Sciweavers

2765 search results - page 456 / 553
» Works and representation
Sort
View
INTERSPEECH
2010
15 years 25 days ago
Towards a robust face recognition system using compressive sensing
An application of compressive sensing (CS) theory in imagebased robust face recognition is considered. Most contemporary face recognition systems suffer from limited abilities to ...
Allen Y. Yang, Zihan Zhou, Yi Ma, Shankar Sastry
INTERSPEECH
2010
15 years 25 days ago
FSM-based pronunciation modeling using articulatory phonological code
According to articulatory phonology, the gestural score is an invariant speech representation. Though the timing schemes, i.e., the onsets and offsets, of the gestural activations...
Chi Hu, Xiaodan Zhuang, Mark Hasegawa-Johnson
JMLR
2010
112views more  JMLR 2010»
15 years 25 days ago
Reduced-Rank Hidden Markov Models
Hsu et al. (2009) recently proposed an efficient, accurate spectral learning algorithm for Hidden Markov Models (HMMs). In this paper we relax their assumptions and prove a tighte...
Sajid M. Siddiqi, Byron Boots, Geoffrey J. Gordon
TOG
2010
121views more  TOG 2010»
15 years 22 days ago
Data-driven image color theme enhancement
It is often important for designers and photographers to convey or enhance desired color themes in their work. A color theme is typically defined as a template of colors and an as...
Baoyuan Wang, Yizhou Yu, Tien-Tsin Wong, Chun Chen...
ICASSP
2011
IEEE
14 years 9 months ago
Jump Function Kolmogorov for overlapping audio event classification
This paper presents a novel method for audio event classi cation in overlapping conditions. The method is based on Jump Function Kolmogorov (JFK), a stochastic representation, whi...
Tran Huy Dat, Haizhou Li