In this paper, we present the Gauss-Newton method as a unified approach to optimizing non-linear noise compensation models, such as vector Taylor series (VTS), data-driven parall...
In this paper, we present a novel technique for modeling the posterior probability estimates obtained from a neural network directly in the HMM framework using the Dirichlet Mixtu...
Balakrishnan Varadarajan, Garimella S. V. S. Sivar...
We present a variational Bayesian algorithm that enhances the log spectra of noisy speech using speaker dependent priors. This algorithm extends prior work by Frey et al. where th...
The use of the PC and Internet for placing telephone calls will present new opportunities to capture vast amounts of un-transcribed speech for a particular speaker. This paper inv...
We describe an acoustic modeling approach in which all phonetic states share a common Gaussian Mixture Model structure, and the means and mixture weights vary in a subspace of the...
Daniel Povey, Lukas Burget, Mohit Agarwal, Pinar A...