{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T10:10:55Z","timestamp":1778235055287,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,16]]},"DOI":"10.1145\/3795011.3795040","type":"proceedings-article","created":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T08:59:16Z","timestamp":1778230756000},"page":"631-641","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["VoiceCoach: An Augmented Human System for Learning Invisible Vocal Techniques"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1297-819X","authenticated-orcid":false,"given":"Yaolin","family":"Zheng","sequence":"first","affiliation":[{"name":"The University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1781-6212","authenticated-orcid":false,"given":"Yoshio","family":"Ishiguro","sequence":"additional","affiliation":[{"name":"The University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,5,8]]},"reference":[{"key":"e_1_3_3_1_2_2","first-page":"12449","volume-title":"Advances in Neural Information Processing Systems","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations. In Advances in Neural Information Processing Systems , Vol.\u00a033. Curran Associates, Inc., Red Hook, NY, USA, 12449\u201312460. https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/92d1e1eb1cd6f9fba3227870bb6d7f07-Abstract.html"},{"key":"e_1_3_3_1_3_2","first-page":"1","volume-title":"Proceedings of the Conference on Interdisciplinary Musicology (CIM04)","author":"Callaghan Jean","year":"2004","unstructured":"Jean Callaghan, William Thorpe, and Jan van Doorn. 2004. The Science of Singing and Seeing. In Proceedings of the Conference on Interdisciplinary Musicology (CIM04). Graz, Austria, 1\u201310. Conference dates: 15\u201318 April 2004.."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR-Adjunct64951.2024.00034"},{"key":"e_1_3_3_1_5_2","unstructured":"Laura Crocco and David Meyer. 2021. Motor Learning and Teaching Singing: An Overview. Journal of Singing 77 5 (2021) 693\u2013702."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.4018\/979-8-3693-8432-9.ch002"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","unstructured":"Behnam Faghih and Joseph Timoney. 2022. Annotated-VocalSet: A Singing Voice Dataset. Applied Sciences 12 18 (2022) 9257. 10.3390\/app12189257","DOI":"10.3390\/app12189257"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","unstructured":"Dhanshree\u00a0R. Gunjawate Rohit Ravi and Rajashekhar Bellur. 2018. Acoustic Analysis of Voice in Singers: A Systematic Review. Journal of Speech Language and Hearing Research 61 1 (2018) 40\u201351. 10.1044\/2017_JSLHR-S-17-0145","DOI":"10.1044\/2017_JSLHR-S-17-0145"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","unstructured":"Christian\u00a0T. Herbst. 2020. Electroglottography\u2014An Update. Journal of Voice 34 4 (2020) 503\u2013526. 10.1016\/j.jvoice.2018.12.014","DOI":"10.1016\/j.jvoice.2018.12.014"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","unstructured":"David Hoppe Makiko Sadakata and Peter Desain. 2006. Development of Real-Time Visual Feedback Assistance in Singing Training: A Review. Journal of Computer Assisted Learning 22 4 (2006) 308\u2013316. 10.1111\/j.1365-2729.2006.00178.x","DOI":"10.1111\/j.1365-2729.2006.00178.x"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","unstructured":"David\u00a0M. Howard. 2005. Technology for Real-Time Visual Feedback in Singing Lessons. Research Studies in Music Education 24 1 (2005) 40\u201357. 10.1177\/1321103X050240010401","DOI":"10.1177\/1321103X050240010401"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","unstructured":"David\u00a0M. Howard Judith Brereton Graham\u00a0F. Welch Evangelos Himonides Mark DeCosta James Williams and A.\u00a0W. Howard. 2007. Are Real-Time Displays of Benefit in the Singing Studio? An Exploratory Study. Journal of Voice 21 1 (2007) 20\u201334. 10.1016\/j.jvoice.2005.10.003","DOI":"10.1016\/j.jvoice.2005.10.003"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","unstructured":"Jing Kang Austin Scholp and Jack\u00a0J. Jiang. 2018. A Review of the Physiological Effects and Mechanisms of Singing. Journal of Voice 32 4 (2018) 390\u2013395. 10.1016\/j.jvoice.2017.07.008","DOI":"10.1016\/j.jvoice.2017.07.008"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"K.\u00a0L. Kim J. Lee S. Kum C.\u00a0L. Park and J. Nam. 2020. Semantic Tagging of Singing Voices in Popular Music Recordings. IEEE\/ACM Transactions on Audio Speech and Language Processing 28 (2020) 1656\u20131668.","DOI":"10.1109\/TASLP.2020.2993893"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","unstructured":"Filipa M.\u00a0B. L\u00e3 and Maria\u00a0B. Fiuza. 2022. Real-Time Visual Feedback in Singing Pedagogy: Current Trends and Future Directions. Applied Sciences 12 21 (2022) 10781. 10.3390\/app122110781","DOI":"10.3390\/app122110781"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","unstructured":"Filipa M.\u00a0B. L\u00e3 and Johan Sundberg. 2015. Contact Quotient Versus Closed Quotient: A Comparative Study on Professional Male Singers. Journal of Voice 29 2 (2015) 148\u2013154. 10.1016\/j.jvoice.2014.07.005","DOI":"10.1016\/j.jvoice.2014.07.005"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","unstructured":"Juheon Lee Hyeong-Seok Choi and Kyogu Lee. 2022. Expressive Singing Synthesis Using Local Style Token and Dual-Path Pitch Encoder. arXiv preprint. arxiv:https:\/\/arXiv.org\/abs\/2204.0324910.48550\/arXiv.2204.03249","DOI":"10.48550\/arXiv.2204.03249"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR59233.2023.00101"},{"key":"e_1_3_3_1_19_2","first-page":"1048","volume-title":"The Oxford Handbook of Singing","author":"Nair Garyth","year":"2019","unstructured":"Garyth Nair, David\u00a0M. Howard, and Graham\u00a0F. Welch. 2019. Practical Voice Analyses and Their Application in the Studio. In The Oxford Handbook of Singing. Oxford University Press, Oxford, UK, 1048\u20131070."},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3689050.3704800"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3490149.3503581"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3519391.3519412"},{"key":"e_1_3_3_1_23_2","volume-title":"Singing for the Stars: A Complete Program for Training Your Voice","author":"Riggs Seth","year":"1998","unstructured":"Seth Riggs. 1998. Singing for the Stars: A Complete Program for Training Your Voice. Alfred Music Publishing, Van Nuys, CA, USA. Illustrated, revised; compiled\/editor credit appears in some catalogs (e.g., John Dominick Carratello).."},{"key":"e_1_3_3_1_24_2","volume-title":"Complete Vocal Technique (3 ed.)","author":"Sadolin Cathrine","year":"2012","unstructured":"Cathrine Sadolin. 2012. Complete Vocal Technique (3 ed.). CVI Publications, Copenhagen, Denmark."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","unstructured":"Steffen Schneider Alexei Baevski Ronan Collobert and Michael Auli. 2019. wav2vec: Unsupervised Pre-Training for Speech Recognition. arXiv preprint. arxiv:https:\/\/arXiv.org\/abs\/1904.0586210.48550\/arXiv.1904.05862","DOI":"10.48550\/arXiv.1904.05862"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373625.3418008"},{"key":"e_1_3_3_1_27_2","volume-title":"The Science of the Singing Voice","author":"Sundberg Johan","year":"1987","unstructured":"Johan Sundberg. 1987. The Science of the Singing Voice. Northern Illinois University Press, DeKalb, IL, USA."},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642324"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","unstructured":"Ingo\u00a0R. Titze. 2023. Simulation of Vocal Loudness Regulation with Lung Pressure Vocal Fold Adduction and Source-Airway Interaction. Journal of Voice 37 2 (2023) 152\u2013161. 10.1016\/j.jvoice.2020.10.021First published online 2021; assigned to an issue in 2023..","DOI":"10.1016\/j.jvoice.2020.10.021"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","unstructured":"George Waddell and Aaron Williamon. 2019. Technology Use and Attitudes in Music Learning. Frontiers in ICT 6 (2019) 11. 10.3389\/fict.2019.00011","DOI":"10.3389\/fict.2019.00011"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","unstructured":"Graham\u00a0F. Welch David\u00a0M. Howard Evangelos Himonides and Judith Brereton. 2005. Real-Time Feedback in the Singing Studio: An Innovatory Action-Research Project Using New Voice Technology. Music Education Research 7 2 (2005) 225\u2013249. 10.1080\/14613800500169779","DOI":"10.1080\/14613800500169779"},{"key":"e_1_3_3_1_32_2","unstructured":"Pat\u00a0H. Wilson Kerrie Lee Jean Callaghan and C.\u00a0William Thorpe. 2008. Learning to Sing in Tune: Does Real-Time Visual Feedback Help? Journal of Interdisciplinary Music Studies 2 1&2 (2008) 157\u2013172. Article #0821210 (as listed by Sing & See research bibliography).."},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581210"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","unstructured":"Yuya Yamamoto Juhan Nam and Hiroko Terasawa. 2022. Analysis and Detection of Singing Techniques in Repertoires of J-POP Solo Singers. arXiv preprint. arxiv:https:\/\/arXiv.org\/abs\/2210.1736710.48550\/arXiv.2210.17367","DOI":"10.48550\/arXiv.2210.17367"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","unstructured":"Tet\u00a0Fei Yap Julien Epps Eliathamby Ambikairajah and Eric H.\u00a0C. Choi. 2015. Voice Source Under Cognitive Load: Effects and Classification. Speech Communication 72 (2015) 74\u201395. 10.1016\/j.specom.2015.05.007","DOI":"10.1016\/j.specom.2015.05.007"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","unstructured":"J. Zhao Low Qi\u00a0Hong Chetwin and Ye Wang. 2024. SinTechSVS: A Singing Technique Controllable Singing Voice Synthesis System. IEEE\/ACM Transactions on Audio Speech and Language Processing 32 (2024) 2641\u20132653. 10.1109\/TASLP.2024.3394769","DOI":"10.1109\/TASLP.2024.3394769"}],"event":{"name":"AHs 2026: The Augmented Humans International Conference 2026","location":"Okinawa Japan","acronym":"AHs 2026"},"container-title":["Proceedings of the Augmented Humans International Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3795011.3795040","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T09:28:04Z","timestamp":1778232484000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3795011.3795040"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":35,"alternative-id":["10.1145\/3795011.3795040","10.1145\/3795011"],"URL":"https:\/\/doi.org\/10.1145\/3795011.3795040","relation":{},"subject":[],"published":{"date-parts":[[2026,3,16]]},"assertion":[{"value":"2026-05-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}