Automatic continuous speech recognition (CSR) is sufficiently

Declaration This dissertation is the result of my own work and includes nothing that 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 [66,69], two journal articles [36,68], two workshop papers [35,67] and a tech-nical report [65]. The length of this thesis including appendices, bibliography, footnotes, tables and equations is approximately 60,000 words. This thesis contains 27 figures and 20 tables. i

The most popular model used in automatic speech recognition is the hidden Markov model (HMM). Though good performance has been obtained with such models there are well known limitations for its ability to model speech. A variety of modications to the standard HMM topology have been proposed to handle these problems. One such scheme is the factorial HMM. This paper introduces a new form of factorial HMM which makes use of transformation streams. This new scheme is a generalisation of the standard factorial HMM and other related schemes in speech processing. A particular form of this model, the HMM error model (HEM) is described in detail. The HEM is evaluated on two standard large vocabulary speaker independent speech recognition tasks. On both tasks signicant reductions in word error rate are obtained over standard HMM-based systems. 2 1

Declaration 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 [15, 16, 17]. The length of this thesis including appendices, references, footnotes, tables and equations is approximately 56,000 words and contains 42 figures and 40 tables. i Summary It has been found that using a combination of systems for large vocabulary continuous speech recognition (LVCSR) can outperform the use of a single system. For the combination to yield gains, the individual models must be complementary, i.e. they must make different errors. Previous work in ASR has mainly relied on an ad-hoc approach to finding complementary systems. Multiple systems are built, and those that perform well in combination are selected. The multiple diverse systems can be built in many ways, including the use of different frontends, injecting randomness, altering the model topology or using different training