Publications by Steve Isard

We describe our work in building a spoken language interface for a tutorial dialogue system. Our goal is to allow natural, unrestricted student interaction with the computer tutor, which has been shown to improve the student's learning gain, but presents challenges for speech recognition and spoken language understanding. We discuss the choice of system components and present the results of development experiments in both acoustic and language modelling for speech recognition in this domain.

We present Beetle II, a tutorial dialogue system which accepts unrestricted language input and supports experimentation with different tutorial planning and dialogue strategies. Our first system evaluation compared two tutorial policies and demonstrated that the system can be used to study the impact of different approaches to tutoring. The system is also designed to allow experimentation with a variety of natural language techniques, and discourse and dialogue strategies.

We discuss the use of an accent-independent keyword lexicon to synthesise speakers with different regional accents. The paper describes the system architecture and the transcription system used in the lexicon, and then focuses on the construction of word-lists for recording speakers. We illustrate by mentioning some of the features of Scottish and Irish English, which we are currently synthesising, and describe how these are captured by keyword synthesis.

We describe a speech recogniser which uses a speech production-motivated phonetic-feature description of speech. We argue that this is a natural way to describe the speech signal and offers an efficient intermediate parameterisation for use in speech recognition. We also propose to model this description at the syllable rather than phone level. The ultimate goal of this work is to generate syllable models whose parameters explicitly describe the trajectories of the phonetic features of the syllable. We hope to move away from Hidden Markov Models (HMMs) of context-dependent phone units. As a step towards this, we present a preliminary system which consists of two parts: recognition of the phonetic features from the speech signal using a neural network; and decoding of the feature-based description into phonemes using HMMs.

This paper reports on work developing an accent-independent lexicon for use in synthesising speech in English. Lexica which use phonemic transcriptions are only suitable for one accent, and developing a lexicon for a new accent is a long and laborious process. Potential solutions to this problem include the use of conversion rules to generate lexica of regional pronunciations from standard accents and encoding of regional variation by means of keywords. The latter proposal forms the basis of the current work. However, even if we use a keyword system for lexical transcription there are a number of remaining theoretical and methodological problems if we are to synthesise and recognise accents to a high degree of accuracy; these problems are discussed in the following paper.

This paper describes a method for using intonation to reduce word error rate in a speech recognition system designed to recognise spontaneous dialogue speech. We use a form of dialogue analysis based on the theory of conversational games. Different move types under this analysis conform to different language models. Different move types are also characterised by different intonational tunes. Our overall recognition strategy is first to predict from intonation the type of game move that a test utterance represents, and then to use a bigram language model for that type of move during recognition. point in a game.

We present work intended to improve speech recognition performance for computer dialogue by taking into account the way that dialogue context and intonational tune interact to limit the possibilities for what an utterance might be. We report here on the extra constraint achieved in a bigram language model expressed in terms of entropy by using separate submodels for different sorts of dialogue acts and trying to predict which submodel to apply by analysis of the intonation of the sentence being recognised.

We report on an automatic speech recognition system intended for use in dialogue, whose original aspect is its use of prosodic information for two different purposes. The first is to improve the word level accuracy of the system. The second is to constrain the language model applied to a given utterance by taking into account the way that dialogue context and intonational tune interact to limit the possibilities for what an utterance might be.