{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T18:03:12Z","timestamp":1725904992345},"publisher-location":"Cham","reference-count":15,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319638584"},{"type":"electronic","value":"9783319638591"}],"license":[{"start":{"date-parts":[[2017,7,18]],"date-time":"2017-07-18T00:00:00Z","timestamp":1500336000000},"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":[[2018]]},"DOI":"10.1007\/978-3-319-63859-1_13","type":"book-chapter","created":{"date-parts":[[2017,7,17]],"date-time":"2017-07-17T07:54:54Z","timestamp":1500278094000},"page":"97-103","source":"Crossref","is-referenced-by-count":0,"title":["Voice Conversion from Arbitrary Speakers Based on Deep Neural Networks with Adversarial Learning"],"prefix":"10.1007","author":[{"given":"Sou","family":"Miyamoto","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takashi","family":"Nose","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suzunosuke","family":"Ito","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harunori","family":"Koike","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuya","family":"Chiba","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akinori","family":"Ito","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takahiro","family":"Shinozaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,7,18]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Desai, S., Raghavendra, E.V., Yegnanarayana, B., Black, A.W., Prahallad, K.: Voice conversion using artificial neural networks. In: Proceedings of the ICASSP, pp. 3893\u20133896 (2009)","DOI":"10.1109\/ICASSP.2009.4960478"},{"issue":"1","key":"13_CR2","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1109\/TASSP.1986.1164788","volume":"34","author":"S Furui","year":"1986","unstructured":"Furui, S.: Speaker-independent isolated word recognition using dynamic features of speech spectrum. IEEE Trans. Acoust. Speech Sig. Process. 34(1), 52\u201359 (1986)","journal-title":"IEEE Trans. Acoust. Speech Sig. Process."},{"key":"13_CR3","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672\u20132680 (2014)"},{"issue":"8","key":"13_CR4","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural comput."},{"key":"13_CR5","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint (2015). arXiv:1502.03167"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Kain, A., Macon, M.: Spectral voice conversion for text-to-speech synthesis. In: Proceedings of the ICASSP, pp. 285\u2013288 (1998)","DOI":"10.1109\/ICASSP.1998.674423"},{"issue":"4","key":"13_CR7","doi-asserted-by":"crossref","first-page":"2963","DOI":"10.1121\/1.4969157","volume":"140","author":"H Koike","year":"2016","unstructured":"Koike, H., Nose, T., Shinozaki, T., Ito, A.: Improvement of quality of voice conversion based on spectral differential filter using straight-based mel-cepstral coefficients. J. Acoust. Soc. Am. 140(4), 2963\u20132963 (2016)","journal-title":"J. Acoust. Soc. Am."},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Ling, Z.H., Wu, Y.J., Wang, Y.P., Qin, L., Wang, R.H.: USTC system for blizzard challenge 2006 an improved HMM-based speech synthesis method. In: Blizzard Challenge Workshop (2006)","DOI":"10.21437\/Blizzard.2006-6"},{"issue":"7","key":"13_CR9","doi-asserted-by":"crossref","first-page":"1877","DOI":"10.1587\/transinf.2015EDP7457","volume":"99","author":"M Morise","year":"2016","unstructured":"Morise, M., Yokomori, F., Ozawa, K.: World: a vocoder-based high-quality speech synthesis system for real-time applications. IEICE Trans. Inf. Syst. 99(7), 1877\u20131884 (2016)","journal-title":"IEICE Trans. Inf. Syst."},{"issue":"9","key":"13_CR10","doi-asserted-by":"crossref","first-page":"2483","DOI":"10.1587\/transinf.E93.D.2483","volume":"E93\u2013D","author":"T Nose","year":"2010","unstructured":"Nose, T., Ota, Y., Kobayashi, T.: HMM-based voice conversion using quantized F0 context. IEICE Trans. Inf. Syst. E93\u2013D(9), 2483\u20132490 (2010)","journal-title":"IEICE Trans. Inf. Syst."},{"issue":"10","key":"13_CR11","doi-asserted-by":"crossref","first-page":"1694","DOI":"10.1109\/TASLP.2016.2580298","volume":"24","author":"T Nose","year":"2016","unstructured":"Nose, T.: Efficient implementation of global variance compensation for parametric speech synthesis. IEEE\/ACM Trans. Audio Speech Lang. Process. 24(10), 1694\u20131704 (2016)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Pilkington, N.C., Zen, H., Gales, M.J., et al.: Gaussian process experts for voice conversion. In: Proceedings of the INTERSPEECH, pp. 2772\u20132775 (2011)","DOI":"10.21437\/Interspeech.2011-691"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Saito, Y., Takamichi, S., Saruwatari, H.: Training algorithm to deceive anti-spoofing verification for DNN-based speech synthesis. In: Proceedings of the ICASSP","DOI":"10.1109\/ICASSP.2017.7953088"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Stylianou, Y.: Voice transformation: a survey. In: Proceedings of the ICASSP, pp. 3585\u20133588 (2009)","DOI":"10.1109\/ICASSP.2009.4960401"},{"issue":"5","key":"13_CR15","first-page":"816","volume":"90","author":"T Tomoki","year":"2007","unstructured":"Tomoki, T., Tokuda, K.: A speech parameter generation algorithm considering global variance for HMM-based speech synthesis. IEICE Trans. Inf. Syst. 90(5), 816\u2013824 (2007)","journal-title":"IEICE Trans. Inf. Syst."}],"container-title":["Smart Innovation, Systems and Technologies","Advances in Intelligent Information Hiding and Multimedia Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-63859-1_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T14:55:57Z","timestamp":1719327357000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-63859-1_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7,18]]},"ISBN":["9783319638584","9783319638591"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-63859-1_13","relation":{},"ISSN":["2190-3018","2190-3026"],"issn-type":[{"type":"print","value":"2190-3018"},{"type":"electronic","value":"2190-3026"}],"subject":[],"published":{"date-parts":[[2017,7,18]]}}}