{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T23:42:48Z","timestamp":1687304568123},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2012,3,8]],"date-time":"2012-03-08T00:00:00Z","timestamp":1331164800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2012,6]]},"DOI":"10.1007\/s10772-012-9135-7","type":"journal-article","created":{"date-parts":[[2012,3,7]],"date-time":"2012-03-07T15:37:50Z","timestamp":1331134670000},"page":"215-225","source":"Crossref","is-referenced-by-count":0,"title":["A HMM-WDLT framework for HNM-based voice conversion with parametric adjustment in formant bandwidth, duration and excitation"],"prefix":"10.1007","volume":"15","author":[{"given":"Hwai-Tsu","family":"Hu","sequence":"first","affiliation":[]},{"given":"Chu","family":"Yu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2012,3,8]]},"reference":[{"key":"9135_CR1","first-page":"655","volume-title":"Proc. ICASSP","author":"M. Abe","year":"1988","unstructured":"Abe, M., Nakamura, S., Shikano, K., & Kuwabara, H. (1988). Voice conversion through vector quantization. In Proc. ICASSP (pp.\u00a0655\u2013658)."},{"key":"9135_CR2","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1016\/S0167-6393(99)00015-1","volume":"28","author":"L. M. Arslan","year":"1999","unstructured":"Arslan, L. M. (1999). Speaker transformation algorithm using segmental. codebooks (STASC). Speech Communication, 28, 211\u2013226.","journal-title":"Speech Communication"},{"key":"9135_CR3","doi-asserted-by":"crossref","first-page":"2413","DOI":"10.21437\/Eurospeech.2003-664","volume-title":"Proc. EUROSPEECH","author":"Y. Chen","year":"2003","unstructured":"Chen, Y., Chu, M., Chang, E., Liu, J., & Liu, R. (2003). Voice conversion with smoothed GMM and MAP adaptation. In Proc. EUROSPEECH (pp. 2413\u20132416)."},{"issue":"5","key":"9135_CR4","doi-asserted-by":"crossref","first-page":"380","DOI":"10.1109\/TASSP.1976.1162849","volume":"24","author":"A. H. Gray Jr.","year":"1976","unstructured":"Gray, A. H., Jr., & Markel, J. D. (1976). Distance measures for speech processing. IEEE Transactions on Acoustics, Speech, and Signal Processing, 24(5), 380\u2013391.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"issue":"7","key":"9135_CR5","doi-asserted-by":"crossref","first-page":"1488","DOI":"10.1587\/transinf.E92.D.1488","volume":"E92-D","author":"H. T. Hu","year":"2009","unstructured":"Hu, H. T., & Yu, C. (2009). Combining HMM and weighted deviation linear transformation for highband speech parameter estimation. IEICE Transactions on Information and Systems, E92-D(7), 1488\u20131490.","journal-title":"IEICE Transactions on Information and Systems"},{"issue":"1","key":"9135_CR6","first-page":"7","volume":"17","author":"H. T. Hu","year":"2010","unstructured":"Hu, H. T., & Yu, C. (2010). Narrowband-to-wideband expansion of telephony speech using piecewise deviation linear transformation. International Journal of Electrical Engineering, 17(1), 7\u201317.","journal-title":"International Journal of Electrical Engineering"},{"key":"9135_CR7","doi-asserted-by":"crossref","first-page":"1707","DOI":"10.1016\/S0165-1684(03)00082-3","volume":"83","author":"P. Jax","year":"2003","unstructured":"Jax, P., & Vary, P. (2003). On artificial bandwidth extension of telephone speech. Signal Processing, 83, 1707\u20131719.","journal-title":"Signal Processing"},{"key":"9135_CR8","doi-asserted-by":"crossref","first-page":"2519","DOI":"10.21437\/Eurospeech.1997-654","volume-title":"Proc. EUROSPEECH","author":"E. K. Kim","year":"1997","unstructured":"Kim, E. K., Lee, S., & Oh, Y. H. (1997). Hidden Markov model based voice conversion using dynamic characteristics of speaker. In Proc. EUROSPEECH (pp. 2519\u20132522)."},{"issue":"2","key":"9135_CR9","doi-asserted-by":"crossref","first-page":"641","DOI":"10.1109\/TASL.2006.876760","volume":"15","author":"K. S. Lee","year":"2007","unstructured":"Lee, K. S. (2007). Statistical approach for voice personality transformation. IEEE Transactions on Audio, Speech, and Language Processing, 15(2), 641\u2013651.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9135_CR10","volume-title":"Advances in Chinese spoken language processing","author":"D. Li","year":"2007","unstructured":"Li, D., & Dang, J. (2007). Speech analysis: the production-perception perspective. In C. H. Lee, H. Li, L. S. Lee, R. H. Wang & Q.\u00a0Huo (Eds.), Advances in Chinese spoken language processing. Singapore: World Scientific."},{"key":"9135_CR11","first-page":"200","volume-title":"Proc. ICASSP","author":"A. McCree","year":"1996","unstructured":"McCree, A., Truong, K., George, E. B., Barnwell, T. P., & Viswanathan, V. (1996). A 2.4 kbit\/s MELP coder candidate for the new U.S. Federal Standard. In Proc. ICASSP (Vol.\u00a01, pp. 200\u2013203)."},{"issue":"2","key":"9135_CR12","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1016\/0167-6393(94)00052-C","volume":"16","author":"H. Mizuno","year":"1995","unstructured":"Mizuno, H., & Abe, M. (1995). Voice conversion algorithm based on piecewise linear conversion rules of formant frequency and spectral tilt. Speech Communication, 16(2), 153\u2013164.","journal-title":"Speech Communication"},{"issue":"2","key":"9135_CR13","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/0167-6393(94)00058-I","volume":"16","author":"M. Narendranath","year":"1995","unstructured":"Narendranath, M., Hema, A., Rajendran, S., & Yegnanarayana, B. (1995). Transformation of formants for voice conversion using artificial neural networks. Speech Communication, 16(2), 207\u2013216.","journal-title":"Speech Communication"},{"issue":"S1","key":"9135_CR14","doi-asserted-by":"crossref","first-page":"S94","DOI":"10.1121\/1.2024485","volume":"81","author":"E. P. Neuburg","year":"1987","unstructured":"Neuburg, E. P. (1987). Dynamic frequency warping, the dual of dynamic time warping. The Journal of the Acoustical Society of America, 81(S1), S94\u2013S94.","journal-title":"The Journal of the Acoustical Society of America"},{"key":"9135_CR15","volume-title":"Fundamentals of speech recognition","author":"L. Rabiner","year":"1993","unstructured":"Rabiner, L., & Juang, B. H. (1993). Fundamentals of speech recognition. New York: Prentice-Hall."},{"key":"9135_CR16","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/1051-2004(91)90099-7","volume":"4","author":"M. Savic","year":"1991","unstructured":"Savic, M., & Nam, I. H. (1991). Voice personality transformation. Digital Signal Processing, 4, 107\u2013110.","journal-title":"Digital Signal Processing"},{"key":"9135_CR17","first-page":"1.10.1","volume-title":"Proc. ICASSP","author":"F. K. Soong","year":"1984","unstructured":"Soong, F. K., & Juang, B. H. (1984). Line spectrum pair (LSP) and speech data compression. In Proc. ICASSP (pp. 1.10.1\u20131.10.4)."},{"key":"9135_CR18","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1007\/s10772-006-5692-y","volume":"8","author":"D. Rentzos","year":"2005","unstructured":"Rentzos, D., Vaseghi, S., & Yan, Q. (2005). Parametric formant modelling and transformation in voice conversion. International Journal of Speech Technology, 8, 227\u2013245.","journal-title":"International Journal of Speech Technology"},{"issue":"1","key":"9135_CR19","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/89.890068","volume":"9","author":"Y. Stylianou","year":"2001","unstructured":"Stylianou, Y. (2001a). Applying the Harmonic plus Noise model in concatenative speech synthesis. IEEE Transactions on Speech and Audio Processing, 9(1), 21\u201329.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"3","key":"9135_CR20","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1109\/89.905997","volume":"9","author":"Y. Stylianou","year":"2001","unstructured":"Stylianou, Y. (2001b). Removing linear phase mismatches in concatenative speech synthesis. IEEE Transactions on Speech and Audio Processing, 9(3), 232\u2013239.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"2","key":"9135_CR21","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1109\/89.661472","volume":"6","author":"Y. Stylianou","year":"1998","unstructured":"Stylianou, Y., Cappe, O., & Moulines, E. (1998). Continuous probabilistic transform for voice conversion. IEEE Transactions on Speech and Audio Processing, 6(2), 131\u2013142.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9135_CR22","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/0167-6393(92)90012-V","volume":"11","author":"H. Valbret","year":"1992","unstructured":"Valbret, H., Moulines, E., & Tubach, J. P. (1992). Voice transformation using PSOLA techniques. Speech Communication, 11, 175\u2013187.","journal-title":"Speech Communication"},{"key":"9135_CR23","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1109\/CISP.2008.165","volume-title":"Congress on image and signal processing","author":"Z. Yue","year":"2008","unstructured":"Yue, Z., Zou, X., Jia, Y., & Wang, H. (2008). Voice conversion using HMM combined with GMM. In Congress on image and signal processing (Vol.\u00a05, pp.\u00a0366\u2013370)."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-012-9135-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-012-9135-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-012-9135-7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T23:21:16Z","timestamp":1687303276000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-012-9135-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,3,8]]},"references-count":23,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2012,6]]}},"alternative-id":["9135"],"URL":"https:\/\/doi.org\/10.1007\/s10772-012-9135-7","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,3,8]]}}}