and Prosodic Models
ICSLP 2002 - September 16, 2002, Denver Colorado
Greg Kochanski and Chilin Shih
Speech is more than just text: it has emotional content and other information "around" the speech. This non-lexical information is called prosody. I'd like to understand what information is carried by prosody and how it is encoded. My recent research is related to these questions, and it includes models of prosody generation and communication, Mandarin intonation, and signal processing algorithms for better measurements of perceptually relevant acoustic properties.
Historically, I've worked in Astrophysics and Surface Physics, with a side trip into field emitters and display technology. Most of my work has involved building models of complex systems that have explanatory as well as predictive power.
|[ Papers | Top | Stem-ML modeling ]||Greg Kochanski: [ Mail | Home
Chilin Shih: [ Mail | Home ]