A Semi - Automatic System for the Syllabification and Stress Assignment

This Master's Thesis concerns research in the automatic analysis of the sub-lexical structure of English words. Sub-lexical structure includes linguistic categories such as syllabification, stress, phonemic representation, phonetics, and spelling. This information could be very useful in all sorts of speech applications, including duration modeling and speech recognition. ANGIE is a system that can parse words, given either their phonetic or orthographic representation, into a common hierarchical framework with the categories mentioned above. A new feature enforcing morphological constraints has recently been added to this paradigm. We define "morphs" to be somewhat like syllable units of a word, but each of them are tagged morphologically, and associated with both an orthographic sequence and a phonemic representation. Each word is represented as concatenations of these morphs, which then encode both the orthography and the phonemics of the word. This thesis defines a procedure to semi-automatically derive a sub-lexical representation of new words in terms of these morphs, using ANGIE's hierarchical framework. One distinctive characteristic of this procedure is that both the phonetics and the spelling information are utilized. The procedure is developed using several corpora. When this procedure is used to derive the sub-lexical representations, some words will fail, either because the word is rejected by the hierarchical framework, or a morph needed to transcribe the word is missing. The words that successfully obtain morphological decompositions are used to evaluate the coverage and accuracy of the existing procedure. The words that fail to be represented are a valuable resource because they provide new information about the sub-lexical structure of English. This new information can be incorporated into our procedure to improve its coverage and accuracy. Thesis Supervisor: Dr. Stephanie Seneff Title: Principal Research Scientist Thesis Co-Supervisor: Dr. Helen Meng Title: Research Scientist