14.00 – 14.05 Welcome by Head of Department Hans Jørgen Andersen
14.05 – 14.50 Inaugural lecture by Professor in Audio Processing Mads Græsbøll Christensen:
“Statistical Parametric Speech Processing: Solving Problems with the Model-Based Approach”
Parametric speech models have been around for many years but have always had their detractors. Two common arguments against such models are that it is too difficult to find their parameters and that the models do not take the complicated nature of real signals into account. In recent years, significant advances have been made in speech models and robust estimation using statistical principles, and it has been demonstrated that, regardless of any deficiencies in the model, the parametric methods outperform the more commonly used non-parametric methods (e.g., autocorrelation-based methods) for problems like pitch estimation. In this talk, state-of-the-art parametric speech models and statistical estimators for finding their parameters will be presented and their pros and cons discussed. The merits of the statistical, parametric approach to speech modeling will be demonstrated by showing how otherwise complicated problems can be solved comparably easily this way. Examples of such problems are pitch estimation for non-stationary speech, distortion-less speech enhancement, noise statistics estimation, speech segmentation, multi-channel modeling, and model-based localization and beamforming with microphone arrays.
14.50 – 15.00 Short break
15.00 – 15.45 Inaugural lecture by Professor in Computer Vision Thomas B. Moeslund:
“A Brief History of Computer Vision and the VAP Lab”
Computer vision is the digital version of human vision, where the eyes are replaced by a camera and the brain is replaced by algorithms implemented in software. Research on computer vision focuses on developing and implementing those algorithms. The aim is not only to replicate a human’s ability to see (human visual perception) but to go beyond that by developing, for example, the ability to see in the dark or measure the distance to an object. One subfield of computer vision is Visual Analysis of People, the focus of which is the automatic camera-based analysis of people and their location. This talk will give a brief introduction to the field of computer vision in general – exemplified by work done in the Visual Analysis of People lab.
16.00 – 17.00 Reception on 2nd floor Rendsburggade 14
Please let us know if you wish to attend by sending a mail to email@example.com no later than May 25th, 2016