Sciweavers

9455 search results - page 1655 / 1891
» The Modelling Language Zinc
Sort
View
JMLR
2010
106views more  JMLR 2010»
15 years 28 days ago
Why Does Unsupervised Pre-training Help Deep Learning?
Much recent research has been devoted to learning algorithms for deep architectures such as Deep Belief Networks and stacks of auto-encoder variants, with impressive results obtai...
Dumitru Erhan, Yoshua Bengio, Aaron C. Courville, ...
180
Voted
TKDE
2010
161views more  TKDE 2010»
15 years 25 days ago
A Deductive Spreadsheet System for End Users
We exploit the spreadsheet metaphor to make deductive problem-solving methods available to the vast population of spreadsheet end users. In particular, we show how the function-bas...
Marcelo Tallis, Robert M. Balzer
ICASSP
2011
IEEE
14 years 9 months ago
Generating compound words with high order n-gram information in large vocabulary speech recognition systems
In this work we concentrate on generating compound words with high order n-gram information for speech recognition. In most existing compound words generation methods, only bi-gra...
Jie Zhou, Qin Shi, Yong Qin
174
Voted
ICASSP
2011
IEEE
14 years 9 months ago
Forensically inspired approaches to automatic speaker recognition
This paper presents ongoing research leveraging forensic methods for automatic speaker recognition. Some of the methods forensic scientists employ include identifying speaker dist...
Kyu J. Han, Mohamed Kamal Omar, Jason W. Pelecanos...
179
Voted
ICDE
2011
IEEE
232views Database» more  ICDE 2011»
14 years 9 months ago
XClean: Providing valid spelling suggestions for XML keyword queries
—An important facility to aid keyword search on XML data is suggesting alternative queries when user queries contain typographical errors. Query suggestion thus can improve users...
Yifei Lu, Wei Wang, Jianxin Li, Chengfei Liu
« Prev « First page 1655 / 1891 Last » Next »