Deep Learning for Audio and Video Signal Processing

Description and objectives

The Master in Deep Learning for Audio and Video Signal Processing is motivated by the recent huge interest in Deep Neural Networks. The results achieved by these techniques to solve problems related to automatic analysis of acoustic and visual signals have largely exceeded the results achieved by previous techniques, which has meant an unprecedented qualitative change in recent years. This situation has created an academic and professional demand for human resources capable of designing, developing and applying Deep Learning technologies. As a result of this growing interest, large technology companies have created specialized divisions that apply Deep Learning to the acoustic / visual field, such as Amazon, Apple, Google, Microsoft, Facebook and NVIDIA.

The objective of this Master's degree is to train researchers in the specific field of Deep Learning and, more specifically, in the plethora of variants and architectures resulting from the application of these techniques to acoustic and visual signals. The academic programme has a highly applied orientation, typical of a field closely linked to transfer and entrepreneurship actions.

Candidates:

Engineers or candidates in possession of a bachelor's degree in Engineering Areas related to ICT (Information and Communication Technologies).

Professional Profile:

Graduates of this master’ degree are expected to be employed in ICT and technology related roles, which have become ubiquitous in many sectors. Although employment statistics are not available for this master’ degree, popular job portals and international organizations indicate that there is a clear shortage of professionals in the areas covered by the master (deep learning, audio and visual processing).