Supervised learning uses a training set of labeled examples to compute a classifier which is a mapping from feature vectors to class labels. The success of a learning algorithm i...
Training accurate acoustic models typically requires a large amount of transcribed data, which can be expensive to obtain. In this paper, we describe a novel semi-supervised learn...
Balakrishnan Varadarajan, Dong Yu, Li Deng, Alex A...
This paper presents the development and evaluation of a speaker-independent audio-visual speech recognition (AVSR) system that utilizes a segment-based modeling strategy. To suppo...
Timothy J. Hazen, Kate Saenko, Chia-Hao La, James ...
—Techniques for automatic annotation of spoken content making use of speech recognition technology have long been characterized as holding unrealized promise to provide access to...
Roeland Ordelman, Franciska de Jong, Martha Larson
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...