Sciweavers

7720 search results - page 1160 / 1544
» Motion signal processing
Sort
View
ICASSP
2011
IEEE
14 years 10 months ago
Discriminatively estimated discrete, parametric and smoothed-discrete duration models for speech recognition
Duration of phonemic segments provide important cues for distinguishing words in languages such as Arabic. Recently, we proposed a discriminatively estimated joint acoustic, durat...
Maider Lehr, Izhak Shafran
ICASSP
2011
IEEE
14 years 10 months ago
Topic-sensitive interactive image object retrieval with noise-proof relevance feedback
One current direction to enhance the search accuracy in visual object retrieval is to reformulate the original query through (pseudo-)relevance feedback, which augments a query wi...
Jen-Hao Hsiao, Henry Chang
ICASSP
2011
IEEE
14 years 10 months ago
An approximate Minimum MOSPA estimator
Optimizing over a variant of the Mean Optimal Subpattern Assignment (MOSPA) metric is equivalent to optimizing over the track accuracy statistic often used in target tracking benc...
David Frederic Crouse, Peter Willett, Marco Guerri...
ICASSP
2011
IEEE
14 years 10 months ago
Integrating frame-based and segment-based dynamic time warping for unsupervised spoken term detection with spoken queries
Rapidly increasing quantities of multimedia and spoken content today demand fast and accurate retrieval approaches for convenient browsing. The spoken documents with wide variety ...
Chun-an Chan, Lin-Shan Lee
ICASSP
2011
IEEE
14 years 10 months ago
Deep Belief Networks using discriminative features for phone recognition
Deep Belief Networks (DBNs) are multi-layer generative models. They can be trained to model windows of coefficients extracted from speech and they discover multiple layers of fea...
Abdel-rahman Mohamed, Tara N. Sainath, George Dahl...
« Prev « First page 1160 / 1544 Last » Next »