Matthew N. Stuttle

Learn More
Within the broad field of spoken dialogue systems, the application of machine-learning approaches to dialogue management strategy design is a rapidly growing research area. The main motivation is the hope of building systems that learn through trial-and-error interaction what constitutes a good dialogue strategy. Training of such systems could in theory be(More)
Over the past decade, a variety of user models have been proposed for user simulation-based reinforcement-learning of dialogue strategies. However, the strategies learned with these models are rarely evaluated in actual user trials and it remains unclear how the choice of user model affects the quality of the learned strategy. In particular, the degree to(More)
We demonstrate a multimodal dialogue system using reinforcement learning for in-car scenarios, developed at Edinburgh University and Cambridge University for the TALK project. This prototype is the first “Information State Update” (ISU) dialogue system to exhibit reinforcement learning of dialogue strategies, and also has a fragmentary clarification(More)
We report results on rapidly building language models for dialogue systems. Our base line is a recogniser using a grammar network. We show that we can almost halve the word error rate (WER) by combining language models generated from a simple task grammar with a standard speech corpus and data collected from the web using a sentence selection algorithm(More)
This paper describes a feature extraction technique based on fitting a Gaussian mixture model (GMM) to the speech spectral envelope. The features obtained (the component means, variances and priors) represent both the the general shape of the spectrum and provide information on the position of the spectral peaks. As the features select peaks in the spectrum(More)
The application of machine learning methods to the dialogue management component of spoken dialogue systems is a growing research area. Whereas traditional methods use handcrafted rules to specify a dialogue policy, machine learning techniques seek to learn dialogue behaviours from a corpus of training data. In this paper, we identify the properties of a(More)
Fitting a Gaussian mixture model (GMM) to the smoothed speech spectrum allows an alternative set of features to be extracted from the speech signal. These features have been shown to possess information complementary to the standard MFCC parameterisation. This paper further investigates the use of these GMM features in combination with MFCCs. The extraction(More)
Speech recognition systems typically contain many Gaussian distributions, and hence a large number of parameters. This makes them both slow to decode speech, and large to store. Techniques have been proposed to decrease the number of parameters. One approach is to share parameters between multiple Gaussians, thus reducing the total number of parameters and(More)
In this paper, part-of-speech (POS) information is used to improve the performance of a Japanese language model (LM). The POS bigram is used to tackle the sparseness problem of the training data. Additionally, due to the characteristics of the Japanese language, part of the Japanese syntax information can be integrated into the POS bigram, through POS(More)