The key problem to be faced when building a HMM-based continuous speech recogniser is maintaining the balance be-tween model complexity and available training data. For large vocabulary systems requiring cross-word context dependent modelling, this is particularly acute since many mmh contexts will never occur in the training data. This paper describes a method of creating a tied-state continuous speech recognition system using a phonetic decision tree. This tree-based clustering is shown to lead to similar recognition performance to that obtained using an earlier data-driven approach but to have the additional advantage of providing a mapping for unseen triphones. State-tying is also compared with traditional model-based tying and shown to be clearly superior. Experimental results are presented for both the Resource Management and Wall Street Journal tasks.

decide which contexts are similar and can share parameters. A key feature of this approach is that it allows the construction of models which are dependent upon contextual effects occurring across word boundaries. The use of cross word context dependent models presents problems for conventional decoders. The second part of the thesis therefore presents a new decoder design which is capable of using these models efficiently. The decoder is suitable for use with very large vocabularies and long span language models. It is also capable of generating a lattice of word hypotheses with little computational overhead. These lattices can be used to constrain further decoding, allowing efficient use of complex acoustic and language models. The effectiveness of these techniques has been assessed on a variety of large vocabulary continuous speech recognition tasks and results are presented which analyse performance in terms of computational complexity and recognition accuracy. The experiments dem

Abstract – Given the importance of implicit communication in human interactions, it would be valuable to have this capability in robotic systems wherein a robot can detect the motivations and emotions of the person it is working with. Recognizing affective states from physiological cues is an effective way of implementing implicit human-robot interaction. Several machine learning techniques have been successfully employed in affect-recognition to predict the affective state of an individual given a set of physiological features. However, a systematic comparison of the strengths and weaknesses of these methods has not yet been done. In this paper we present a comparative study of four machine learning methods- K-Nearest Neighbor, Regression Tree, Bayesian Network and Support Vector Machine as applied to the domain of affect recognition using physiological signals. The results showed that Support Vector Machine gave the best classification accuracy even though all the methods performed competitively. Regression Tree gave the next best classification accuracy and was the most space and time efficient.

The adaptation of existing general-purpose speech recognition and language understanding systems can greatly reduce the cost of developing applications. However, the components must have appropriate characteristics for this to be possible. Work is in progress to adapt two task-independent components, the AURIX speech recognizer and the CLARE language processor to create a system allowing spoken queries of the PC-based Autoroute route planning package. Keywords: adaptability, general purpose, speech recognition, language understanding, AURIX, CLARE 1. INTRODUCTION A spoken language understanding system is being built by the reconfiguration of two general purpose components. AURIX is designed to be a reconfigurable speech recognizer generating either a string or words or a lattice. Either input can be fed into CLARE, a general purpose language processor, which can generate suitable commands or database queries for a particular application. In the following sections, we describe first...

Abstract: A novel implicit communication framework in human-machine interaction that is sensitive to human affective states is presented in this paper. The focus is to achieve detection and recognition of human affect based on physiological signals. This involves building an affect recognition system that accepts as input various physiological parameters and predicts the probable related affective state. Both decision tree and fuzzy logic methodologies have been applied to this problem. This paper presents the results of the two methods and discusses their comparative merit. Three human subject experiments were designed and trials were conducted with six participants. The experimental results demonstrate the feasibility of the proposed implicit human-machine interaction framework.