Sciweavers

10792 search results - page 1917 / 2159
» An Evaluation of Non-Equijoin Algorithms
Sort
View
ICASSP
2010
IEEE
15 years 6 months ago
Boosted binary features for noise-robust speaker verification
The standard approach to speaker verification is to extract cepstral features from the speech spectrum and model them by generative or discriminative techniques. We propose a nov...
Anindya Roy, Mathew Magimai-Doss, Sébastien...
ICASSP
2010
IEEE
15 years 6 months ago
Language recognition using deep-structured conditional random fields
We present a novel language identification technique using our recently developed deep-structured conditional random fields (CRFs). The deep-structured CRF is a multi-layer CRF mo...
Dong Yu, Shizhen Wang, Zahi Karam, Li Deng
ICASSP
2010
IEEE
15 years 6 months ago
Semi-Supervised Fisher Linear Discriminant (SFLD)
Supervised learning uses a training set of labeled examples to compute a classifier which is a mapping from feature vectors to class labels. The success of a learning algorithm i...
Seda Remus, Carlo Tomasi
ICASSP
2010
IEEE
15 years 6 months ago
An improved deviation measure for two-path echo cancellation
—The two-path algorithm is a well-known approach for overcoming the dead-lock problem in echo cancellation systems. Typically, a fixed foreground filter is producing the echo c...
Christian Schüldt, Fredric Lindström, In...
ICASSP
2010
IEEE
15 years 6 months ago
Voice source estimation for artificial bandwidth extension of telephone speech
Artificial bandwidth extension (ABWE) of speech signals aims to estimate wideband speech (50 Hz – 7 kHz) from narrowband signals (300 Hz – 3.4 kHz). Applying the source-filt...
Mark R. P. Thomas, Jon Gudnason, Patrick A. Naylor...
« Prev « First page 1917 / 2159 Last » Next »