Speech Recognition

A key theoretical axiom of the Featurally Underspecified Lexicon model of distinctive features theory is that "features" (the articulatory and acoustic properties that make one sound crucially contrast with another) should have rigorous definitions, not only in terms of the movement of speech organs, but most importantly in terms of the effect they have on the acoustic speech signal.

This makes it possible for the FUL concept to be used as the basis of a novel Automated Speech Recognition engine, and development of this idea continued under the WORDS project.

The FUL ASR system examines the acoustic properties of a speech sound and extracts distinctive features from it. These features are then matched against the lexicon to identify the words used. The result is an ASR system that requires no training, and employs theoretical insights from the study of how the human brain processes speech to emulate this process on the computer.

 

Research interests: