Results 1 
4 of
4
Discriminative classifiers with adaptive kernels for noise robust speech recognition
 Comput. Speech Lang
, 2010
"... Discriminative classifiers are a popular approach to solving classification problems. However one of the problems with these approaches, in particular kernel based classifiers such as Support Vector Machines (SVMs), is that they are hard to adapt to mismatches between the training and test data. Thi ..."
Abstract

Cited by 23 (18 self)
 Add to MetaCart
Discriminative classifiers are a popular approach to solving classification problems. However one of the problems with these approaches, in particular kernel based classifiers such as Support Vector Machines (SVMs), is that they are hard to adapt to mismatches between the training and test data. This paper describes a scheme for overcoming this problem for speech recognition in noise by adapting the kernel rather than the SVM decision boundary. Generative kernels, defined using generative models, are one type of kernel that allows SVMs to handle sequence data. By compensating the parameters of the generative models for each noise condition noisespecific generative kernels can be obtained. These can be used to train a noiseindependent SVM on a range of noise conditions, which can then be used with a testset noise kernel for classification. The noisespecific kernels used in this paper are based on Vector Taylor Series (VTS) modelbased compensation. VTS allows all the model parameters to be compensated and the background noise to be estimated in a maximum likelihood fashion. A brief discussion of VTS, and the optimisation of the mismatch function representing the impact of noise on the clean speech, is also included. Experiments using these VTSbased testset noise kernels were run on the AURORA 2 continuous digit task. The proposed SVM rescoring scheme yields large gains in performance over the VTS compensated models. Key words: speech recognition, noise robustness, support vector machines, generative kernels
Discriminative Classifiers with Generative Kernels for Noise Robust ASR
"... Discriminative classifiers are a popular approach to solving classification problems. However one of the problems with these approaches, in particular kernel based classifiers such as Support Vector Machines (SVMs), is that they are hard to adapt to mismatches between the training and test data. Thi ..."
Abstract

Cited by 5 (5 self)
 Add to MetaCart
Discriminative classifiers are a popular approach to solving classification problems. However one of the problems with these approaches, in particular kernel based classifiers such as Support Vector Machines (SVMs), is that they are hard to adapt to mismatches between the training and test data. This paper describes a scheme for overcoming this problem for speech recognition in noise. Generative kernels, defined using generative models, allow SVMs to handle sequence data. By compensating the generative models for the noise conditions noisespecific generative kernels can be obtained. These can be used to train a noiseindependent SVM on a range of noise conditions, which can then be used with a testset noise kernel for classification. Initial experiments using an idealised version of modelbased compensation were run on the AURORA 2.0 continuous digit task. The proposed scheme yielded large gains in performance over the compensated models.
Importance Sampling to Compute Likelihoods of NoiseCorrupted Speech ✩
"... One way of making speech recognisers more robust to noise is model compensation. Rather than enhancing the incoming observations, model compensation techniques modify a recogniser’s stateconditional distributions so they model the speech in the target environment. Because the interaction between sp ..."
Abstract
 Add to MetaCart
One way of making speech recognisers more robust to noise is model compensation. Rather than enhancing the incoming observations, model compensation techniques modify a recogniser’s stateconditional distributions so they model the speech in the target environment. Because the interaction between speech and noise is nonlinear, even for Gaussian speech and noise the corrupted speech distribution has no closed form. Thus, model compensation methods approximate it with a parametric distribution, such as a Gaussian or a mixture of Gaussians. The impact of this approximation has never been quantified. This paper therefore introduces a nonparametric method to compute the likelihood of a corrupted speech observation. It uses sampling and, given speech and noise distributions and a mismatch function, is exact in the limit. It therefore gives a theoretical bound for model compensation. Though computing the likelihood is computationally expensive, the novel method enables a performance comparison based on the criterion that model compensation methods aim to minimise: the KL divergence to the ideal compensation. It gives the point where the KullbackLeibler (KL) divergence is zero. This paper examines the performance of various compensation methods, such as vector Taylor series (VTS) and datadriven parallel model combination (DPMC). It shows that more accurate modelling than GaussianforGaussian compensation improves the performance of speech recognition.
A Variational Perspective on NoiseRobust Speech Recognition
"... Abstract—Model compensation methods for noiserobust speech recognition have shown good performance. Predictive linear transformations can approximate these methods to balance computational complexity and compensation accuracy. This paper examines both of these approaches from a variational perspect ..."
Abstract
 Add to MetaCart
Abstract—Model compensation methods for noiserobust speech recognition have shown good performance. Predictive linear transformations can approximate these methods to balance computational complexity and compensation accuracy. This paper examines both of these approaches from a variational perspective. Using a matchedpair approximation at the component level yields a number of standard forms of model compensation and predictive linear transformations. However, a tighter bound can be obtained by using variational approximations at the state level. Both modelbased and predictive linear transform schemes can be implemented in this framework. Preliminary results show that the tighter bound obtained from the statelevel variational approach can yield improved performance over standard schemes. θt−1 kt−1 xt−1 yt−1 nt−1 θt kt xt yt nt θt−1 mt−1 yt−1 θt mt yt I.