Sciweavers

801 search results - page 56 / 161
» The Inefficiency of Batch Training for Large Training Sets
Sort
View
ICDAR
2005
IEEE
14 years 2 months ago
IAM-OnDB - an On-Line English Sentence Database Acquired from Handwritten Text on a Whiteboard
In this paper we present IAM-OnDB - a new large online handwritten sentences database. It is publicly available and consists of text acquired via an electronic interface from a wh...
Marcus Liwicki, Horst Bunke
ICMCS
2005
IEEE
92views Multimedia» more  ICMCS 2005»
14 years 2 months ago
Semi-supervised meeting event recognition with adapted HMMs
This paper investigates the use of unlabeled data to help labeled data for audio-visual event recognition in meetings. To deal with situations in which it is difficult to collect...
Dong Zhang, Daniel Gatica-Perez, Samy Bengio
CANDC
2007
ACM
14 years 25 days ago
Software for systematic and imaginative exploration
This paper describes a software system that has been designed to enhance individual creativity. It was once thought that the era of information visualization would empower people ...
Daryl H. Hepting
ACL
2008
13 years 10 months ago
Classification of Semantic Relationships between Nominals Using Pattern Clusters
There are many possible different semantic relationships between nominals. Classification of such relationships is an important and difficult task (for example, the well known nou...
Dmitry Davidov, Ari Rappoport
NIPS
2008
13 years 10 months ago
Correlated Bigram LSA for Unsupervised Language Model Adaptation
We present a correlated bigram LSA approach for unsupervised LM adaptation for automatic speech recognition. The model is trained using efficient variational EM and smoothed using...
Yik-Cheung Tam, Tanja Schultz