{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T05:32:15Z","timestamp":1731735135213,"version":"3.28.0"},"reference-count":35,"publisher":"Information Processing Society of Japan","issue":"0","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Journal of Information Processing"],"published-print":{"date-parts":[[2024]]},"DOI":"10.2197\/ipsjjip.32.938","type":"journal-article","created":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T22:14:59Z","timestamp":1731622499000},"page":"938-947","source":"Crossref","is-referenced-by-count":0,"title":["Shadowed Speech: An Approach for Slowing Speech Rate Using Adaptive Delayed Auditory Feedback"],"prefix":"10.2197","volume":"32","author":[{"given":"Mariko","family":"Chiba","sequence":"first","affiliation":[{"name":"NTT DOCOMO, INC."}]},{"given":"Wataru","family":"Yamada","sequence":"additional","affiliation":[{"name":"NTT DOCOMO, INC."}]},{"given":"Keiichi","family":"Ochiai","sequence":"additional","affiliation":[{"name":"NTT DOCOMO, INC."}]}],"member":"1012","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] Black, J.W.: The effect of delayed side-tone upon vocal rate and intensity, <i>Journal of Speech and Hearing Disorders<\/i>, Vol.16, No.1, pp.56-60 (1951).","DOI":"10.1044\/jshd.1601.56"},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] Bosker, H.R., Reinisch, E. and Sjerps, M.J.: Cognitive load makes speech sound fast, but does not modulate acoustic context effects, <i>Journal of Memory and Language<\/i>, Vol.94, pp.166-176 (online), DOI: 10.1016\/j.jml.2016.12.002 (2017).","DOI":"10.1016\/j.jml.2016.12.002"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] Bubel, M., Jiang, R., Lee, C.H., Shi, W. and Tse, A.: AwareMe: Addressing Fear of Public Speech through Awareness, <i>Proc. 2016 CHI Conference Extended Abstracts on Human Factors in Computing Systems, CHI EA &apos;16<\/i>, pp.68-73, Association for Computing Machinery (online), DOI: 10.1145\/2851581.2890633 (2016).","DOI":"10.1145\/2851581.2890633"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] Costa, J., Jung, M.F., Czerwinski, M., Guimbreti\u00e8re, F., Le, T. and Choudhury, T.: Regulating Feelings During Interpersonal Conflicts by Changing Voice Self-perception, <i>Proc. 2018 CHI Conference on Human Factors in Computing Systems, CHI \u201918<\/i>, pp.1-13, Association for Computing Machinery (online), DOI: 10.1145\/3173574.3174205 (2018).","DOI":"10.1145\/3173574.3174205"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] Damian, I., Tan, C.S., Baur, T., Sch\u00f6ning, J., Luyten, K. and Andr\u00e9, E.: Augmenting Social Interactions: Realtime Behavioural Feedback using Social Signal Processing Techniques, <i>Proc. 33rd Annual ACM Conference on Human Factors in Computing Systems, CHI &apos;15<\/i>, pp.565-574, Association for Computing Machinery (online), DOI: 10.1145\/2702123.2702314 (2015).","DOI":"10.1145\/2702123.2702314"},{"key":"6","doi-asserted-by":"publisher","unstructured":"[6] de Jong, N.H. and Wempe, T.: Praat script to detect syllable nuclei and measure speech rate automatically, <i>Behavior Research Methods<\/i>, Vol.41, No.2, pp.385-390 (online), DOI: 10.3758\/BRM.41.2.385 (2009).","DOI":"10.3758\/BRM.41.2.385"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] Dermody, F.: Multimodal positive computing system for public speaking with real-time feedback, <i>Proc. 18th ACM International Conference on Multimodal Interaction, ICMI &apos;16<\/i>, pp.541-545, Association for Computing Machinery (online), DOI: 10.1145\/2993148.2997616 (2016).","DOI":"10.1145\/2993148.2997616"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] Fairbanks, G. and Guttman, N.: Effects of delayed auditory feedback upon articulation, <i>Journal of Speech and Hearing Research<\/i>, Vol.1, No.1, pp.12-22 (1958).","DOI":"10.1044\/jshr.0101.12"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] Giles, H., Coupland, N. and Coupland, J.: Accommodation theory: Communication, context, and consequence, <i>Contexts of accommodation: Developments in Applied Sociolinguistics<\/i>, Studies in emotion and social interaction, Editions de la Maison des Sciences de l&apos;Homme, Paris, France, pp.1-68 (online), DOI: 10.1017\/CBO9780511663673.001 (1991).","DOI":"10.1017\/CBO9780511663673.001"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] Grosjean, F. and Lane, H.: How the listener integrates the components of speaking rate, <i>Journal of Experimental Psychology: Human Perception and Performance<\/i>, Vol.2, No.4, p.538 (1976).","DOI":"10.1037\/\/0096-1523.2.4.538"},{"key":"11","unstructured":"[11] Hoogterp, B.: <i>Your Perfect Presentation: Speak in Front of Any Audience Anytime Anywhere and Never Be Nervous Again<\/i>, McGraw Hill Professional (2014)."},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] Kurihara, K., Goto, M., Ogata, J., Matsusaka, Y. and Igarashi, T.: Presentation sensei: A presentation training system using speech and image processing, <i>Proc. 9th International Conference on Multimodal Interfaces, ICMI &apos;07<\/i>, pp.358-365, Association for Computing Machinery (online), DOI: 10.1145\/1322192.1322256 (2007).","DOI":"10.1145\/1322192.1322256"},{"key":"13","unstructured":"[13] Kurihara, K. and Tsukada, K.: SpeechJammer: A System Utilizing Artificial Speech Disturbance with Delayed Auditory Feedback, <i>Proc. 2010 WISS Workshop on Interactive Systems and Software<\/i>, pp.77-82 (2010), available from &lt;https:\/\/www.wiss.org\/WISS2010Proceedings\/PDF\/P14.pdf&gt; (Japanese only)."},{"key":"14","unstructured":"[14] Kurihara, K. and Tsukada, K.: SpeechJammer: A System Utilizing Artificial Speech Disturbance with Delayed Auditory Feedback (2012), available from &lt;https:\/\/arxiv.org\/abs\/1202.6106&gt;."},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] Lee, A., Kawahara, T. and Shikano, K.: Julius\u2014An open source real-time large vocabulary recognition engine, <i>EUROSPEECH<\/i>, pp.1691-1694 (2001).","DOI":"10.21437\/Eurospeech.2001-396"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] Lui, A.K., Ng, S. and Wong, W.: A Novel Mobile Application for Training Oral Presentation Delivery Skills, <i>Technology in Education. Technology-Mediated Proactive Learning<\/i>, Lam, J., Ng, K.K., Cheung, S.K., Wong, T.L., Li, K.C. and Wang, F.L. (Eds.), Communications in Computer and Information Science, pp.79-89, Springer (online), DOI: 10.1007\/978-3-662-48978-9_8 (2015).","DOI":"10.1007\/978-3-662-48978-9_8"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] Maekawa, K., Yamazaki, M., Ogiso, T., Maruyama, T., Ogura, H., Kashino, W., Koiso, H., Yamaguchi, M., Tanaka, M. and Den, Y.: Balanced corpus of contemporary written Japanese, <i>Language Resources and Evaluation<\/i>, Vol.48, No.2, pp.345-371 (online), DOI: 10.1007\/s10579-013-9261-0(2014).","DOI":"10.1007\/s10579-013-9261-0"},{"key":"18","doi-asserted-by":"publisher","unstructured":"[18] Malloy, J.R., Nistal, D., Heyne, M., Tardif, M.C. and Bohland, J.W.: Delayed Auditory Feedback Elicits Specific Patterns of Serial Order Errors in a Paced Syllable Sequence Production Task, <i>Journal of Speech, Language, and Hearing Research<\/i>, Vol.65, No.5, pp.1800-1821 (online), DOI: 10.1044\/2022_JSLHR-21-00427 (2022).","DOI":"10.1044\/2022_JSLHR-21-00427"},{"key":"19","doi-asserted-by":"publisher","unstructured":"[19] Nakamura, A., Seiyama, N., Imai, A., Takagi, T. and Miyasaka, E.: A new approach to compensate degeneration of speech intelligibility for elderly listeners-development of a portable real time speech rate conversion system, <i>IEEE Trans. Broadcasting<\/i>, Vol.42, No.3, pp.285-293 (online), DOI: 10.1109\/11.536593 (1996).","DOI":"10.1109\/11.536593"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] Naruse, K., Takamichi, S., Tanikawa, T., Yoshida, S., Narumi, T. and Hirose, M.: Estimating confidence in voices using crowdsourcing for alleviating tension with altered auditory feedback, <i>Proc. Asian CHI Symposium 2019: Emerging HCI Research Collection, AsianHCI &apos;19<\/i>, pp.15-22, Association for Computing Machinery (online), DOI: 10.1145\/3309700.3338418 (2019).","DOI":"10.1145\/3309700.3338418"},{"key":"21","doi-asserted-by":"publisher","unstructured":"[21] Nash, G., Crimmins, G. and Oprescu, F.: If First-Year Students Are Afraid of Public Speaking Assessments What Can Teachers Do to Alleviate Such Anxiety?, <i>Assessment &amp; Evaluation in Higher Education<\/i>, Vol.41, No.4, pp.586-600 (online), DOI: 10.1080\/02602938.2015.1032212 (2016).","DOI":"10.1080\/02602938.2015.1032212"},{"key":"22","doi-asserted-by":"publisher","unstructured":"[22] Prafiyanto, H., Nose, T., Chiba, Y. and Ito, A.: Analysis of preferred speaking rate and pause in spoken easy Japanese for non-native listeners, <i>Acoustical Science and Technology<\/i>, Vol.39, No.2, pp.92-100 (online), DOI: 10.1250\/ast.39.92 (2018).","DOI":"10.1250\/ast.39.92"},{"key":"23","unstructured":"[23] Puckette, M. et al.: Pure Data: another integrated computer music environment, <i>Proc. 2nd Intercollege Computer Music Concerts<\/i>, pp.37-41 (1996)."},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] Rubin, S., Berthouzoz, F., Mysore, G.J. and Agrawala, M.: Capture-Time Feedback for Recording Scripted Narration, <i>Proc. 28th Annual ACM Symposium on User Interface Software &amp; Technology, UIST &apos;15<\/i>, pp.191-199, Association for Computing Machinery (online), DOI: 10.1145\/2807442.2807464 (2015).","DOI":"10.1145\/2807442.2807464"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] Schneider, J., B\u00f6rner, D., van Rosmalen, P. and Specht, M.: Presentation Trainer, your Public Speaking Multimodal Coach, <i>Proc. 2015 ACM on International Conference on Multimodal Interaction, ICMI &apos;15<\/i>, pp.539-546, Association for Computing Machinery (online), DOI: 10.1145\/2818346.2830603 (2015).","DOI":"10.1145\/2818346.2830603"},{"key":"26","doi-asserted-by":"crossref","unstructured":"[26] Sohn, J., Kim, N.S. and Sung, W.: A statistical model-based voice activity detection, <i>IEEE Signal Processing Letters<\/i>, Vol.6, No.1, pp.1-3 (online), DOI: 10.1109\/97.736233 (1999).","DOI":"10.1109\/97.736233"},{"key":"27","doi-asserted-by":"publisher","unstructured":"[27] Stuart, A., Kalinowski, J. and Rastatter, M.P.: Effect of monaural and binaural altered auditory feedback on stuttering frequency, <i>The Journal of the Acoustical Society of America<\/i>, Vol.101, No.6, pp.3806-3809 (online), DOI: 10.1121\/1.418387 (1997).","DOI":"10.1121\/1.418387"},{"key":"28","doi-asserted-by":"publisher","unstructured":"[28] Stuart, A., Kalinowski, J., Rastatter, M.P. and Lynch, K.: Effect of delayed auditory feedback on normal speakers at two speech rates, <i>The Journal of the Acoustical Society of America<\/i>, Vol.111, No.5, pp.2237-2241 (online), DOI: 10.1121\/1.1466868 (2002).","DOI":"10.1121\/1.1466868"},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] Tanveer, M.I., Lin, E. and Hoque, M.: Rhema: A Real-Time In-Situ Intelligent Interface to Help People with Public Speaking, <i>Proc. 20th International Conference on Intelligent User Interfaces, IUI &apos;15<\/i>, pp.286-295, Association for Computing Machinery (online), DOI: 10.1145\/2678025.2701386 (2015).","DOI":"10.1145\/2678025.2701386"},{"key":"30","unstructured":"[30] Casa Futura Technologies: SmallTalk DAF helps stutterers speak fluently (2022)."},{"key":"31","doi-asserted-by":"publisher","unstructured":"[31] Trinh, H., Asadi, R., Edge, D. and Bickmore, T.: RoboCOP: A Robotic Coach for Oral Presentations, <i>Proc. ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies<\/i>, Vol.1, No.2, pp.27:1-27:24 (online), DOI: 10.1145\/3090092 (2017).","DOI":"10.1145\/3090092"},{"key":"32","doi-asserted-by":"crossref","unstructured":"[32] Viterbi, A.: Error bounds for convolutional codes and an asymptotically optimum decoding algorithm, <i>IEEE Trans. Information Theory<\/i>, Vol.13, No.2, pp.260-269 (1967).","DOI":"10.1109\/TIT.1967.1054010"},{"key":"33","doi-asserted-by":"crossref","unstructured":"[33] Wang, X., Zeng, H., Wang, Y., Wu, A., Sun, Z., Ma, X. and Qu, H.: VoiceCoach: Interactive Evidence-based Training for Voice Modulation Skills in Public Speaking, <i>Proc. 2020 CHI Conference on Human Factors in Computing Systems, CHI &apos;20<\/i>, pp.1-12, Association for Computing Machinery (online), DOI: 10.1145\/3313831.3376726 (2020).","DOI":"10.1145\/3313831.3376726"},{"key":"34","doi-asserted-by":"crossref","unstructured":"[34] Yu, D. and Deng, L.: <i>Automatic Speech Recognition<\/i>, Signals and Communication Technology, Springer London (2015).","DOI":"10.1007\/978-1-4471-5779-3"},{"key":"35","doi-asserted-by":"crossref","unstructured":"[35] Zhang, X., Miyaki, T. and Rekimoto, J.: WithYou: Automated Adaptive Speech Tutoring With Context-Dependent Speech Recognition, <i>Proc. 2020 CHI Conference on Human Factors in Computing Systems, CHI &apos;20<\/i>, pp.1-12, Association for Computing Machinery (online), DOI: 10.1145\/3313831.3376322(2020).","DOI":"10.1145\/3313831.3376322"}],"container-title":["Journal of Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/ipsjjip\/32\/0\/32_938\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T03:54:47Z","timestamp":1731729287000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/ipsjjip\/32\/0\/32_938\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":35,"journal-issue":{"issue":"0","published-print":{"date-parts":[[2024]]}},"URL":"https:\/\/doi.org\/10.2197\/ipsjjip.32.938","relation":{},"ISSN":["1882-6652"],"issn-type":[{"type":"electronic","value":"1882-6652"}],"subject":[],"published":{"date-parts":[[2024]]}}}