{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T16:22:32Z","timestamp":1673540552077},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2015,7,10]],"date-time":"2015-07-10T00:00:00Z","timestamp":1436486400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2016,4]]},"DOI":"10.1007\/s00034-015-0118-1","type":"journal-article","created":{"date-parts":[[2015,7,9]],"date-time":"2015-07-09T08:24:25Z","timestamp":1436430265000},"page":"1283-1311","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["A Multi-level GMM-Based Cross-Lingual Voice Conversion Using Language-Specific Mixture Weights for Polyglot Synthesis"],"prefix":"10.1007","volume":"35","author":[{"given":"B.","family":"Ramani","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M. P.","family":"Actlin Jeeva","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"P.","family":"Vijayalakshmi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"T.","family":"Nagarajan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,7,10]]},"reference":[{"key":"118_CR1","doi-asserted-by":"crossref","unstructured":"M. Abe, S. Nakamura, K. Shikano, H. Kuwabara, Voice conversion through vector quantization, in International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 1 (1988), pp. 655\u2013658","DOI":"10.1109\/ICASSP.1988.196671"},{"key":"118_CR2","doi-asserted-by":"crossref","unstructured":"M. Abe, K. Shikano, H. Kuwabara, Cross-language voice conversion, in International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 1 (1990), pp. 345\u2013348","DOI":"10.1109\/ICASSP.1990.115676"},{"key":"118_CR3","unstructured":"M. Charlier, Y. Ohtani, T. Toda, A. Moinet, T. Dutoit, Cross-language voice conversion based on eigenvoices, in INTERSPEECH (2009), pp. 1635\u20131638"},{"issue":"5","key":"118_CR4","doi-asserted-by":"crossref","first-page":"922","DOI":"10.1109\/TASL.2009.2038663","volume":"18","author":"D Erro","year":"2010","unstructured":"D. Erro, A. Moreno, A. Bonafonte, Voice conversion based on weighted frequency warping. IEEE Trans. Audio Speech Lang. Process. 18(5), 922\u2013931 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"4","key":"118_CR5","doi-asserted-by":"crossref","first-page":"1313","DOI":"10.1109\/TASL.2011.2177820","volume":"20","author":"E Godoy","year":"2012","unstructured":"E. Godoy, O. Rosec, T. Chonavel, Voice conversion using dynamic frequency warping with amplitude scaling, for parallel or nonparallel corpora. IEEE Trans. Audio Speech Lang. Process. 20(4), 1313\u20131323 (2012)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"118_CR6","doi-asserted-by":"crossref","unstructured":"A.J. Hunt, A.W. Black, Unit selection in a concatenative speech synthesis system using a large speech database, in International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 1 (1996), pp. 373\u2013376","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"118_CR7","unstructured":"H.T. Hwang, Y. Tsao, H.M. Wang, Y.R. Wang, S.H. Chen, Alleviating the over-smoothing problem in GMM-based voice conversion with discriminative training, in INTERSPEECH (2013), pp. 3062\u20133066"},{"key":"118_CR8","doi-asserted-by":"crossref","unstructured":"A. Kain, M. Macon, Spectral voice conversion for text-to-speech synthesis. In International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 1 (1998), pp. 285\u2013288","DOI":"10.1109\/ICASSP.1998.674423"},{"key":"118_CR9","doi-asserted-by":"crossref","unstructured":"H. Kawahara, Speech representation and transformation using adaptive interpolation of weighted spectrum: vocoder revisited, in International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 2 (1997), pp. 1303\u20131306","DOI":"10.1109\/ICASSP.1997.596185"},{"key":"118_CR10","unstructured":"E.K. Kim, S. Lee, Y.H. Oh, Hidden Markov model based voice conversion using dynamic characteristics of speaker, in EUROSPEECH (1997), pp. 2519\u20132522"},{"issue":"10","key":"118_CR11","doi-asserted-by":"crossref","first-page":"1227","DOI":"10.1016\/j.specom.2006.05.003","volume":"48","author":"J Latorre","year":"2006","unstructured":"J. Latorre, K. Iwano, S. Furui, New approach to the polyglot speech generation by means of an HMM-based speaker adaptable synthesizer. Speech Commun. 48(10), 1227\u20131242 (2006)","journal-title":"Speech Commun."},{"key":"118_CR12","unstructured":"A.F. Machado, M. Quieroz, Voice conversion: a critical survey. In: Sound and Music Computing, pp. 291\u2013298 (2010)"},{"key":"118_CR13","unstructured":"T. Masuko, HMM-based speech synthesis and its applications. Ph.D. Dissertation, (2002)"},{"key":"118_CR14","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1109\/TASL.2006.876878","volume":"15","author":"PA Naylor","year":"2007","unstructured":"P.A. Naylor, A. Kounoudes, J. Gudnason, M. Brookes, Estimation of glottal closure instants in voiced speech using the DYPSA algorithm. IEEE Trans. Audio Speech Lang. Process. 15, 34\u201343 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"118_CR15","unstructured":"W.H. Press, S.A. Teukolsky, W.T. Vetterling, B.P. Flannery, Numerical recipes in C: the art of scientific computing (Chapter 14), 2nd edn. (Cambridge University Press, Cambridge, 1992), pp. 615\u2013619"},{"key":"118_CR16","unstructured":"B. Ramani, M.P. Actlin Jeeva, P. Vijayalakshmi, T. Nagarajan, Cross-lingual voice conversion-based polyglot speech synthesizer for Indian languages, in INTERSPEECH (2014), pp. 775\u2013779"},{"key":"118_CR17","unstructured":"B. Ramani, S.L. Christina, G.A. Rachel, V.S. Solomi, M.K. Nandwana, A. Prakash, A. Shanmugam, R. Krishnan, S. Kishore, K. Samudravijaya, P. Vijayalakshmi, T. Nagarajan, H.A. Murthy, A common attribute based unified HTS framework for speech synthesis in Indian languages, in ISCA Workshop on Speech Synthesis (2013), pp. 291\u2013296"},{"key":"118_CR18","unstructured":"A.K. Singh, A computational phonetic model for indian language scripts, in Constraints on Spelling Changes: Fifth International Workshop on Writing Systems (2006)"},{"key":"118_CR19","unstructured":"V.S. Solomi, S.L. Christina, G.A. Rachel, B. Ramani, P. Vijayalakshmi, T. Nagarajan, Analysis on acoustic similarities between tamil and english phonemes using product of likelihood-Gaussians for an HMM-based mixed-language synthesizer, in COCOSDA (2013), pp. 1\u20135"},{"key":"118_CR20","doi-asserted-by":"crossref","unstructured":"Y. Stylianou, Voice transformation: a survey, in International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (2009), pp. 3585\u20133588","DOI":"10.1109\/ICASSP.2009.4960401"},{"key":"118_CR21","unstructured":"Y. Stylianou, O. Cappe, E. Moulines, Statistical methods for voice quality transformation, in EUROSPEECH (1995), pp. 447\u2013450"},{"key":"118_CR22","doi-asserted-by":"crossref","unstructured":"D. Sundermann, H. Hoge, A. Bonafonte, H. Ney, A. Black, S. Narayanan, Text-independent voice conversion based on unit selection, in International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 1 (2006), pp. I81\u2013I84","DOI":"10.1109\/ICASSP.2006.1659962"},{"key":"118_CR23","doi-asserted-by":"crossref","unstructured":"D. Sundermann, H. Ney, H. Hoge, VTLN-based cross-language voice conversion, in IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU\u201903 (2003), pp. 676\u2013681","DOI":"10.1109\/ASRU.2003.1318521"},{"key":"118_CR24","unstructured":"Technology Development for Indian Languages Programme, DeitY (2013), http:\/\/tdil.mit.gov.in\/AboutUs.aspx . Last Accessed on 06 Sept 2014"},{"key":"118_CR25","doi-asserted-by":"crossref","unstructured":"T. Toda, H. Saruwatari, K. Shikano, Voice conversion algorithm based on Gaussian mixture model with dynamic frequency warping of straight spectrum, in International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 2 (2001), pp. 841\u2013844","DOI":"10.1109\/ICASSP.2001.941046"},{"key":"118_CR26","doi-asserted-by":"crossref","first-page":"2222","DOI":"10.1109\/TASL.2007.907344","volume":"15","author":"T Toda","year":"2007","unstructured":"T. Toda, A. Black, K. Tokuda, Voice conversion based on maximum-likelihood estimation of spectral parameter trajectory. IEEE Trans. Audio Speech Lang. Process. 15, 2222\u20132235 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"118_CR27","doi-asserted-by":"crossref","unstructured":"P.A. Torres-carrasquillo, D.A. Reynolds, J. Deller Jr, Language identification using Gaussian mixture model tokenization, in International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. I-757\u2013I-760 (2002)","DOI":"10.1109\/ICASSP.2002.5743828"},{"key":"118_CR28","doi-asserted-by":"crossref","unstructured":"H. Valbret, E. Moulines, J.P. Tubach, Voice transformation using PSOLA technique, in International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 1 (1992), pp. 145\u2013148","DOI":"10.1109\/ICASSP.1992.225951"},{"issue":"4","key":"118_CR29","first-page":"131","volume":"7","author":"P Vijayalakshmi","year":"2011","unstructured":"P. Vijayalakshmi, T. Nagarajan, P. Mahadevan, Improving speech intelligibility in cochlear implants using acoustic models. WSEAS Trans. Signal Process. 7(4), 131\u2013144 (2011)","journal-title":"WSEAS Trans. Signal Process."},{"issue":"1","key":"118_CR30","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1109\/TASL.2008.2006647","volume":"17","author":"J Yamagishi","year":"2009","unstructured":"J. Yamagishi, T. Kobayashi, Y. Nakano, K. Ogata, J. Isogai, Analysis of speaker adaptation algorithms for HMM-based speech synthesis and a constrained SMAPLR adaptation algorithm. IEEE Trans. Audio Speech Lang. Process. 17(1), 66\u201383 (2009)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"118_CR31","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1016\/j.specom.2009.04.004","volume":"51","author":"H Zen","year":"2009","unstructured":"H. Zen, K. Tokuda, A.W. Black, Statistical parametric speech synthesis. Speech Commun. 51, 1039\u20131064 (2009)","journal-title":"Speech Commun."},{"key":"118_CR32","doi-asserted-by":"crossref","unstructured":"M. Zhang, J. Tao, J. Tian, X. Wang, Text-independent voice conversion based on state mapped codebook, in International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (2008), pp. 4605\u20134608","DOI":"10.1109\/ICASSP.2008.4518682"},{"key":"118_CR33","doi-asserted-by":"crossref","unstructured":"M.A. Zissman, E. Singer, Automatic language identification of telephone speech messages using phoneme recognition and N-gram modeling, in International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 1 (1994), pp. I-305\u2013I-308","DOI":"10.1109\/ICASSP.1994.389377"}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-015-0118-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00034-015-0118-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-015-0118-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,22]],"date-time":"2019-05-22T11:01:51Z","timestamp":1558522911000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00034-015-0118-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,7,10]]},"references-count":33,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2016,4]]}},"alternative-id":["118"],"URL":"https:\/\/doi.org\/10.1007\/s00034-015-0118-1","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"value":"0278-081X","type":"print"},{"value":"1531-5878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,7,10]]}}}