no code implementations • 26 Jan 2016 • Prasanna Kumar Muthukumar, Alan W. black
In the last two years, there have been numerous papers that have looked into using Deep Neural Networks to replace the acoustic model in traditional statistical parametric speech synthesis.
no code implementations • 30 Sep 2014 • Prasanna Kumar Muthukumar, Alan W. black
Mel Cepstral coefficients were never intended to work in a parametric speech synthesis framework, but as yet, there has been little success in creating a better parameterization that is more suited to synthesis.