Negative transfer in training of acoustic models for automatic speech recognition has been
reported in several contexts such as domain change or speaker characteristics. This paper …

Huge amounts of digital videos are being produced and broadcast every day, leading to
giant media archives. Effective techniques are needed to make such data accessible further …

This paper presents a new method for the discovery of latent domains in diverse speech
data, for the use of adaptation of Deep Neural Networks (DNNs) for Automatic Speech …

Speech recognition systems are often highly domain dependent, a fact widely reported in
the literature. However the concept of domain is complex and not bound to clear criteria …

The performance of video genre classification approaches strongly depends on the selected
feature set. Feature selection requires for expert knowledge and is commonly driven by the …

Video analytics refers to the process of automatically analysing a video for spatial and
temporal events. Effective video analytics require exploitation of genre-related information …

This paper presents the most recent developments of the webASR service (www. webasr.
org), the world's first web–based fully functioning automatic speech recognition platform for …

This paper presents a method for the classification of animated video that does not rely on
hue or saturation information, and aims to achieve a high level of performance in the context …

This paper proposes a framework for performing adaptation to complex and non-stationary
background conditions in Automatic Speech Recognition (ASR) by means of asynchronous …

In this paper, we propose an effective way for combining the discriminative and generative
models for emotion recognition from speech signal. Finding an efficient feature extraction …