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

The scarcity of emotional speech data is a bottleneck of developing automatic speech emotion recognition (ASER) systems. One way to alleviate this issue is to use unsupervised feature learning techniques to learn features from the widely available general speech and use these features to train emotion classifiers. These unsupervised methods, such as denoising autoencoder (DAE), variational autoencoder (VAE), adversarial autoencoder (AAE) and adversarial variational Bayes (AVB), can capture the intrinsic structure of the data distribution in the learned feature representation.

Robustness to errors produced by automatic speech recognition (ASR) is essential for Spoken Language Understanding (SLU). Traditional robust SLU typically needs ASR hypotheses with semantic annotations for training. However, semantic annotation is very expensive, and the corresponding ASR system may change frequently. Here, we propose a novel unsupervised ASR-error adaptation method, obviating the need of annotated ASR hypotheses.

Embedding textured images in manifolds reveals latent information regarding texture structure and allows useful analysis of these high dimensional images in a low dimensional space. We present a framework for analysis and synthesis of natural stochastic textures (NST) which constitute an important subset of textures that are modelled as realizations of random processes. The randomness of NST differentiates them from other types of images and requires a dedicated method for analysis and synthesis. We demonstrate several applications of this framework.

Convolutional sparse representations allow modeling an entire image as an alternative to the more common independent patch-based
formulations. Although many approaches have been proposed to efficiently solve the convolutional dictionary learning (CDL) problem,
their computational performance is constrained by the dictionary update stage. In this work, we include two improvements to existing

Spectrum sensing in heterogeneous networks is very challenging as it usually requires a large number of static secondary users (SUs) to obtain the global spectrum states. In this paper, we tackle the spectrum sensing in heterogeneous networks from a new perspective. We exploit the mobility of multiple SUs to simultaneously collect spatial-temporal spectrum sensing data. Then, we propose a novel non-parametric Bayesian learning model, referred to as beta process hidden Markov model to capture the spatio-temporal correlation in the collected spectrum data.