{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T00:41:20Z","timestamp":1780533680156,"version":"3.54.1"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2017,9,18]],"date-time":"2017-09-18T00:00:00Z","timestamp":1505692800000},"content-version":"unspecified","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":[[2018,5]]},"DOI":"10.1007\/s00034-017-0659-6","type":"journal-article","created":{"date-parts":[[2017,9,18]],"date-time":"2017-09-18T10:30:52Z","timestamp":1505730652000},"page":"2142-2163","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["A Multilingual to Polyglot Speech Synthesizer for Indian Languages Using a Voice-Converted Polyglot Speech Corpus"],"prefix":"10.1007","volume":"37","author":[{"given":"P.","family":"Vijayalakshmi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"B.","family":"Ramani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"M. P. Actlin","family":"Jeeva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"T.","family":"Nagarajan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2017,9,18]]},"reference":[{"key":"659_CR1","unstructured":"L. Badino, C. Barolo, S. Quazza, Language independent phoneme mapping for foreign TTS, in ISCA Workshop on Speech Synthesis, pp. 217\u2013218 (2004)"},{"key":"659_CR2","doi-asserted-by":"crossref","unstructured":"A.W. Black, K.A. Lenzo, Multilingual text-to-speech synthesis, in International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. III-761\u2013III-764 (2004)","DOI":"10.1109\/ICASSP.2004.1326656"},{"key":"659_CR3","unstructured":"N. Campbell, Foreign language speech synthesis, in The Third ESCA\/COCOSDA Workshop on Speech, Synthesis, pp. 177\u2013180 (1998)"},{"key":"659_CR4","doi-asserted-by":"crossref","unstructured":"N. Campbell, Talking foreign\u2014concatenative speech synthesis and the language barrier, in EUROSPEECH, pp. 337\u2013340 (2001)","DOI":"10.21437\/Eurospeech.2001-105"},{"issue":"10","key":"659_CR5","doi-asserted-by":"crossref","first-page":"1558","DOI":"10.1109\/TASLP.2014.2339738","volume":"22","author":"CP Chen","year":"2014","unstructured":"C.P. Chen, Y.C. Huang, C.H. Wu, K.D. Lee, Polyglot speech synthesis based on cross-lingual frame selection using auditory and articulatory features. IEEE\/ ACM Trans. Audio Speech Lang. Process. 22(10), 1558\u20131570 (2014)","journal-title":"IEEE\/ ACM Trans. Audio Speech Lang. Process."},{"key":"659_CR6","first-page":"373","volume":"1","author":"AJ Hunt","year":"1996","unstructured":"A.J. Hunt, A.W. Black, Unit selection in a concatenative speech synthesis system using a large speech database. Int. Conf. Acoust. Speech Signal Process. (ICASSP) 1, 373\u2013376 (1996)","journal-title":"Int. Conf. Acoust. Speech Signal Process. (ICASSP)"},{"issue":"10","key":"659_CR7","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":"659_CR8","unstructured":"A.F. Machado, M. Quieroz, Voice conversion: a critical survey, in Sound and Music Computing, pp. 291\u2013298 (2010)"},{"key":"659_CR9","doi-asserted-by":"crossref","unstructured":"M. Mashimo, T. Toda, K. Shikano, N. Campbell, Evaluation of cross-language voice conversion based on GMM and STRAIGHT, in EUROSPEECH, pp. 361\u2013364 (2001)","DOI":"10.21437\/Eurospeech.2001-111"},{"key":"659_CR10","doi-asserted-by":"crossref","unstructured":"M. Moberg, K. Parssinen, J. Iso-Sipila, Cross-lingual phoneme mapping for multilingual synthesis systems, in INTERSPEECH, pp. 1029\u20131032 (2004)","DOI":"10.21437\/Interspeech.2004-364"},{"key":"659_CR11","unstructured":"B. Mobius, J. Schroeter, J. Van Santen, R. Sproat, J. Olive, Recent advances in multilingual text-to-speech synthesis, in Fortschritte der Akustik - DAGA 96 (DEGA, Oldenburg, 1996), pp. 82\u201385"},{"issue":"6","key":"659_CR12","doi-asserted-by":"crossref","first-page":"1231","DOI":"10.1109\/TASL.2009.2015708","volume":"17","author":"Y Qian","year":"2009","unstructured":"Y. Qian, H. Liang, F.K. Soong, A Cross-language state sharing and mapping approach to bilingual (Mandarin\u2013English) TTS. IEEE Trans. Audio Speech Lang. Process. 17(6), 1231\u20131239 (2009)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"659_CR13","unstructured":"B. Ramani, S. Lilly Christina, G. Anushiya Rachel, V. Sherlin 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, pp. 291\u2013296 (2013)"},{"key":"659_CR14","doi-asserted-by":"crossref","unstructured":"B. Ramani, V. Sherlin Solomi, G. Anushiya Rachel, S. Lilly Christina, P. Vijayalakshmi, T. Nagarajan, H.A. Murthy, Development and evaluation of unit selection and HMM-based speech synthesis systems for Tamil, in National Conference on Communications (NCC), pp. 1\u20135 (2013)","DOI":"10.1109\/NCC.2013.6487984"},{"issue":"4","key":"659_CR15","doi-asserted-by":"crossref","first-page":"1283","DOI":"10.1007\/s00034-015-0118-1","volume":"35","author":"B Ramani","year":"2016","unstructured":"B. Ramani, M.P. Actlin Jeeva, P. Vijayalakshmi, T. Nagarajan, A multi-level GMM-based cross-lingual voice conversion using language specific mixture weights for polyglot synthesis. Circuits Syst. Signal Process. 35(4), 1283\u20131311 (2016)","journal-title":"Circuits Syst. Signal Process."},{"issue":"4","key":"659_CR16","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1080\/02564602.2016.1192963","volume":"34","author":"B Sharma","year":"2017","unstructured":"B. Sharma, S.R.M. Prasanna, Polyglot speech synthesis: a review. IETE Tech. Rev. 34(4), 366\u2013389 (2017)","journal-title":"IETE Tech. Rev."},{"key":"659_CR17","doi-asserted-by":"crossref","unstructured":"V. Sherlin Solomi, S. Lilly Christina, G. Anushiya 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 International Conference Oriental COCOSDA, pp. 1\u20135 (2013)","DOI":"10.1109\/ICSDA.2013.6709898"},{"key":"659_CR18","doi-asserted-by":"crossref","unstructured":"V. Sherlin Solomi, M.S. Saranya, G. Anushiya Rachel, P. Vijayalakshmi, T. Nagarajan, Performance comparison of KLD and PoG metrics for finding the acoustic similarity between phonemes for the development of a polyglot synthesizer, in IEEE TENCON, pp. 1\u20134 (2014)","DOI":"10.1109\/TENCON.2014.7022438"},{"key":"659_CR19","doi-asserted-by":"crossref","unstructured":"Y. Stylianou, O. Cappe, E. Moulines, Statistical methods for voice quality transformation, in EUROSPEECH, pp. 447\u2013450 (1995)","DOI":"10.21437\/Eurospeech.1995-121"},{"key":"659_CR20","first-page":"I81","volume":"1","author":"D Sundermann","year":"2006","unstructured":"D. Sundermann, H. Hoge, A. Bonafonte, H. Ney, A. Black, S. Narayanan, Text-independent voice conversion based on unit selection. Int. Conf. Acoust. Speech Signal Process. (ICASSP) 1, I81\u2013I84 (2006)","journal-title":"Int. Conf. Acoust. Speech Signal Process. (ICASSP)"},{"key":"659_CR21","doi-asserted-by":"crossref","unstructured":"Y. Tabet, M. Boughazi, Speech synthesis techniques\u2014a survey, in 7th International Workshop on Systems, Signal Processing and Their Applications (WOSSPA), pp. 67\u201370 (2011)","DOI":"10.1109\/WOSSPA.2011.5931414"},{"key":"659_CR22","unstructured":"Technology Development for Indian Languages Programme, DeitY, http:\/\/tdil.mit.gov.in\/AboutUs.aspx (2016). Accessed on 30 June 2017"},{"key":"659_CR23","first-page":"841","volume":"2","author":"T Toda","year":"2001","unstructured":"T. Toda, H. Saruwatari, K. Shikano, Voice conversion algorithm based on Gaussian mixture model with dynamic frequency warping of STRAIGHT spectrum. Int. Conf. Acoust. Speech Signal Process. (ICASSP) 2, 841\u2013844 (2001)","journal-title":"Int. Conf. Acoust. Speech Signal Process. (ICASSP)"},{"issue":"8","key":"659_CR24","doi-asserted-by":"crossref","first-page":"2222","DOI":"10.1109\/TASL.2007.907344","volume":"15","author":"T Toda","year":"2007","unstructured":"T. Toda, A.W. Black, K. Tokuda, Voice conversion based on maximum-likelihood estimation of spectral parameter trajectory. IEEE Trans. Audio Speech Lang. Process. 15(8), 2222\u20132235 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"659_CR25","doi-asserted-by":"crossref","unstructured":"C. Traber, K. Huber, K. Nedir, B. Pfister, E. Keller, B. Zellner, From multilingual to polyglot speech synthesis, in EUROSPEECH, pp. 835\u2013838 (1999)","DOI":"10.21437\/Eurospeech.1999-203"},{"key":"659_CR26","first-page":"145","volume":"1","author":"H Valbret","year":"1992","unstructured":"H. Valbret, E. Moulines, J.P. Tubach, Voice transformation using PSOLA technique. Int. Conf. Acoust. Speech Signal Process. (ICASSP) 1, 145\u2013148 (1992)","journal-title":"Int. Conf. Acoust. Speech Signal Process. (ICASSP)"},{"key":"659_CR27","volume-title":"The HTK Book (for HTK Version 3.4)","author":"S Young","year":"2002","unstructured":"S. Young, G. Evermann, M. Gales, T. Hain, D. Kershaw, X. Liu, G. Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev, P. Woodland, The HTK Book (for HTK Version 3.4) (Cambridge University Engineering Department, Cambridge, 2002)"},{"issue":"11","key":"659_CR28","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(11), 1039\u20131064 (2009)","journal-title":"Speech Commun."},{"key":"659_CR29","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), pp. 4605\u20134608 (2008)","DOI":"10.1109\/ICASSP.2008.4518682"}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00034-017-0659-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-017-0659-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-017-0659-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T19:50:11Z","timestamp":1750881011000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00034-017-0659-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,9,18]]},"references-count":29,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2018,5]]}},"alternative-id":["659"],"URL":"https:\/\/doi.org\/10.1007\/s00034-017-0659-6","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"value":"0278-081X","type":"print"},{"value":"1531-5878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,9,18]]}}}