{"id":"https://openalex.org/W12678886","doi":"https://doi.org/10.21437/eurospeech.2003-387","title":"Speech shift: direct speech-input-mode switching through intentional control of voice pitch","display_name":"Speech shift: direct speech-input-mode switching through intentional control of voice pitch","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W12678886","doi":"https://doi.org/10.21437/eurospeech.2003-387","mag":"12678886"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-387","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-387","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","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/A5030650456","display_name":"Masataka Goto","orcid":"https://orcid.org/0000-0003-1167-0977"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masataka Goto","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Techno"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Techno","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090220807","display_name":"Yukihiro Omoto","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yukihiro Omoto","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108574981","display_name":"Katunobu Itou","orcid":null},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katunobu Itou","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Techno"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Techno","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101188700","display_name":"Tetsunori Kobayashi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tetsunori Kobayashi","raw_affiliation_strings":["School of Fundamental Science and Engineering"],"affiliations":[{"raw_affiliation_string":"School of Fundamental Science and Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030650456"],"corresponding_institution_ids":["https://openalex.org/I73613424"],"apc_list":null,"apc_paid":null,"fwci":1.3708,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.83094272,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1201","last_page":"1204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9995999932289124,"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/T12031","display_name":"Speech and dialogue systems","score":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9944999814033508,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9927999973297119,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7743970155715942},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7562553882598877},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6955846548080444},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.6021132469177246},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5236572623252869},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5075715780258179},{"id":"https://openalex.org/keywords/dictation","display_name":"Dictation","score":0.4792064130306244},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.43848860263824463},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.437051385641098},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3655654788017273},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.1828020215034485},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06347298622131348}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7743970155715942},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7562553882598877},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6955846548080444},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.6021132469177246},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5236572623252869},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5075715780258179},{"id":"https://openalex.org/C2779077324","wikidata":"https://www.wikidata.org/wiki/Q1087138","display_name":"Dictation","level":2,"score":0.4792064130306244},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.43848860263824463},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.437051385641098},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3655654788017273},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.1828020215034485},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06347298622131348},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.2003-387","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-387","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","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":9,"referenced_works":["https://openalex.org/W10719946","https://openalex.org/W57094479","https://openalex.org/W198720948","https://openalex.org/W1582730572","https://openalex.org/W1584626359","https://openalex.org/W1590070522","https://openalex.org/W1908300549","https://openalex.org/W2020933619","https://openalex.org/W2130416582"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W642007152","https://openalex.org/W4253660971","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W1909292483","https://openalex.org/W2052688117","https://openalex.org/W2550171623","https://openalex.org/W596245619"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,12,16,38,57,81,92,98,131],"speech-input":[4,17,27,74],"interface":[5,42],"function,":[6],"called":[7],"speech":[8,41],"shift,":[9],"that":[10,121],"enables":[11],"user":[13,58],"to":[14,128],"specify":[15],"mode":[18],"by":[19,43],"simply":[20],"changing":[21,72],"(shifting)":[22],"voice":[23,50],"pitch.":[24,51],"While":[25],"current":[26],"interfaces":[28],"have":[29],"used":[30],"only":[31],"verbal":[32],"information,":[33,48],"we":[34],"aimed":[35],"at":[36],"building":[37],"more":[39],"user-friendly":[40],"making":[44],"use":[45],"of":[46],"nonverbal":[47],"the":[49,55,61,73,104,122],"By":[52],"intentionally":[53],"controlling":[54],"pitch,":[56,101],"can":[59,87],"enter":[60],"same":[62],"word":[63,83],"with":[64,91,97],"it":[65],"having":[66],"different":[67],"meanings":[68],"(functions)":[69],"without":[70],"explicitly":[71],"mode.":[75],"Our":[76,114],"speech-shift":[77,123],"function":[78,124],"implemented":[79],"on":[80],"voice-enabled":[82],"processor,":[84],"for":[85],"example,":[86],"distinguish":[88],"an":[89],"utterance":[90],"high":[93],"pitch":[94],"from":[95,117],"one":[96],"normal":[99],"(low)":[100],"and":[102,130],"regard":[103],"former":[105],"as":[106,109],"voice-command-mode":[107],"input(suchasfile-menuandedit-menucommands)andthelatter":[108],"regular":[110],"dictation-mode":[111],"text":[112],"input.":[113],"experimental":[115],"results":[116],"twenty":[118],"subjects":[119],"showed":[120],"is":[125],"effective,":[126],"easy":[127],"use,":[129],"labor-saving":[132],"input":[133],"method.":[134]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
