Sorry, you need to enable JavaScript to visit this website.

Many state-of-the-art solutions for the understanding of speech data
have in common to be probabilistic and to rely on machine learning
algorithms to train their models from large amount of data. The
difficulty remains in the cost of collecting and annotating such data.
Another point is the time for updating an existing model to a new domain.
Recent works showed that a zero-shot learning method allows
to bootstrap a model with good initial performance. To do so, this
method relies on exploiting both a small-sized ontological description

Many image retrieval systems adopt the bag-of-words model and rely on matching of local descriptors. However, these descriptors of keypoints, such as SIFT, may lead to false matches, since they do not consider the contextual information of the keypoints. In this paper, we incorporate the cues of meaningful regions where local descriptors are extracted. We describe a matching region estimation (MRE) method to find appropriate matching regions for local descriptor matching pairs.

In practical situations, the emotional speech utterances are often collected from different devices and conditions, which will obviously affect the recognition performance. To address this issue, in this paper, a novel transfer non-negative matrix factorization (TNMF) method is presented for cross-corpus speech emotion recognition. First, the NMF algorithm is adopted to learn a latent common feature space for the source and target datasets.

In this presentation, we present an improved set-membership partial-update
affine projection (I-SM-PUAP) algorithm, aiming at
accelerating the convergence, and decreasing the update rates
and the computational complexity of the set-membership
partial-update affine projection (SM-PUAP) algorithm. To
meet these targets, we constrain the weight vector perturbation
to be bounded by a hypersphere instead of the threshold
hyperplanes as in the standard algorithm. We use the distance
between the present weight vector and the expected update

In a video surveillance system with static cameras, object segmentation often fails when part of the object has similar color with the background, resulting in poor performance of the subsequent object tracking. Multiple kernels have been utilized in object tracking to deal with occlusion, but the performance still highly depends on segmentation.

We propose sequential Monte Carlo (SMC) methods for state-space models. The latent processes represent correlated mixtures of fractional Gaussian processes embedded in white Gaussian noises and the observed data are nonlinear functions of the latent states.