Sciweavers

54 search results - page 2 / 11
» A new HMM training and testing scheme
Sort
View
PRL
2000
148views more  PRL 2000»
13 years 5 months ago
One-dimensional representation of two-dimensional information for HMM based handwriting recognition
: In this study, we introduce a set of one-dimensional features to represent two dimensional shape information for HMM (Hidden Markov Model) based handwritten optical character rec...
Nafiz Arica, Fatos T. Yarman-Vural
ICIAR
2009
Springer
13 years 10 months ago
Abnormal Behavior Recognition Using Self-Adaptive Hidden Markov Models
A self-adaptive Hidden Markov Model (SA-HMM) based framework is proposed for behavior recognition in this paper. In this model, if an unknown sequence cannot be classified into an...
Jun Yin, Yan Meng
ICASSP
2008
IEEE
13 years 11 months ago
Text-independent voice conversion based on state mapped codebook
Voice conversion has become more and more important in speech technology, but most of current works have to use parallel utterances of both source and target speaker as the traini...
Meng Zhang, Jianhua Tao, Jilei Tian, Xia Wang
ISM
2006
IEEE
187views Multimedia» more  ISM 2006»
13 years 11 months ago
Camera View-Based American Football Video Analysis
We present a top-down statistical modeling approach to explore the semantic structure in the American football video. First, a semantic space is defined where the video semantic ...
Yi Ding, Guoliang Fan
ICASSP
2011
IEEE
12 years 9 months ago
Automatic speech recognition using Hidden Conditional Neural Fields
Hidden Conditional Random Fields(HCRF) is a very promising approach to model speech. However, because HCRF computes the score of a hypothesis by summing up linearly weighted featu...
Yasuhisa Fujii, Kazumasa Yamamoto, Seiichi Nakagaw...