"voice.":[87],"The":[88],"proposed":[89],"does":[91],"not":[92],"require":[93],"any":[94],"special":[95],"hardware":[96],"than":[98],"regular":[100],"microphone,":[101],"thus":[102],"enabling":[103],"complete":[105],"hands-free":[106],"interaction,":[107],"can":[110],"used":[112],"wide":[115],"range":[116],"of":[117],"situations":[118],"where":[119],"already":[123],"available.":[124],"We":[125],"designed":[126],"two":[127],"neural":[128],"networks,":[129],"one":[130],"for":[131,141],"discriminating":[132],"from":[135],"the":[139],"second":[140],"recognizing":[142],"whisper":[143],"speech.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}