We study how potential attackers can identify accounts on different social network sites that
all belong to the same user, exploiting only innocuous activity that inherently comes with …

The proliferation of social networks and all the personal data that people share brings many
opportunities for develo** exciting new applications. At the same time, however, the …

Class posterior distributions can be used to classify or as intermediate features, which can
be further exploited in different classifiers (eg, Gaussian Mixture Models, GMM) towards …

Automatic speech recognition (ASR) is an application of pattern recognition and machine
learning, in which the speech recognizer learns to map acoustic features representing …

There are several thousand languages in the world and each language has a multitude of
dialects. State-of-the-art speech recognition techniques, which are usually based on …

We present a theoretical investigation into the use of normalised artificial neural network
(ANN) outputs in the context of hidden Markov models (HMMs). The work is motivated by the …

In recent works, the use of phone class-conditional posterior probabilities (posterior
features) directly as features provided successful results in template-based ASR systems. In …

We investigate the invariance of posterior features estimated using MLP trained on auxiliary
corpus towards different data condition and different distance measures for matching …