No description available.

Thesis (Ph.D.). / Written for the Dept. of Mathematics. Title from title page of PDF (viewed 2008/08/07). Includes bibliographical references.

No description available.

No description available.

A statistical language model attempts to characterise the patterns present in a natural language as a probability distribution defined over word sequences. Typically, they are trained using word co-occurrence statistics from a large sample of text. In some language modelling applications, such as automatic speech recognition (ASR), the availability of acoustic data provides an additional source of knowledge. This contains, amongst other things, the melodic and rhythmic aspects of speech referred to as prosody. Although prosody has been found to be an important factor in human speech recognition, its use in ASR has been limited. The goal of this research is to investigate how prosodic information can be employed to improve the language modelling component of a continuous speech recognition system. Because prosodic features are largely suprasegmental, operating over units larger than the phonetic segment, the language model is an appropriate place to incorporate such information. The prosodic features and standard language model features are combined under the maximum entropy framework, which provides an elegant solution to modelling information obtained from multiple, differing knowledge sources. We derive features for the model based on perceptually transcribed Tones and Break Indices (ToBI) labels, and analyse their contribution to the word recognition task. While ToBI has a solid foundation in linguistic theory, the need for human transcribers conflicts with the statistical model's requirement for a large quantity of training data. We therefore also examine the applicability of features which can be automatically extracted from the speech signal. We develop representations of an utterance's prosodic context using fundamental frequency, energy and duration features, which can be directly incorporated into the model without the need for manual labelling. Dimensionality reduction techniques are also explored with the aim of reducing the computational costs associated with training a maximum entropy model. Experiments on a prosodically transcribed corpus show that small but statistically significant reductions to perplexity and word error rates can be obtained by using both manually transcribed and automatically extracted features.

Thesis (M.S.)--Rochester Institute of Technology, 1983. / Typescript. Includes bibliographical references (leaves 115-119).

Thesis (Ph. D.)--Illinois State University, 2004. / Title from title page screen, viewed Jan. 21, 2005. Dissertation Committee: Nerida F. Ellerton (chair), Sherry L. Meier, Sharon Soucy McCrone, Tami S. Martin. Includes bibliographical references (leaves 153-163) and abstract. Also available in print.

No description available.

Thesis (Ph.D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1979. / MICROFICHE COPY AVAILABLE IN ARCHIVES AND ENGINEERING. / Bibliography: leaves 275-282. / by Candace Lee Sidner. / Ph.D.

Habilitationsschrift--Universität Regensburg, 1985. / Includes indexes. Includes bibliographical references (p. 296-310).