Joel J. Cartwright

Learn More
We investigate a solution to the problem of multi-sensor perception and tracking by formulating it in the framework of Bayesian model selection. Humans robustly associate multi-sensory data as appropriate , but previous theoretical work has fo-cused largely on purely integrative cases, leaving segregation unaccounted for and unexploited by machine(More)
We formulate a novel Bayesian generative model for binaural sound source localisa-tion using time delay estimation. This is a form of hiearchical hidden Markov model, including data association and second order time delay state. Learning of system parameters is performed with EM. Using a typical cluttered office test environment and custom moving sound(More)
  • 1