15 search results - page 2 / 3 » Transfer Learning for Tandem ASR Feature Extraction |
ICDM
2007
IEEE
13 years 11 months ago
2007
IEEE
The problem of transfer learning, where information gained in one learning task is used to improve performance in another related task, is an important new area of research. While...
CLIN
2001
13 years 6 months ago
2001
The present paper evaluates the role selected features and feature combinations play for error detection in spoken dialogue systems. We investigate the relevance of various, readi...
AAAI
2012
11 years 7 months ago
2012
Knowledge transfer is computationally challenging, due in part to the curse of dimensionality, compounded by source and target domains expressed using different features (e.g., do...
TNN
2011
13 years 6 days ago
2011
Domain adaptation solves a learning problem in a target domain by utilizing the training data in a different but related source domain. Intuitively, discovering a good feature rep...
DAGM
2008
Springer
13 years 7 months ago
2008
Springer
Abstract. In this paper, we propose a new approach to learn structured visual compound models from shape-based feature descriptions. We use captioned text in order to drive the pro...