108 search results - page 8 / 22 » High-level approaches to confidence estimation in speech rec... |
ICASSP
2011
IEEE
12 years 11 months ago
2011
IEEE
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...
SEMCO
2007
IEEE
14 years 1 months ago
2007
IEEE
Discriminative training has been a leading factor for improving automatic speech recognition (ASR) performance over the last decade. The traditional discriminative training, howev...
ICPR
2000
IEEE
14 years 8 months ago
2000
IEEE
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...
TASLP
2008
13 years 6 months ago
2008
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...
ICIP
2000
IEEE
14 years 9 months ago
2000
IEEE
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...