A comparative study on system combination schemes for LVCSR
Chengyuan Ma, Hong-Kwang Jeff Kuo, et al.
ICASSP 2010
To improve recognition performance in noisy environments, multicondition training is usually applied in which speech signals corrupted by a variety of noise are used in acoustic model training. Published hidden Markov modeling of speech uses multiple Gaussian distributions to cover the spread of the speech distribution caused by noise, which distracts the modeling of speech event itself and possibly sacrifices the performance on clean speech. In this paper, we propose a novel approach which extends the conventional Gaussian mixture hidden Markov model (GMHMM) by modeling state emission parameters (mean and variance) as a polynomial function of a continuous environment-dependent variable. At the recognition time, a set of HMMs specific to the given value of the environment variable is instantiated and used for recognition. The maximum-likelihood (ML) estimation of the polynomial functions of the proposed variable-parameter GMHMM is given within the expectation-maximization (EM) framework. Experiments on the Aurora 2 database show significant improvements of the variable-parameter Gaussian mixture HMMs compared to the conventional GMHMMs © 2007 IEEE.
Chengyuan Ma, Hong-Kwang Jeff Kuo, et al.
ICASSP 2010
Xiaodong Cui, Vaibhava Goel, et al.
INTERSPEECH 2013
Xiaodong Cui, Abeer Alwan
IEEE Transactions on Audio, Speech and Language Processing
Han Shen, Songtao Lu, et al.
AISTATS 2023