Sciweavers

421 search results - page 52 / 85
» CSL
Sort
View
CSL
2007
Springer
14 years 9 months ago
'Early recognition' of polysyllabic words in continuous speech
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...
Odette Scharenborg, Louis ten Bosch, Lou Boves
CSL
2007
Springer
14 years 9 months ago
Stochastic and syntactic techniques for predicting phrase breaks
Determining the position of breaks in a sentence is a key task for a text-to-speech (TTS) system. We describe some methods for phrase break prediction in which the whole sentence ...
Ian Read, Stephen Cox
CSL
2007
Springer
14 years 9 months ago
Discriminative n-gram language modeling
This paper describes discriminative language modeling for a large vocabulary speech recognition task. We contrast two parameter estimation methods: the perceptron algorithm, and a...
Brian Roark, Murat Saraclar, Michael Collins
CSL
2004
Springer
14 years 9 months ago
Arc minimization in finite-state decoding graphs with cross-word acoustic context
Recent approaches to large vocabulary decoding with finite state graphs have focused on the use of state minimization algorithms to produce relatively compact graphs. This paper e...
François Yvon, Geoffrey Zweig, George Saon
CSL
2004
Springer
14 years 9 months ago
Lexical knowledge and human disagreement on a WSD task
This paper explores factors correlating with lack of inter-annotator agreement on a word sense disambiguation (WSD) task taken from SENSEVAL-2. Twenty-seven subjects were given a ...
G. Craig Murray, Rebecca Green