CNEL Alumnus: Mark SkowronskiFormer student webpage:
Mark Skowronski is a recent Ph.D. graduate under the supervision of Dr. John G. Harris of the Computational Neuro-Engineering Lab (CNEL). See cnel.ufl.edu/~markskow for details.
|My Research Interests|
Noise robust feature extraction, automatic speech recognition, nonlinear dynamics, Freeman model
I would like to improve automatic speech recognition technology, specifically in two areas. Current ASR is limited by test/train mismatch--I would like to decrease this mismatch by investigating noise-robust feature extraction. Also, current ASR handles the time-varying nonstationary nature of human speech poorly. I want to develop a classification method, inspired by our knowledge of the functioning of the human brain, that exhibits recognition performance in adverse listening environments closer to that of the human auditory system when compared with current HMM-based systems.
|1||Mark D. Skowronski, John G. Harris, "Increased mfcc Filter Bandwidth for Noise-robust Phoneme Recognition", Intl. Conf. on Acoustics, Speech, and Signal Processing, pp. 801-804, Mar. 2002 (author PDF) |
|2||Mark D. Skowronski, John G. Harris, "A Probabilistic Analysis of the Ratio Spectrum", Symposium on Adaptive Systems for Signal Processing, Communications and Control, pp. 333-336, Oct. 2000 (author PDF) |
Copyright Notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.