96 search results - page 3 / 20 » Lightly supervised and unsupervised acoustic model training |
ICASSP
2010
IEEE
13 years 8 months ago
2010
IEEE
This paper addresses the training of classification trees for weakly labelled data. We call ”weakly labelled data”, a training set such as the prior labelling information pro...
INTERSPEECH
2010
13 years 3 months ago
2010
Log-linear models have recently been used in acoustic modeling for speech recognition systems. This has been motivated by competitive results compared to systems based on Gaussian...
ICPR
2008
IEEE
2008
IEEE
Weakly supervised learning using proportion-based information: An application to fisheries acoustics
14 years 9 months ago
This paper addresses the inference of probabilistic classification models using weakly supervised learning. In contrast to previous work, the use of proportion-based training data...
PRL
2011
13 years 3 months ago
2011
: This paper addresses the inference of probabilistic classification models using weakly supervised learning. The main contribution of this work is the development of learning meth...
ICML
2009
IEEE
14 years 9 months ago
2009
IEEE
Training principles for unsupervised learning are often derived from motivations that appear to be independent of supervised learning. In this paper we present a simple unificatio...