Yu-Hsiang Bosco Chiu

Yu-Hsiang Bosco Chiu

Department of Electrical and Computer Engineering

RESUME

About Me

I am a PhD student at Carnegie Mellon. My advisor is Prof. Richard Stern, and my main interests are in speech recognition and machine learning. Most of my work relates to learning and optimizing the essential properties which we found from human auditory processing that contribute the most to the speech recognition robustbess directly from data.

Publications

Y.-H. Chiu, B. Raj and R. Stern, "Towards Fusion of Feature Extraction and Acoustic Model Training: A Top Down Process for Robust Speech Recognition". International Conference on Spoken Language Processing (ICSLP), September 2009, Brighton, U.K.
M. Lu, Y.-H. Chiu and T. Chen, "Classification-based Relay Selection for Wireless Video Streaming". IEEE International Conference on Multimedia and Expo (ICME), July 2009 New York, USA.
Y.-H. Chiu and R. Stern, "Minimum Variance Modulation Filter for Robust Speech Recognition". IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), April 2009, Taipei, Taiwan.
Y.-H. Chiu and R. Stern, "Analysis of Physiology-Motivated Signal Processing for Robust Speech Recognition". ICSLP, September 2008, Brisbane, Australia.
J. Droppo, M. Seltzer A. Acero and Y.-H. Chiu, " Towards a Non-Parametric Acoustic Model: An Acoustic Decision Tree for Observation Probability Calculation". ICSLP, September 2008, Brisbane, Australia.
C. Kim, Y.-H. Chiu and R. Stern, "Physiologically-Motivated Synchrony-Based Processing for Robust Automatic Speech Recognition". ICSLP, September 2006, Pittsburgh, USA.
Y.-H. Chiu, H.-C. Wang, Y.-C. Chang, and K.-C. Huang, "A design of filter-bank for auditory training". In Proc. The 8th Asia-Pacific Congress on Deafness, Taipei, Taiwan, 2002, pp. 27.1-27.8.

Presentations

Signal Processing for Robust Speech Recognition: Voice Activity Detection (Slides)