Sciweavers

3477 search results - page 596 / 696
» From Tables to Frames
Sort
View
ICASSP
2011
IEEE
14 years 10 months ago
Language-independent constrained cepstral features for speaker recognition
Constrained cepstral systems, which select frames to match various linguistic “constraints” in enrollment and test, have shown significant improvements for speaker verificatio...
Elizabeth Shriberg, Andreas Stolcke
175
Voted
ICASSP
2011
IEEE
14 years 10 months ago
Sub-Nyquist sampling of short pulses
—We develop sub-Nyquist sampling systems for analog signals comprised of several, possibly overlapping, finite duration pulses with unknown shapes and time positions. Efficient...
Ewa Matusiak, Yonina C. Eldar
ICASSP
2011
IEEE
14 years 10 months ago
A distance-based slice interleaving scheme for robust video transmission over error-prone networks
Video transmission over wireless networks suffers from packet loss due to either temporary packet drop or fadinginduced bit errors. To ensure that the quality of the decoded video...
Yu Wang, Jo Yew Tham, Kwong Huang Goh, Wei Siong L...
177
Voted
ICASSP
2011
IEEE
14 years 10 months ago
SEAMLESS P2P-MDVC with well-balanced descriptions
Multiple-description coding (MDC) provides a promising solution to support the error-prone transmission over multiple channels. One extremely important application is to design ef...
Shuyuan Zhu, Jeff Siu-Kei Au-Yeung, Bing Zeng
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...