167 search results - page 15 / 34 » Continuous Audio-Visual Speech Recognition |
ICASSP
2009
IEEE
15 years 6 months ago
2009
IEEE
This paper addresses selecting between candidate pronunciations for out-of-vocabulary words in speech processing tasks. We introduce a simple, unsupervised method that outperforms...
INTERSPEECH
2010
14 years 6 months ago
2010
Neural network language models (NNLM) have become an increasingly popular choice for large vocabulary continuous speech recognition (LVCSR) tasks, due to their inherent generalisa...
SPEECH
2008
14 years 11 months ago
2008
In this paper, we propose a new approach for extracting and representing prosodic features directly from the speech signal. We hypothesize that prosody is linked to linguistic uni...
115
click to vote
ECAI
2008
Springer
15 years 1 months ago
2008
Springer
Abstract. The paper presents an implemented model for priming speech recognition, using contextual information about salient entities. The underlying hypothesis is that, in human-r...
UIST
1995
ACM
15 years 3 months ago
1995
ACM
We describe the Informediatm News-on-Demand system. News-on-Demand is an innovative example of indexing and searching broadcast video and audio material by text content. The fully...