344 search results - page 56 / 69 » speech 2011 |
ICASSP
2011
IEEE
14 years 1 months ago
2011
IEEE
Model M, a novel class-based exponential language model, has been shown to significantly outperform word n-gram models in state-of-the-art machine translation and speech recognit...
ICASSP
2011
IEEE
14 years 1 months ago
2011
IEEE
Neural networks are a useful alternative to Gaussian mixture models for acoustic modeling; however, training multilayer networks involves a difficult, nonconvex optimization that...
ICASSP
2011
IEEE
14 years 1 months ago
2011
IEEE
Spoken dialogue systems are gaining popularity with improvements in speech recognition technologies. Dialogue systems can be modeled effectively using POMDPs, achieving improvemen...
ICASSP
2011
IEEE
14 years 1 months ago
2011
IEEE
This paper presents a novel method for reducing the dimensionality of kernel spaces. Recently, to maintain the convexity of training, loglinear models without mixtures have been u...
118
click to vote
ICASSP
2011
IEEE
14 years 1 months ago
2011
IEEE
This paper presents a semantic confidence measure that aims to predict the relevance of automatic transcripts for a task of Spoken Document Retrieval (SDR). The proposed predicti...