121 search results - page 4 / 25 » Corrected tandem features for acoustic model training |
ICASSP
2010
IEEE
13 years 7 months ago
2010
IEEE
Class posterior distributions have recently been used quite successfully in Automatic Speech Recognition (ASR), either for frame or phone level classification or as acoustic featu...
ICASSP
2010
IEEE
13 years 7 months ago
2010
IEEE
We recently proposed a new algorithm to perform acoustic model adaptation to noisy environments called Linear Spline Interpolation (LSI). In this method, the nonlinear relationshi...
ICASSP
2011
IEEE
12 years 11 months ago
2011
IEEE
This paper presents a discriminative training (DT) approach to irrelevant variability normalization (IVN) based training of feature transforms and hidden Markov models for large v...
ICASSP
2011
IEEE
12 years 11 months ago
2011
IEEE
We describe feature space and model space discriminative training for a new class of acoustic models called Bayesian sensing hidden Markov models (BS-HMMs). In BS-HMMs, speech dat...
NOLISP
2007
Springer
14 years 1 months ago
2007
Springer
We have previously proposed a trajectory model which is based on a mixture density network (MDN) trained with target variables augmented with dynamic features together with an algo...