Initial background references

• Kang, S., Qian, X., & Meng, H. (2013). Multi-distribution deep belief network for speech synthesis. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8012–8016. 
• Senior, A. W., Chun, B., & Schuster, M. (2013). Speech synthesis using deep neural networks. U.S. Patent No. 8,527,276. Washington, DC: U.S. Patent and Trademark Office.
• Hinton, G., Deng, L., Yu, D., Dahl, G. E., Mohamed, A., Jaitly, N., … Senior, A. (2012). Deep Neural Networks for Acoustic Modeling in Speech Recognition. IEEE Signal Processing Magazine, (November), 1–27.
• Jaitly, N., & Hinton, G. (2011). Learning a better representation of speech soundwaves using restricted Boltzmann machines. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (Vol. 1, pp. 5884–5887). 
• Deng, L., Seltzer, M. L., Yu, D., Acero, A., Mohamed, A. R., & Hinton, G. E. (2010, September). Binary coding of speech spectrograms using a deep auto-encoder. In INTERSPEECH (pp. 1692-1695)