Untranslated words still constitute a major problem for Statistical Machine Translation (SMT), and current SMT systems are limited by the quantity of parallel training texts. Augm...
Language Identification (LID) refers to the task of identifying an unknown language from the test utterances. In this paper, a new method of feature extraction, viz., Teager Energy...
Based on ten years' experience developing interactive camera/projector systems for public science and culture exhibits, we define a distinct form of augmented reality focused...
Discriminative training for language recognition has been a key tool for improving system performance. In addition, recognition directly from shifted-delta cepstral features has p...
Varying channel conditions present a difficult problem for many speech technologies such as language identification (LID). Channel compensation techniques have been shown to sig...