We propose a new active learning algorithm to address the problem of selecting a limited subset of utterances for transcribing from a large amount of unlabeled utterances so that ...
Balakrishnan Varadarajan, Dong Yu, Li Deng, Alex A...
When exposed to environmental noise, speakers adjust their speech production to maintain intelligible communication. This phenomenon, called Lombard effect (LE), is known to consi...
Abstract. Automatic personal identification based on palmprints has been considered as a promising technology in biometrics family during recent years. In pursuit of accurate palmp...
Abstract. In this paper we introduce a novel approach for learning view-invariant gait representation that does not require synthesizing particular views or any camera calibration....