{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T12:28:25Z","timestamp":1725884905629},"publisher-location":"Tokyo","reference-count":24,"publisher":"Springer Japan","isbn-type":[{"type":"print","value":"9784431565338"},{"type":"electronic","value":"9784431565352"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-4-431-56535-2_3","type":"book-chapter","created":{"date-parts":[[2017,4,20]],"date-time":"2017-04-20T08:19:35Z","timestamp":1492676375000},"page":"77-114","source":"Crossref","is-referenced-by-count":1,"title":["User Generated Dialogue Systems: uDialogue"],"prefix":"10.1007","author":[{"given":"Keiichi","family":"Tokuda","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akinobu","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshihiko","family":"Nankaku","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keiichiro","family":"Oura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kei","family":"Hashimoto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daisuke","family":"Yamamoto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ichi","family":"Takumi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takahiro","family":"Uchiya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuhei","family":"Tsutsumi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steve","family":"Renals","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,4,21]]},"reference":[{"key":"3_CR1","unstructured":"HTS: HMM speech synthesis toolkit, http:\/\/www.hts.nitech.ac.jp\/"},{"key":"3_CR2","unstructured":"Open JTalk: Japanese text-to-speech system, http:\/\/open-jtalk.sourceforge.net\/"},{"key":"3_CR3","unstructured":"Julius: Open-source large vocabulary continuous speech recognition engine, http:\/\/julius.sourceforge.jp\/"},{"key":"3_CR4","unstructured":"MMDAgent: Toolkit for building voice interaction systems, http:\/\/www.mmdagent.jp\/"},{"key":"3_CR5","unstructured":"T. Funayachi, K. Oura, Y. Nankaku, A. Lee, K. Tokuda, A simple dialogue description based on finite state transducers for user-generated spoken dialog content, in Proceedings of ASJ 2013 Autumn Meeting, 2-P-28, pp. 223\u2013224, 25\u201327 Sept 2013. (in Japanese)"},{"key":"3_CR6","doi-asserted-by":"publisher","unstructured":"K. Nakamura, K. Hashimoto, Y. Nankaku, K. Tokuda, Integration of spectral feature extraction and modeling for HMM-based speech synthesis. IEICE Trans. Inf. Syst. E97-D(6), 1438\u20131448 (2014)","DOI":"10.1587\/transinf.E97.D.1438"},{"key":"3_CR7","doi-asserted-by":"publisher","unstructured":"S. Takaki, Y. Nankaku, K. Tokuda, Contextual partial additive structure for HMM-based speech synthesis, in 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Vancouver, Canada, pp. 7878\u20137882, 2013","DOI":"10.1109\/ICASSP.2013.6639198"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"R. Dall, M. Tomalin, M. Wester, W. Byrne, S. King, Investigating automatic & human filled pause insertion for speech synthesis, in Proceedings of Interspeech, 2014","DOI":"10.21437\/Interspeech.2014-11"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"S. R. Gangireddy, S. Renals, Y. Nankaku, A. Lee, Prosodically-enhanced recurrent neural network language models, in Proceedings of Interspeech 2015, Dresden, Sept 2015","DOI":"10.21437\/Interspeech.2016-1342"},{"key":"3_CR10","doi-asserted-by":"publisher","unstructured":"K. Hashimoto, K. Oura, Y. Nankaku, K. Tokuda, The effect of neural networks in statistical parametric speech synthesis, in Proceedings of 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2015), Brisbane, Australia, pp. 4455\u20134459, 19\u201324 Apr 2015","DOI":"10.1109\/ICASSP.2015.7178813"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"S. Takaki, S. Kim, J. Yamagishi, J.J. Kim, Multiple feed-forward deep neural networks for statistical parametric speech synthesis, in Proceedings of Interspeech, vol. 2015, pp. 2242\u20132246, 2015","DOI":"10.21437\/Interspeech.2015-133"},{"key":"3_CR12","doi-asserted-by":"publisher","unstructured":"K. Hashimoto, K. Oura, Y. Nankaku, K. Tokuda, Trajectory training considering global variance for speech synthesis based on neural networks, in Proceedings of 2016 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2016), Shanghai, China, pp. 5600\u20135604, 20\u201325 Mar 2016","DOI":"10.1109\/ICASSP.2016.7472749"},{"key":"3_CR13","unstructured":"K. Sawada, K. Hashimoto, K. Oura, Y. Nankaku, and K. Tokuda, \u201cEvaluation of text-to-speech system construction for unknown-pronunciation languages,\u201d Technical Report of IEICE, vol. 115, no. 346, SP2015-80, pp. 93\u201398, 2\u20133 Dec 2015"},{"key":"3_CR14","unstructured":"S.R. Gangireddy, Q. Huang, S. Renals, F. McInnes, J. Yamagishi, in Topic Model Features in Neural Network Language Models, (UK Speech Meeting, 2013)"},{"key":"3_CR15","unstructured":"CSTR VCTK Corpus, http:\/\/www.udialogue.org\/ja\/download-ja.html"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"D. Yamamoto, K. Oura, R. Nishimura, T. Uchiya, A. Lee, I. Takumi, Keiichi Tokuda, Voice interaction system with 3D-CG human agent for Stand-alone smartphones, in Proceedings of the 2nd International Conference on Human Agent Interaction (ACM digital library, 2014), pp. 320\u2013330","DOI":"10.1145\/2658861.2658874"},{"key":"3_CR17","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1007\/978-3-319-23467-0_9","volume":"614","author":"K Wakabayashi","year":"2016","unstructured":"K. Wakabayashi, D. Yamamoto, N. Takahashi, A voice dialog editor based on finite state transducer using composite state for tablet devices, computer and information science 2015. Stud. Comput. Intell. 614, 125\u2013139 (2016)","journal-title":"Stud. Comput. Intell."},{"key":"3_CR18","doi-asserted-by":"publisher","unstructured":"R. Nishimura, D. Yamamoto, T. Uchiya, I. Takumi, Development of a dialogue scenario editor on a web browser for a spoken dialogue system, in Proceedings of the Second International Conference on Human-agent Interaction, pp. 129\u2013132, 2014","DOI":"10.1145\/2658861.2658904"},{"key":"3_CR19","doi-asserted-by":"publisher","unstructured":"Y. Matsushita, T. Uchiya, R. Nishimura, D. Yamamoto, I. Takumi, Crowdsourcing environment to create voice interaction scenario of spoken dialogue system, in Proceedings of the 18th International Conference on Network-Based Information Systems (NBiS-2015), pp. 500\u2013504, 2015","DOI":"10.1109\/NBiS.2015.74"},{"key":"3_CR20","first-page":"321","volume":"2015","author":"Y Matsushita","year":"2015","unstructured":"Y. Matsushita, T. Uchiya, R. Nishimura, D. Yamamoto, I. Takumi, Experiment and evaluation of crowd sourcing model for creation of voice interaction scenario. Proc. IEEE GCCE 2015, 321\u2013322 (2015)","journal-title":"Proc. IEEE GCCE"},{"key":"3_CR21","first-page":"298","volume":"2015","author":"T Uchiya","year":"2015","unstructured":"T. Uchiya, R. Nakano, D. Yamamoto, R. Nishimura, I. Takumi, Extension with intelligent agents for the spoken dialogue system for smartphones. Proc. IEEE GCCE 2015, 298\u2013299 (2015)","journal-title":"Proc. IEEE GCCE"},{"key":"3_CR22","unstructured":"T. Uchiya, D. Yamamoto, M. Shibakawa, M. Yoshida, R. Nishimura, I. Takumi, Development of spoken dialogue service based on video call named \u201cMobile Meichan\u201d. Proc. JAWS2012 (2012). (in Japanese)"},{"key":"3_CR23","unstructured":"T. Uchiya, M. Yoshida, D. Yamamoto, R. Nishimura, I. Takumi, Design and implementation of open-campus event system with voice interaction agent. Int. J. Mob. Multimed. 11(3, 4), 237\u2013250 (2015)"},{"key":"3_CR24","first-page":"529","volume":"2014","author":"R Nishimura","year":"2014","unstructured":"R. Nishimura, K. Sugioka, D. Yamamoto, T. Uchiya, I. Takumi, A VoIP-based voice interaction system for a virtual telephone operator using video calls. Proc. IEEE GCCE 2014, 529\u2013532 (2014)","journal-title":"Proc. IEEE GCCE"}],"container-title":["Human-Harmonized Information Technology, Volume 2"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-4-431-56535-2_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T06:08:29Z","timestamp":1692770909000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-4-431-56535-2_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9784431565338","9784431565352"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-4-431-56535-2_3","relation":{},"subject":[],"published":{"date-parts":[[2017]]}}}