Statistical language models play a major role in current speech recognition systems. Most of these models have focussed on relatively local interactions between words. Recently, h...
Spoken dialogue systemperformance canvary widely fordifferentusers, aswell for the same userduring different dialogues.This paper presents the design and evaluation ofan adaptive v...
Humans are able to recognise a word before its acoustic realisation is complete. This in contrast to conventional automatic speech recognition (ASR) systems, which compute the lik...
We present a novel tracking algorithm that uses dynamic programming to determine the path of target objects and that is able to track an arbitrary number of different objects. The...
Philippe Dreuw, Thomas Deselaers, David Rybach, Da...
Collecting supervised training data for automatic speech recognition (ASR) systems is both time consuming and expensive. In this paper we use the notion of virtual evidence in a g...