Sciweavers

3481 search results - page 366 / 697
» A New Approach to Component Testing
Sort
View
TCSV
2002
124views more  TCSV 2002»
15 years 6 months ago
Fast and automatic video object segmentation and tracking for content-based applications
The new video-coding standard MPEG-4 enables content-based functionality, as well as high coding efficiency, by taking into account shape information of moving objects. A novel alg...
Changick Kim, Jenq-Neng Hwang
INFORMATICALT
2010
151views more  INFORMATICALT 2010»
15 years 5 months ago
The Use of Group Delay Features of Linear Prediction Model for Speaker Recognition
Abstract. New text independent speaker identification method is presented. Phase spectrum of allpole linear prediction (LP) model is used to derive the speech features. The featur...
Algirdas Bastys, Andrej Kisel, Bernardas Salna
ICIP
2010
IEEE
15 years 4 months ago
Pyramidal segmentation using higher-order local auto-correlations and its applications to Landsat forestry data
The goal of image segmentation is to partition an image into regions that are internally homogeneous and heterogeneous with respect to neighbouring regions. Recently, a link shifti...
Milos Stojmenovic, Takumi Kobayashi, Nobuyuki Otsu
INTERSPEECH
2010
15 years 1 months ago
Dynamic model selection for spectral voice conversion
Statistical methods for voice conversion are usually based on a single model selected in order to represent a tradeoff between goodness of fit and complexity. In this paper we ass...
Pierre Lanchantin, Xavier Rodet
JMLR
2010
106views more  JMLR 2010»
15 years 1 months 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, ...