198 search results - page 1 / 40 » From flat direct models to segmental CRF models |
ICASSP
2010
IEEE
13 years 5 months ago
2010
IEEE
This paper summarizes recent work at Microsoft on the development of novel direct models. The key characteristic of our approaches is the use of long-span segment level features t...
ICASSP
2010
IEEE
13 years 5 months ago
2010
IEEE
This paper addresses the problem of developing appropriate features for use in direct modeling approaches to speech recognition, such as those based on Maximum Entropy models or S...
CVPR
2011
IEEE
12 years 8 months ago
2011
IEEE
Simultaneously segmenting and labeling images is a fundamental problem in Computer Vision. In this paper, we introduce a hierarchical CRF model to deal with the problem of labelin...
ICASSP
2009
IEEE
13 years 11 months ago
2009
IEEE
We introduce a direct model for speech recognition that assumes an unstructured, i.e., flat text output. The flat model allows us to model arbitrary attributes and dependences o...
ACL
2010
13 years 2 months ago
2010
This paper presents a joint optimization method of a two-step conditional random field (CRF) model for machine transliteration and a fast decoding algorithm for the proposed metho...