Sciweavers

191 search results - page 21 / 39
» Adding Weight to DL-Lite
Sort
View
TSD
2010
Springer
14 years 8 months ago
Using Gradient Descent Optimization for Acoustics Training from Heterogeneous Data
In this paper, we study the use of heterogeneous data for training of acoustic models. In initial experiments, a significant drop of accuracy has been observed on in-domain test s...
Martin Karafiát, Igor Szöke, Jan Cerno...
ICPR
2010
IEEE
14 years 7 months ago
Automatic Music Genre Classification Using Bass Lines
A bass line is an instrumental melody that encapsulates both rhythmic, melodic, and harmonic features and arguably contains sufficient information for accurate genre classificatio...
Umut Simsekli
ICDE
2008
IEEE
122views Database» more  ICDE 2008»
15 years 11 months ago
On Signatures for Communication Graphs
Abstract-- Communications between individuals can be represented by (weighted, multi-) graphs. Many applications operate on communication graphs associated with telephone calls, em...
Graham Cormode, Flip Korn, S. Muthukrishnan, Yihua...
ICMCS
2005
IEEE
90views Multimedia» more  ICMCS 2005»
15 years 3 months 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
TREC
1998
14 years 11 months ago
Spoken Document Retrieval For TREC-7 At Cambridge University
This paper presents work done at Cambridge University, on the TREC7 Spoken Document Retrieval (SDR) Track. The broadcast news audio was transcribed using a 2-pass gender-dependent...
Sue E. Johnson, P. Jourlin, G. L. Moore, Karen Spa...