We describe experiments in visual-only language identification (VLID), in which only lip shape, appearance and motion are used to determine the language of a spoken utterance. In...
A significant challenge in Text-to-Speech (TtS) synthesis is the formulation of the prosodic structures (phrase breaks, pitch accents, phrase accents and boundary tones) of uttera...
Phonotactic approach, phone recognition to be followed by language modeling, is one of the most popular approaches to language identification (LID). In this work, we explore how ...
C. P. Santhosh Kumar, Haizhou Li, Rong Tong, Pavel...
Abstract. In some learning settings, the cost of acquiring features for classification must be paid up front, before the classifier is evaluated. In this paper, we introduce the fo...
Jason V. Davis, Jungwoo Ha, Christopher J. Rossbac...
Decision-tree algorithms are known to be unstable: small variations in the training set can result in different trees and different predictions for the same validation examples. B...