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...
Discriminative training has been a leading factor for improving automatic speech recognition (ASR) performance over the last decade. The traditional discriminative training, howev...
Speech can be represented as a time/frequency distribution of energy using a multi-band filter bank. A Markov random field model, which takes into account the possible time asynch...
All discrete Fourier transform (DFT) domain-based speech enhancement gain functions rely on knowledge of the noise power spectral density (PSD). Since the noise PSD is unknown in a...
Richard C. Hendriks, Jesper Jensen, Richard Heusde...
This paper presents an approach to estimating the parameters of continuous density HMMs for visual speech recognition. One of the key issues of image-based visual speech recogniti...