Statistical machine translation (SMT) systems for spoken languages suffer from conversational speech phenomena, in particular, the presence of speech dis uencies. We examine the i...
We investigate the automatic labelling of “events” from an audio recording of a sports game. We describe a technique that utilises a hierarchy of language models, which are a ...
In our days knowledge extraction methods are able to produce artifacts (also called patterns) that concisely represent data. Patterns are usually quite heterogeneous and require a...
Human expressive interactions are characterized by an ongoing unfolding of verbal and nonverbal cues. Such cues convey the interlocutor’s emotional state which is continuous and...
This paper considers application of Deep Belief Nets (DBNs) to natural language call routing. DBNs have been successfully applied to a number of tasks, including image, audio and ...
Ruhi Sarikaya, Geoffrey E. Hinton, Bhuvana Ramabha...