We propose a unified global entropy reduction maximization (GERM) framework for active learning and semi-supervised learning for speech recognition. Active learning aims to select...
Dong Yu, Balakrishnan Varadarajan, Li Deng, Alex A...
In this paper, we present a novel approach for human activities recognition in the video. We analyze human activities in the sequential frames because human activities can be cons...
The concept of probabilistic Latent Semantic Analysis (pLSA) has gained much interest as a tool for feature transformation in image categorization and scene recognition scenarios. ...
Towards the goal of realizing a generic automatichuman activity recognition system, a new formalism is proposed. Activities are described by a chained hierarchical representation ...
Abstract. An important step to bring speech technologies into wide deployment as a functional component in man-machine interfaces is to free the users from close-talk or desktop mi...
Stephen M. Chu, Etienne Marcheret, Gerasimos Potam...