This paper describes, and evaluates on a large scale, the lattice based framework for discriminative training of large vocabulary speech recognition systems based on Gaussian mixture hidden Markov models (HMMs). The paper concentrates on the maximum mutual information estimation (MMIE) criterion which has been used to train HMM systems for conversational telephone speech transcription using up to 265 hours of training data. These experiments represent the largest-scale application of discriminative training techniques for speech recognition of which the authors are aware, and have led to significant reductions in word error rate for both triphone and quinphone HMMs compared to our best models trained using maximum likelihood estimation. The MMIE latticebased implementation used; techniques for ensuring improved generalisation; and interactions with maximum likelihood based adaptation are all discussed. Furthermore several variations to the MMIE training scheme are introduced with the a...

When labelled training data is plentiful, discriminative techniques are widely used since they give excellent generalization performance. However, for large-scale applications such as object recognition, hand labelling of data is expensive, and there is much interest in semi-supervised techniques based on generative models in which the majority of the training data is unlabelled. Although the generalization performance of generative models can often be improved by ‘training them discriminatively’, they can then no longer make use of unlabelled data. In an attempt to gain the benefit of both generative and discriminative approaches, heuristic procedure have been proposed [2, 3] which interpolate between these two extremes by taking a convex combination of the generative and discriminative objective functions. In this paper we adopt a new perspective which says that there is only one correct way to train a given model, and that a ‘discriminatively trained ’ generative model is fundamentally a new model [7]. From this viewpoint, generative and discriminative models correspond to specific choices for the prior over parameters. As well as giving a principled interpretation of ‘discriminative training’, this approach opens door to very general ways of interpolating between generative and discriminative extremes through alternative choices of prior. We illustrate this framework using both synthetic data and a practical example in the domain of multi-class object recognition. Our results show that, when the supply of labelled training data is limited, the optimum performance corresponds to a balance between the purely generative and the purely discriminative. 1.

This paper describes the application of a discriminative HMM parameter estimation technique called Frame Discrimination (FD), to medium and large vocabulary continuous speech recognition. Previous work has shown that FD training can give better results than maximum mutual information (MMI) training for small tasks. The use of FD for much larger tasks required the development of a technique to be able to rapidly find the most likely set of Gaussians for each frame in the system. Experiments on the Resource Management and North American Business tasks show that FD training can give comparable improvements to MMI, but is less computationally intensive. 1. INTRODUCTION Previous research has shown that the accuracy of a speech recognition system trained using Maximum Likelihood Estimation (MLE) can often be improved further using discriminative training. All such techniques normally give much greater improvements in recognition accuracy on the training data than on the test set except wh...

Abstract—Acoustic modeling based on hidden Markov models (HMMs) is employed by state-of-the-art stochastic speech recognition systems. Although HMMs are a natural choice to warp the time axis and model the temporal phenomena in the speech signal, their conditional independence properties limit their ability to model spectral phenomena well. In this paper, a new acoustic modeling paradigm based on augmented conditional random fields (ACRFs) is investigated and developed. This paradigm addresses some limitations of HMMs while maintaining many of the aspects which have made them successful. In particular, the acoustic modeling problem is reformulated in a data driven, sparse, augmented space to increase discrimination. Acoustic context modeling is explicitly integrated to handle the sequential phenomena of the speech signal. We present an efficient framework for estimating these models that ensures scalability and generality. In the TIMIT

Currently the most popular acoustic model for speech recognition is the hidden Markov model (HMM). However, HMMs are based on a series of assumptions some of which are known to be poor. In particular, the assumption that successive speech frames are conditionally independent given the discrete state that generated them is not a good assumption for speech recognition. State space models may be used to address some shortcomings of this assumption. State space models are based on a continuous state vector evolving through time according to a state evo-

Maximum Likelihood Linear Regression (MLLR) has become the most popular approach for adapting speakerindependent Hidden Markov Models to a specic speaker's characteristics. However, it is well known, that discriminative training objectives outperform Maximum Likelihood training approaches, especially in cases where training data is very limited, as it always is the case in adaptation tasks. Therefore, this paper explores the application of a framebased discriminative training objective for adaptation. It presents evaluations for supervised as well as for unsupervised adaption on the 1993 WSJ adaptation tests of native and non-native speakers. Relative improvements in word error rate of up to 25% could be measured compared to the MLLR adapted recognition systems. Along with unsupervised adaptation, the paper also presents the improvements achieved by the application of condence measures. They provided an average relative improvement of 10% compared to ordinary unsupervised MLLR. 1. I...

This paper investigates the use of discriminative training techniques for large vocabulary speech recogntion with training datasets up to 265 hours. Techniques for improving lattice-based Maximum Mutual Information Estimation (MMIE) training are described and compared to Frame Discrimination (FD). An objective function which is an interpolation of MMIE and standard Maximum Likelihood Estimation (MLE) is also discussed. Experimental results on both the Switchboard and North American Business News tasks show that MMIE training can yield significant performance improvements over standard MLE even for the most complex speech recognition problems with very large training sets.

Declaration This dissertation is the result of my own work and includes nothing which is the outcome of work done in collaboration, except where stated. It has not been submitted in whole or part for a degree at any other university. The length of this thesis including footnotes and appendices does not exceed 29,500 words and includes no more than 40 figures. 1 Systems which automatically transcribe carefully dictated speech are now commercially available, but their performance degrades dramatically when the speaking style of users becomes more relaxed or conversational. This dissertation focuses on techniques that aim to improve the robustness of statistical speech transcription systems to conversational speaking styles. The dissertation shows first that the performance degradation occuring as speech becomes more conversational is severe and is partially attributable to differences in the acoustic realizations of sentences. Hypothesizing that the quantifiably wider range of

This paper gives an overview of discriminative training as it pertains to the speech recognition problem. The basic theory of discriminative training will be discussed and an explanation of maximum mutual information (MMI) given. Common problems inherent to discriminative training will be explored as well as practicalities associated with implementing discriminative training for large vocabulary recognition. Alternatives to the MMI objective function such as minimum word error (MWE) and minimum phone error (MPE) will be discussed. The application of discriminative techniques for adaptation will be described. Finally, possible future avenues of research will be given. 1.

Abstract not found