TY - JOUR AU - Stylianou, O. Y. C. AU - Moulines, E. PY - 1998 DA - 1998// TI - Continuous probabilistic transform for voice conversion JO - IEEE Trans. Speech Audio Proc. VL - 6 UR - https://doi.org/10.1109/89.661472 DO - 10.1109/89.661472 ID - Stylianou1998 ER - TY - CHAP AU - Kain, A. AU - Macon, M. PY - 1998 DA - 1998// TI - Spectral voice conversion for text-to-speech synthesis BT - Proc. ICASSP PB - IEEE CY - Seattle, Washington, USA ID - Kain1998 ER - TY - CHAP AU - Toda, T. AU - Black, A. W. AU - Tokuda, K. PY - 2005 DA - 2005// TI - Spectral conversion based on maximum likelihood estimation considering global variance of converted parameter BT - Proc. ICASSP PB - IEEE CY - Philadelphia, Pennsylvania, USA ID - Toda2005 ER - TY - CHAP AU - Toda, T. AU - Saruwatari, H. AU - Shikano, K. PY - 2001 DA - 2001// TI - Voice conversion algorithm based on Gaussian mixture model with dynamic frequency warping of STRAIGHT spectrum BT - Proc. ICASSP PB - IEEE CY - Orlando, Florida, USA ID - Toda2001 ER - TY - CHAP AU - Kain, A. AU - Macon, M. W. PY - 2001 DA - 2001// TI - Design and evaluation of a voice conversion algorithm based on spectral envelope mapping and residual prediction BT - Proc. ICASSP PB - IEEE CY - Salt Lake City, Utah, USA ID - Kain2001 ER - TY - STD TI - T En-Najjary, O Rosec, T Chonavel, in Proc. Interspeech ICSLP. A voice conversion method based on joint pitch and spectral envelope transformation (Jeju Island, Korea, 2004), pp. 1225–1225. ID - ref6 ER - TY - JOUR AU - Toda, T. AU - Black, A. W. AU - Tokuda, K. PY - 2007 DA - 2007// TI - Voice conversion based on maximum-likelihood estimation of spectral parameter trajectory JO - IEEE Trans. Audio Speech Lang. Proc. VL - 15 UR - https://doi.org/10.1109/TASL.2007.907344 DO - 10.1109/TASL.2007.907344 ID - Toda2007 ER - TY - CHAP AU - Benisty, H. AU - Malah, D. PY - 2011 DA - 2011// TI - Voice conversion using GMM with enhanced global variance BT - Proc. Interspeech PB - ISCA CY - Florence, Italy ID - Benisty2011 ER - TY - CHAP AU - Toda, T. AU - Muramatsu, T. AU - Banno, H. PY - 2012 DA - 2012// TI - Implementation of computationally efficient real-time voice conversion BT - INTERSPEECH PB - ISCA CY - Portland, Oregon, U.S ID - Toda2012 ER - TY - STD TI - T Muramatsu, Y Ohtani, T Toda, H Saruwatari, K Shikano, in Interspeech. Low-delay voice conversion based on maximum likelihood estimation of spectral parameter trajectory (ISCA, 2008), pp. 1076–1079. ID - ref10 ER - TY - STD TI - Y Nankaku, K Nakamura, T Toda, K Tokuda, in Proc. Interspeech. Spectral conversion based on statistical models including time-sequence matching (ISCA, 2007), pp. 333–338. ID - ref11 ER - TY - JOUR AU - Erro, D. AU - Moreno, A. AU - Bonafonte, A. PY - 2010 DA - 2010// TI - Inca algorithm for training voice conversion systems from nonparallel corpora JO - Audio Speech Lang. Process. IEEE Trans. VL - 18 UR - https://doi.org/10.1109/TASL.2009.2038669 DO - 10.1109/TASL.2009.2038669 ID - Erro2010 ER - TY - CHAP AU - Benisty, H. AU - Malah, D. AU - Crammer, K. PY - 2014 DA - 2014// TI - Non-parallel voice conversion using joint optimization of alignment by temporal context and spectral distortion BT - Proc. ICASSP PB - IEEE CY - Florence, Italy ID - Benisty2014 ER - TY - JOUR AU - Erro, D. AU - Moreno, A. AU - Bonafonte, A. PY - 2010 DA - 2010// TI - Voice conversion based on weighted frequency warping JO - IEEE Trans. Audio Speech Lang. Proc. VL - 18 UR - https://doi.org/10.1109/TASL.2009.2038663 DO - 10.1109/TASL.2009.2038663 ID - Erro2010 ER - TY - CHAP AU - Helander, E. AU - Schwarz, J. AU - Nurminen, S. H. J. AU - Gabbouj, M. PY - 2008 DA - 2008// TI - On the impact of alignment on voice conversion performance BT - Proc. Interspeech PB - ISCA CY - Brisbane, Australia ID - Helander2008 ER - TY - STD TI - T Toda, Y Ohtani, K Shikano, in Proc. ICSLP. Eigenvoice conversion based on Gaussian mixture model, (2006), pp. 2446–2449. ID - ref16 ER - TY - JOUR AU - Xu, N. AU - Yang, Z. AU - Zhang, L. AU - Zhu, W. AU - Bao, J. PY - 2009 DA - 2009// TI - Voice conversion based on state-space model for modelling spectral trajectory JO - Electron. Lett. VL - 45 UR - https://doi.org/10.1049/el.2009.0904 DO - 10.1049/el.2009.0904 ID - Xu2009 ER - TY - JOUR AU - Wu, Z. AU - Virtanen, T. AU - Chng, E. S. AU - Li, H. PY - 2014 DA - 2014// TI - Exemplar-based sparse representation with residual compensation for voice conversion JO - Audio Speech Lang. Process. IEEE/ACM Trans. VL - 22 UR - https://doi.org/10.1109/TASLP.2014.2333242 DO - 10.1109/TASLP.2014.2333242 ID - Wu2014 ER - TY - JOUR AU - Arulampalam, M. S. AU - Maskell, S. AU - Gordon, N. AU - Clapp, T. PY - 2002 DA - 2002// TI - A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking JO - IEEE Trans. Signal Proc. VL - 50 UR - https://doi.org/10.1109/78.978374 DO - 10.1109/78.978374 ID - Arulampalam2002 ER - TY - STD TI - H Benisty, D Malah, K Crammer, in Electrical & Electronics Engineers in Israel (IEEEI), 2014 IEEE 28th Convention Of. Sequential voice conversion using grid-based approximation (IEEE, 2014), pp. 1–5. ID - ref20 ER - TY - STD TI - H Benisty, D Malah, K Crammer, in Proc. EUSIPCO. Modular global variance enhancement for voice conversion systems, (2012), pp. 370–374. ID - ref21 ER - TY - BOOK AU - Anderson, B. AU - Moore, J. PY - 1979 DA - 1979// TI - Optimal Filtering PB - Prentice-Hall CY - Englewood Cliffs, NJ ID - Anderson1979 ER - TY - JOUR AU - Dempster, A. AU - Laird, N. AU - Rubin, D. PY - 1977 DA - 1977// TI - Maximum likelihood from incomplete data via the EM algorithm JO - J. R. Stat. Soc. B VL - 39 ID - Dempster1977 ER - TY - STD TI - J Kominek, AW Black, CMU ARCTIC Databases for Speech Synthesis, (2003). ID - ref24 ER - TY - STD TI - Aholab Coder. http://aholab.ehu.es/ahocoder/. Accessed Jan 2013. UR - http://aholab.ehu.es/ahocoder/ ID - ref25 ER - TY - STD TI - D Erro, I Sainz, I Hernaez, in Proc. Interspeech. Improved HNM-based vocoder for statistical synthesizers, (2011), pp. 1809–1812. ID - ref26 ER - TY - JOUR AU - Cappe, O. AU - Moulines, E. PY - 1996 DA - 1996// TI - Regularization techniques for discrete cepstrum estimation JO - IEEE Signal Process. Lett. VL - 3 UR - https://doi.org/10.1109/97.489060 DO - 10.1109/97.489060 ID - Cappe1996 ER - TY - JOUR AU - Kuwabara, H. AU - Sagisaka, Y. PY - 1995 DA - 1995// TI - Acoustic characteristics of speaker individuality: control and conversion JO - IEEE Trans. Signal Proc. VL - 16 ID - Kuwabara1995 ER - TY - JOUR AU - Erro, D. AU - Moreno, A. AU - Bonafonte, A. PY - 2010 DA - 2010// TI - Inca algorithm for training voice conversion systems from nonparallel corpora JO - IEEE Trans. Audio Speech Lang. Proc. VL - 18 UR - https://doi.org/10.1109/TASL.2009.2038669 DO - 10.1109/TASL.2009.2038669 ID - Erro2010 ER - TY - JOUR AU - Ye, H. AU - Young, S. PY - 2006 DA - 2006// TI - Quality-enhanced voice morphing using maximum likelihood transformations JO - IEEE Trans. Audio Apeech Lang. Proc. VL - 14 UR - https://doi.org/10.1109/TSA.2005.860839 DO - 10.1109/TSA.2005.860839 ID - Ye2006 ER - TY - STD TI - Sound Samples. http://sipl.technion.ac.il/Info/hadas/sound-samples.htm Accessed Mar 2015. UR - http://sipl.technion.ac.il/Info/hadas/sound-samples.htm ID - ref31 ER - TY - STD TI - Multi stimulus test with hidden reference and anchors (MUSHRA) (2003). Technical Report ITU-R BS.1534-1, International Telecommunications Union. ID - ref32 ER - TY - JOUR AU - Godoy, E. AU - Rosec, O. AU - Chonavel, T. PY - 2012 DA - 2012// TI - Voice conversion using dynamic frequency warping with amplitude scaling, for parallel or nonparallel corpora JO - IEEE Trans. Audio Speech Lang. Proc. VL - 20 UR - https://doi.org/10.1109/TASL.2011.2177820 DO - 10.1109/TASL.2011.2177820 ID - Godoy2012 ER -