Carol Espy-Wilson receives NSF grant for acoustic-phonetic knowledge and speech recognition.

Associate Professor Carol Espy-Wilson (ECE/ISR) has received a three-year, $407,549 National Science Foundation grant for "Acoustic-Phonetic Knowledge and Speech Recognition." This project will develop a robust automatic speech recognition system, including acoustic parameters that target the linguistic information in the speech signal and a new paradigm for recognition that integrates current speech knowledge with a powerful statistical framework.

The knowledge-based speech recognition system will serve as a model of the early stages of speech perception, and will aid in understanding and coping with variation in speech that occurs within and across speakers due to differences in gender, age and emotional states. Different components of the system will serve as speech analysis tools for applications such as speech coding, automatic speech transcription, speech enhancement, and speech training aids for speech pathologists and their clients.

Published April 15, 2003