{"id":"https://openalex.org/W7160667351","doi":"https://doi.org/10.1145/3795011.3795040","title":"VoiceCoach: An Augmented Human System for Learning Invisible Vocal Techniques","display_name":"VoiceCoach: An Augmented Human System for Learning Invisible Vocal Techniques","publication_year":2026,"publication_date":"2026-03-16","ids":{"openalex":"https://openalex.org/W7160667351","doi":"https://doi.org/10.1145/3795011.3795040"},"language":null,"primary_location":{"id":"doi:10.1145/3795011.3795040","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3795011.3795040","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Augmented Humans International Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3795011.3795040","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135722489","display_name":"Yaolin Zheng","orcid":"https://orcid.org/0009-0009-1297-819X"},"institutions":[{"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":false,"raw_author_name":"Yaolin Zheng","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0009-1297-819X","affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069105845","display_name":"Yoshio Ishiguro","orcid":"https://orcid.org/0000-0002-1781-6212"},"institutions":[{"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":false,"raw_author_name":"Yoshio Ishiguro","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-1781-6212","affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.5538516,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"631","last_page":"641"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.2689000070095062,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.2689000070095062,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10667","display_name":"Emotion and Mood Recognition","score":0.13680000603199005,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.09719999879598618,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6050999760627747},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.54339998960495},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4830000102519989},{"id":"https://openalex.org/keywords/auditory-feedback","display_name":"Auditory feedback","score":0.4092999994754791},{"id":"https://openalex.org/keywords/augmented-reality","display_name":"Augmented reality","score":0.35190001130104065},{"id":"https://openalex.org/keywords/sensory-cue","display_name":"Sensory cue","score":0.3221000134944916},{"id":"https://openalex.org/keywords/vocal-folds","display_name":"Vocal folds","score":0.3091000020503998},{"id":"https://openalex.org/keywords/phonation","display_name":"Phonation","score":0.3050999939441681}],"concepts":[{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6050999760627747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.588699996471405},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.54339998960495},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4830000102519989},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44920000433921814},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.41679999232292175},{"id":"https://openalex.org/C2779864741","wikidata":"https://www.wikidata.org/wiki/Q4820027","display_name":"Auditory feedback","level":2,"score":0.4092999994754791},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4023999869823456},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3646000027656555},{"id":"https://openalex.org/C153715457","wikidata":"https://www.wikidata.org/wiki/Q254183","display_name":"Augmented reality","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3352000117301941},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C2780336059","wikidata":"https://www.wikidata.org/wiki/Q215558","display_name":"Vocal folds","level":3,"score":0.3091000020503998},{"id":"https://openalex.org/C173988693","wikidata":"https://www.wikidata.org/wiki/Q678132","display_name":"Phonation","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2989000082015991},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C2776575663","wikidata":"https://www.wikidata.org/wiki/Q1514944","display_name":"Vocal learning","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C22033958","wikidata":"https://www.wikidata.org/wiki/Q7167036","display_name":"Perceptual learning","level":3,"score":0.2782000005245209},{"id":"https://openalex.org/C3020716817","wikidata":"https://www.wikidata.org/wiki/Q4132092","display_name":"Visual feedback","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C102964294","wikidata":"https://www.wikidata.org/wiki/Q4820028","display_name":"Auditory learning","level":3,"score":0.2766999900341034},{"id":"https://openalex.org/C28427503","wikidata":"https://www.wikidata.org/wiki/Q13580300","display_name":"Internal model","level":3,"score":0.26750001311302185},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3795011.3795040","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3795011.3795040","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Augmented Humans International Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3795011.3795040","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3795011.3795040","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Augmented Humans International Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.757532000541687}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W407865814","https://openalex.org/W1703011138","https://openalex.org/W2059305518","https://openalex.org/W2085135962","https://openalex.org/W2103889926","https://openalex.org/W2107317015","https://openalex.org/W2747457316","https://openalex.org/W2783763901","https://openalex.org/W2922499188","https://openalex.org/W2944632629","https://openalex.org/W3027728407","https://openalex.org/W3097294246","https://openalex.org/W3111611745","https://openalex.org/W4211033543","https://openalex.org/W4224294423","https://openalex.org/W4225919501","https://openalex.org/W4286797312","https://openalex.org/W4296095733","https://openalex.org/W4307216906","https://openalex.org/W4307934381","https://openalex.org/W4366549513","https://openalex.org/W4389296445","https://openalex.org/W4396214748","https://openalex.org/W4396833497","https://openalex.org/W4404915142","https://openalex.org/W4407941444","https://openalex.org/W4409125382"],"related_works":[],"abstract_inverted_index":{"Learning":[0],"complex":[1],"vocal":[2,22,35],"techniques":[3],"such":[4],"as":[5],"mixed":[6],"voice":[7],"requires":[8],"learners":[9],"to":[10,15,65],"map":[11],"subtle":[12],"auditory":[13],"cues":[14],"largely":[16],"invisible":[17],"physiological":[18],"control":[19],"of":[20,55],"the":[21],"apparatus.":[23],"This":[24],"process":[25],"is":[26],"particularly":[27],"challenging":[28],"for":[29],"self-learners,":[30],"who":[31],"must":[32],"infer":[33],"internal":[34,60],"mechanisms":[36],"without":[37],"direct":[38],"visual":[39],"feedback":[40],"or":[41],"continuous":[42],"expert":[43],"guidance.":[44],"From":[45],"an":[46],"augmented":[47],"humans":[48],"perspective,":[49],"this":[50],"setting":[51],"exemplifies":[52],"a":[53],"class":[54],"\u201cinvisible":[56],"skills\u201d":[57],"in":[58],"which":[59],"bodily":[61],"states":[62],"are":[63],"hard":[64],"perceive,":[66],"interpret,":[67],"and":[68],"control.":[69]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-09T00:00:00"}