Statistical Analysis of Phonetic Inventories of the Worlds Languages

This project will involve analyzing the distribution of sounds across
the worlds languages. The goal is to develop a phonetic prior model
that can serve to guide a computer as it tries to learn the phonetic
inventory of an unknown language. The CSAIL Spoken Language Systems
groups has been developing non-parametric Bayesian methods to learn
speech sounds. The student involved in this project would work with
graduate students to refine these models. Interested students should
send a CV to Jim Glass,