The Human Speech Recognition Group is interested in hearing functions both in disabled and non-disabled people, discovering non-invasive testing, the theory and practice of the process of human speech recognition, and perceiving music as well. In the last 10 years, we have collected several large databases of speech perception in noise, by normal and impaired human subjects which have resulted in many publications. Among our current goals is to improve hearing aid signal processing as well as automatic speech recognition robustness in the presences of noise and filtering. See Figure 1.3 for a visual representation of our work. Our research interests include:
- Sources of reading disabilities in children
- Human Speech Recognition
- Modeling of consonant-vowel confusions
- Auditory masking
- Speech processing for hearing aids
- Auditory psychophysics
- Diagnostic testing of the middle and inner ear
- Wave propagation in horns
- Acoustical transducer physics and modeling
- Cochlear modeling
- Modeling the middle ear and ear canal
- Speech modeling and coding
- Musical acoustics
Our Group Leader is Jont Allen.
Learn more about us at our website here.