One commonly used approach for language recognition is to convert the input speech into a sequence of tokens such as words or phones and then to use these token sequences to deter...
We describe a framework for inducing probabilistic grammars from corpora of positive samples. First, samples are incorporated by adding ad-hoc rules to a working grammar; subseque...
We propose a robust scene recognition system for baseball broadcast videos. This system is based on the data-driven approach which has been successful in continuous speech recogni...
In this paper, we propose a novel technique for modelbased recognition of complex object motion trajectories using Hidden Markov Models (HMM). We build our models on Principal Com...
Faisal I. Bashir, Wei Qu, Ashfaq A. Khokhar, Dan S...
This paper studies the influence of n-gram language models in the recognition of sung phonemes and words. We train uni-, bi-, and trigram language models for phonemes and bi- and...