Deep Belief Networks (DBNs) are multi-layer generative models. They can be trained to model windows of coefficients extracted from speech and they discover multiple layers of fea...
Abdel-rahman Mohamed, Tara N. Sainath, George Dahl...
Situated, spontaneous speech may be ambiguous along acoustic, lexical, grammatical and semantic dimensions. To understand such a seemingly difficult signal, we propose to model th...
In this paper we discuss the design, acquisition and preprocessing of a Czech audio-visual speech corpus. The corpus is intended for training and testing of existing audio-visual ...
Close-talk headset microphones have been traditionally used for speech acquisition in a number of applications, as they naturally provide a higher signal-to-noise ratio -needed fo...
Iain McCowan, Maganto Hari Krishna, Daniel Gatica-...
This paper presents a plan-based model of dialogue that combines world, linguistic, and contextual knowledge in order to recognize complex communicative actions such as expressing...