One of the key issues for adaptation algorithms is to modify a large number of parameters with only a small amount of adaptation data. Speaker adaptation techniques try to obtain near speaker dependent (SD) performance with only small amounts of speaker specific data, and are often based on initial speaker independent (SI) recognition systems. Some of these speaker adaptation techniques may also be applied to the task of adaptation to a new acoustic environment. In this case a SI recognition system trained in, typically, a clean acoustic environment is adapted to operate in a new, noise-corrupted, acoustic environment. This paper examines the Maximum Likelihood Linear Regression (MLLR) adaptation technique. MLLR estimates linear transformations for groups of models parameters to maximise the likelihood of the adaptation data. Previously, MLLR has been applied to the mean parameters in mixture Gaussian HMM systems. In this paper MLLR is extended to also update the Gaussian variances and re-estimation formulae are derived for these variance transforms. MLLR with variance compensation is evaluated on several large vocabulary recognition tasks. The use of mean and variance MLLR adaptation was found to give an additional 2% to 7% decrease in word error rate over mean-only MLLR adaptation. 1

This paper addresses the problem of automatic speech recognition in the presence of interfering noise. It focuses on the Parallel Model Combination (PMC) scheme, which has been shown to be a powerful technique for achieving noise robustness. Most experiments reported on PMC to date have been on small, 10-50 word vocabulary systems. Experiments on the Resource Management (RM) database, a 1000 word continuous speech recognition task, reveal compensation requirements not highlighted by the smaller vocabulary tasks. In particular, that it is necessary to compensate the dynamic parameters as well as the static parameters to achieve good recognition performance. The database used for these experiments was the RM speaker independent task with either Lynx Helicopter noise or Operation Room noise from the NOISEX-92 database added. The experiments reported here used the HTK RM recogniser developed at CUED modified to include PMC based compensation for the static, delta and delta-delta parameters. After training on clean speech data,the performance of the recogniser was found to be severely degraded when noise was added to the speech signal at between 10dB and 18dB. However, using PMC the performance was restored to a level comparable with that obtained when training directly in the noise corrupted environment. 1

Graphical models provide a promising paradigm to study both existing and novel techniques for automatic speech recognition. This paper first provides a brief overview of graphical models and their uses as statistical models. It is then shown that the statistical assumptions behind many pattern recognition techniques commonly used as part of a speech recognition system can be described by a graph – this includes Gaussian distributions, mixture models, decision trees, factor analysis, principle component analysis, linear discriminant analysis, and hidden Markov models. Moreover, this paper shows that many advanced models for speech recognition and language processing can also be simply described by a graph, including many at the acoustic-, pronunciation-, and language-modeling levels. A number of speech recognition techniques born directly out of the graphical-models paradigm are also surveyed. Additionally, this paper includes a novel graphical analysis regarding why derivative (or delta) features improve hidden Markov model-based speech recognition by improving structural discriminability. It also includes an example where a graph can be used to represent language model smoothing constraints. As will be seen, the space of models describable by a graph is quite large. A thorough exploration of this space should yield techniques that ultimately will supersede the hidden Markov model.

This dissertation is the result of my own work and includes nothing which is the outcome of work done in collaboration. It has not been submitted in whole or in part for a degree at any other university. Some of the work has been published previously in conference proceedings

This paper describes techniques to improve the robustness of the HTK large vocabulary speech recognition system to non-ideal acoustic environments. The primary methods are single-pass retraining using stereo training data; parallel model combination which combines HMMs trained on clean data with estimates of convolutional and additive noise; and maximum likelihood linear regression which estimates a set of linear transformations of the model parameters to the current conditions. Experiments are reported on both the 1994 ARPA CSR S5 (alternate microphones) and S10 (additive noise) spoke tasks and the 1995 ARPA CSR H3 task (multiple unknown microphones). The HTK system yielded the lowest error rates in both the H3-P0 and H3-C0 tests. 1. INTRODUCTION Most work on speaker independent large vocabulary continuous speech recognition (LVCSR) has focused on the use of speech recorded using a close-talking noise-cancelling microphone i.e. clean speech. Furthermore, the recognition performance o...

Z. In this paper, we generalize relations between clean and noisy speech signal using vector Taylor series VTS expansion Z. for noise-robust speech recognition. We use it for both the noisy data compensation and hidden Markov model HMM parameter adaptation, and apply it for the cepstral domain directly, while Moreno used it to estimate the log-spectral parameters. Also, we develop a detailed procedure to estimate environmental variables in the cepstral domain using the Z. Z. expectation and maximization EM algorithms based on the maximum likelihood ML sense. To evaluate the developed method, we conduct speaker-independent isolated word and continuous speech recognition experiments. White Gaussian and driving car noises added to clean speech at various SNR are used as disturbing sources. Using only noise statistics obtained from three frames of silence and noisy speech to be recognized, we achieve significant performance improvement. Z. Especially, HMM parameter adaptation with VTS i...

Since their inception over thirty years ago, hidden Markov models (HMMs) have have become the predominant methodology for automatic speech recognition (ASR) systems — today, most state-of-the-art speech systems are HMM-based. There have been a number of ways to explain HMMs and to list their capabilities, each of these ways having both advantages and disadvantages. In an effort to better understand what HMMs can do, this tutorial analyzes HMMs by exploring a novel way in which an HMM can be defined, namely in terms of random variables and conditional independence assumptions. We prefer this definition as it allows us to reason more throughly about the capabilities of HMMs. In particular, it is possible to deduce that there are, in theory at least, no theoretical limitations to the class of probability distributions representable by HMMs. This paper concludes that, in search of a model to supersede the HMM for ASR, we should rather than trying to correct for HMM limitations in the general case, new models should be found based on their potential for better parsimony, computational requirements, and noise insensitivity.

For practical applications speech recognition systems need to be insensitive to differences between training and test acoustic conditions. Differences in the acoustic environment may result from various sources, such as ambient background noise, channel variations and speaker stress. These differences can dramatically degrade the performance of a speech recognition system. A wide range of techniques have been proposed for achieving noise robustness. This paper considers one particular approach to model-based compensation, predictive model-based compensation, which has been shown to achieve good noise robustness in a wide range of acoustic environments. The characteristic of these schemes is that they combine a speech model with an additive noise model, a channel model and, in the general case, a speaker stress model, to generate a corrupted-speech model. The general theory of these predictive techniques is discussed. Various approximations for rapidly performing the model combination stage have been proposed and are reviewed in this paper. The advantages and the limitations of such a predictive approach to noise robustness are also discussed. In addition, methods for combining predictive schemes with schemes which make use of speech data in the new environment, adaptive schemes, are detailed. This combined approach overcomes some of the limitations of the predictive schemes. 1 The author is now at the IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA. 1

Recent advances in automatic speech recognition are accomplished by designing a plug-in maximum a posteriori decision rule such that the forms of the acoustic and language model distributions are specified and the parameters of the assumed distributions are estimated from a collection of speech and language training corpora. Maximum-likelihood point estimation is by far the most prevailing training method. However, due to the problems of unknown speech distributions, sparse training data, high spectral and temporal variabilities in speech, and possible mismatch between training and testing conditions, a dynamic training strategy is needed. To cope with the changing speakers and speaking conditions in real operational conditions for high-performance speech recognition, such paradigms incorporate a small amount of speaker and environment specific adaptation data into the training process. Bayesian adaptive learning is an optimal way to combine

The HTK large vocabulary speech recognition system has previously shown very good performance for clean speech. This paper describes developments of the system aimed at recognition of speech from the ARPA H3 task which contains data of a relatively low signal-to-noise ratio from unknown microphones. It is shown that a two-phase approach can be effective. The first phase is to derive an initial set of models that are more appropriate for the current conditions than using models trained on clean speech. This is done using either single-pass retraining with multiple microphone data or parallel model combination which combines HMMs trained on clean data with estimates of convolutional and additive noise. The second stage provides more detailed environmental and speaker adapatation using maximum likelihood linear regression which estimates a set of linear transformations of the model parameters to the current conditions. Experiments are reported on both the 1994 ARPA CSR S5 (alternate micro...