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...

This paper describes a framework for optimising the structure and parameters of a continuous density HMM-based large Z. vocabulary recognition system using the Maximum Mutual Information Estimation MMIE criterion. To reduce the computational complexity of the MMIE training algorithm, confusable segments of speech are identified and stored as word lattices of alternative utterance hypotheses. An iterative mixture splitting procedure is also employed to adjust the number of mixture components in each state during training such that the optimal balance between the number of parameters and the available training data is achieved. Experiments are presented on various test sets from the Wall Street Journal database using up to 66 hours of acoustic training data. These demonstrate that the use of lattices makes MMIE training practicable for very complex recognition systems and large training sets. Furthermore, the experimental results show that MMIE optimisation of system structure and param...

The aim of this work is to build up a common framework for a class of discriminative training criteria and optimization methods for continuous speech recognition. A unified discriminative criterion based on likelihood ratios of correct and competing models with optional smoothing is presented. The unified criterion leads to particular criteria through the choice of competing word sequences and the choice of smoothing. Analytic and experimental comparisons are presented for both the maximum mutual information (MMI) and the minimum classification error (MCE) criterion together with the optimization methods gradient descent (GD) and extended Baum (EB) algorithm. A tree search-based restricted recognition method using word graphs is presented, so as to reduce the computational complexity of large vocabulary discriminative training. Moreover, for MCE training, a method using word graphs for efficient calculation of discriminative statistics is introduced. Experiments were performed for continuous speech recognition using the ARPA wall street journal (WSJ) corpus with a vocabulary of 5k words and for the recognition of continuously spoken digit strings using both the TI digit string corpus for American English digits, and the SieTill corpus for telephone line recorded German digits. For the MMI criterion, neither analytical nor experimental results do indicate significant differences between EB and GD optimization. For acoustic models of low complexity, MCE training gave significantly better results than MMI training. The recognition results for large vocabulary MMI training on the WSJ corpus show a significant dependence on the context length of the language model used for training. Best results were obtained using a unigram language model for MMI training. No significant co...

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...

This paper describes a lattice-based framework for maximum mutual information estimation (MMIE) of HMM parameters 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 use of MMIE training was a key contributer to the performance of the CU-HTK March 2000 Hub5 evaluation system. 1 INTRODUCTION The model parameters in HMM based speech recognition systems are normally estimated using Maximum Likelihood Estimation (MLE). If certain conditions hold, including model correctness, then MLE can be shown to be optimal. However, when estimating the parameters of HMM-based speech recognisers, the true d...

We present a simplified derivation of the extended Baum-Welch procedure, which shows that it can be used for Maximum Mutual Information (MMI) of a large class of continuous emission density hidden Markov models (HMMs). We use the extended Baum-Welch procedure for discriminative estimation of MLLR-type speaker adaptation transformations. The resulting adaptation procedure, termed Conditional Maximum Likelihood Linear Regression (CMLLR), is used successfully for supervised and unsupervised adaptation tasks on the Switchboard corpus, yielding an improvement over MLLR. The interaction of unsupervised CMLLR with segmental minimum Bayes risk lattice voting procedures is also explored, showing that the two procedures are complimentary. 1.

We investigate a learning algorithm for the classification of nonnegative data by mixture models. Multiplicative update rules are derived that directly optimize the performance of these models as classifiers. The update rules have a simple closed form and an intuitive appeal. Our algorithm retains the main virtues of the Expectation-Maximization (EM) algorithm—its guarantee of monotonic improvement, and its absence of tuning parameters—with the added advantage of optimizing a discriminative objective function. The algorithm reduces as a special case to the method of generalized iterative scaling for log-linear models. The learning rate of the algorithm is controlled by the sparseness of the training data. We use the method of nonnegative matrix factorization (NMF) to discover sparse distributed representations of the data. This form of feature selection greatly accelerates learning and makes the algorithm practical on large problems. Experiments show that discriminatively trained mixture models lead to much better classification than comparably sized models trained by EM.

We introduce an expectation maximizationtype (EM) algorithm for maximum likelihood optimization of conditional densities. It is applicable to hidden variable models where the distributions are from the exponential family. The algorithm can alternatively be viewed as automatic step size selection for gradient ascent, where the amount of computation is traded off to guarantees that each step increases the likelihood. The tradeoff makes the algorithm computationally more feasible than the earlier conditional EM. The method gives a theoretical basis for extended Baum Welch algorithms used in discriminative hidden Markov models in speech recognition, and compares favourably with the current best method in the experiments.

Discriminative training techniques for Hidden-Markov Models were recently proposed and successfully applied for automatic speech recognition. In this paper a discussion of the Minimum Classification Error and the Maximum Mutual Information objective is presented. An extended reestimation formula is used for the HMM parameter update for both objective functions. The discriminative training methods were utilized in speaker independent phoneme recognition experiments and improved the phoneme recognition rates for both discriminative training techniques. 1. INTRODUCTION Recently discriminative training techniques for Hidden- Markov Models (HMM) were used successfully for automatic speech recognition. They provide better performance compared to Maximum Likelihood Estimation (MLE), since the training is concentrated on the estimation of class boundaries and not on parameters of assumed model distributions [1,12]. Although MLE and discriminative training are theoretically equivalent (if su...

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.