2047 search results - page 114 / 410 » The limits of speech recognition |
ICASSP
2009
IEEE
14 years 3 months ago
2009
IEEE
In previous work we introduced a new missing data imputation method for ASR, dubbed sparse imputation. We showed that the method is capable of maintaining good recognition accurac...
ACSC
2004
IEEE
14 years 18 days ago
2004
IEEE
This paper reports on an experiment to determine the optimal parameters for a speech recogniser that is part of a computer aided instruction system for assisting learners of Engli...
ICASSP
2011
IEEE
13 years 18 days ago
2011
IEEE
We introduce Bayesian sensing hidden Markov models (BS-HMMs) to represent speech data based on a set of state-dependent basis vectors. By incorporating the prior density of sensin...
ICASSP
2011
IEEE
13 years 18 days 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...
ICASSP
2010
IEEE
13 years 9 months ago
2010
IEEE
Mismatch between training and test conditions deteriorates the performance of speech recognizers. This paper investigates the combination of parametric histogram equalization (pHE...