Voice conversion can be reduced to a problem to find a transformation function between the corresponding speech sequences of two speakers. Perhaps the most voice conversions meth...
We present an algorithm to estimate the parameters of a linear model in the presence of heteroscedastic noise, i.e., each data point having a different covariance matrix. The algor...
The distortion cost function used in Mosesstyle machine translation systems has two flaws. First, it does not estimate the future cost of known required moves, thus increasing sea...
Spence Green, Michel Galley, Christopher D. Mannin...
In this paper, we describe a novel speaker adaptation algorithm based on Gaussian mixture weight adaptation. A small number of latent speaker vectors are estimated with non-negati...
— We consider nonlinear detection in rank-deficient multiple-antenna assisted beamforming systems. By exploiting the inherent symmetry of the underlying optimal Bayesian detecti...