1585 search results - page 35 / 317 » Using a Non-prior Training Active Feature Model |
123
click to vote
INTERSPEECH
2010
14 years 8 months ago
2010
In an attempt to improve models of human perception, the recognition of phonemes in nonsense utterances was predicted with automatic speech recognition (ASR) in order to analyze i...
107
click to vote
NLPRS
2001
Springer
15 years 6 months ago
2001
Springer
This paper proposes a method to resolve Japanese zero pronouns by identifying their antecedents. Our method uses a probabilistic model, which is decomposed into syntactic and sema...
116
Voted
ICCV
2009
IEEE
14 years 11 months ago
2009
IEEE
This paper proposes a learnt data-driven approach for accurate, real-time tracking of facial features using only intensity information. Constraints such as a-priori shape models o...
122
click to vote
SDM
2008
SIAM
15 years 3 months ago
2008
SIAM
Bayesian text classifiers face a common issue which is referred to as data sparsity problem, especially when the size of training data is very small. The frequently used Laplacian...
111
click to vote
ICASSP
2010
IEEE
15 years 2 months ago
2010
IEEE
In this study, a system that discriminates laughter from speech by modelling the relationship between audio and visual features is presented. The underlying assumption is that thi...