Sciweavers

700 search results - page 129 / 140
» Transducing Markov sequences
Sort
View
INTERSPEECH
2010
13 years 1 months ago
Deep-structured hidden conditional random fields for phonetic recognition
We extend our earlier work on deep-structured conditional random field (DCRF) and develop deep-structured hidden conditional random field (DHCRF). We investigate the use of this n...
Dong Yu, Li Deng
VLSISP
2010
191views more  VLSISP 2010»
13 years 1 months ago
Sign Language Phoneme Transcription with Rule-based Hand Trajectory Segmentation
A common approach to extract phonemes of sign language is to use an unsupervised clustering algorithm to group the sign segments. However, simple clustering algorithms based on dis...
W. W. Kong, Surendra Ranganath
CORR
2011
Springer
165views Education» more  CORR 2011»
13 years 1 months ago
On the Semantics of Purpose Requirements in Privacy Policies
Privacy policies often place requirements on the purposes for which a governed entity may use personal information. For example, regulations, such as HIPAA, require that hospital ...
Michael Carl Tschantz, Anupam Datta, Jeannette M. ...
ICASSP
2011
IEEE
12 years 10 months ago
Learning and inference algorithms for partially observed structured switching vector autoregressive models
We present learning and inference algorithms for a versatile class of partially observed vector autoregressive (VAR) models for multivariate time-series data. VAR models can captu...
Balakrishnan Varadarajan, Sanjeev Khudanpur
ICASSP
2011
IEEE
12 years 10 months ago
Optimal structure of memory models for lossless compression of binary image contours
In this paper we study various chain codes, which are representations of binary image contours, in terms of their ability to compress in the best way the contour information using...
Ioan Tabus, Septimia Sarbu