Approximately, 10,000 naturally occurring noun phrases taken from the LOB corpus were used firstly, to evaluate the NP component of the Alvey ANLT grammar (Grover et al., 1987, 19...
Data sparseness is an ever dominating problem in automatic emotion recognition. Using artificially generated speech for training or adapting models could potentially ease this: t...
Anaphora resolution is envisaged in this paper as part of the reference resolution process. A general open architecture is proposed, which can be particularized and configured in ...
Stochastic optimization arising from precoding in a multi-antenna fading channel with channel mean feedback to maximize data rates is important but challenging. The use of relayin...
We propose Cross-Channel Spectral Subtraction (CCSS), a source separation method for recognizing meeting speech where one microphone is prepared for each speaker. The method quick...