Current automatic speech recognition systems function usefully, but operate very differently from human speech perception. This project involves work on a speech signal-analysis system that is modeled more closely on what we know about human speech processing. We will work to develop a consolidator module to integrate acoustic, lexical, and prosodic information derived from the signal into a preliminary hierarchical structure for the entire phrase or utterance even before the speaker’ s intended words are fully recognized.

“Personally, this project builds on a previous project that challenged me and which I enjoyed working on. More important, improving speech processing methods currently used has wide-reaching and long-term benefits across multiple fields. Successfully completing this project will be both rewarding and impactful beyond the scope of what I do. I am looking forward to it.”