Sciweavers

37 search results - page 1 / 8
» An Integrated Model for Evaluating the Amount of Data Requir...
Sort
View
ACCV
1995
Springer
13 years 10 months ago
An Integrated Model for Evaluating the Amount of Data Required for Reliable Recognition
—Many recognition procedures rely on the consistency of a subset of data features with a hypothesis as the sufficient evidence to the presence of the corresponding object. We ana...
Michael Lindenbaum
ICMCS
2005
IEEE
90views Multimedia» more  ICMCS 2005»
14 years 19 days ago
Integrating co-training and recognition for text detection
Training a good text detector requires a large amount of labeled data, which can be very expensive to obtain. Cotraining has been shown to be a powerful semi-supervised learning t...
Wen Wu, Datong Chen, Jie Yang
SPEECH
2010
136views more  SPEECH 2010»
13 years 5 months ago
Robust speech recognition by integrating speech separation and hypothesis testing
Missing data methods attempt to improve robust speech recognition by distinguishing between reliable and unreliable data in the time-frequency domain. Such methods require a binar...
Soundararajan Srinivasan, DeLiang L. Wang
LRE
2006
173views more  LRE 2006»
13 years 7 months ago
Automatic induction of language model data for a spoken dialogue system
When building a new spoken dialogue application, large amounts of domain specific data are required. This paper addresses the issue of generating in-domain training data when litt...
Chao Wang, Grace Chung, Stephanie Seneff
MOBISYS
2009
ACM
14 years 7 months ago
SolarStore: enhancing data reliability in solar-powered storage-centric sensor networks
In this paper, we present a reliable storage service, called SolarStore, that adaptively trades-off storage reliability versus energy consumption in solar-powered sensor networks....
Yong Yang, Lili Wang, Dong Kun Noh, Hieu Khac Le, ...