Alwin de Rooij | Portfolio

A follow-up on the work we did on the “One-press Control” and “WYTIWYG” projects using a pressure sensitive keyboard will be presented on the CHI 2010 conference which will be held from 10 to 15 april 2010 in Atlanta, GA, USA. The project is accepted for presentation and publication as a work in progress. Next to a poster presentation at the conference the scientific article “One-press Control: A Tactile Input Method for Pressure-Sensitive Computer Keyboards” will be published in the electronic CHI Extended Abstracts Proceedings and the ACM Digital Library. The paper can also be downloaded here.

The project “Inter-Voice Morphing using a neural network based dimensionality reduction technique” is created in collaboration with Tommaso Villanova. In this project we have attempted to set up the first experiments for a novel way to generate and morph voice sounds. In this project we use a special case of a feedforward neural network and train it using a large phoneme dataset. The idea is to encode the phoneme data in the neural network and extract its minimal amount of principal components. After training the neural network is used to construct a synthesizer for voice (phoneme) sounds.

For more information about the preliminary tests go here!

Finished this project about a month ago. Its about retrieving scenes (scenic pictures) from a database using visual information retrieval techniques only. You can just give the program an image you found or took and then the program will try to find similar pictures. The retrieval part uses a variety of techniques and concepts like the perceptually uniform CIE L*A*B* colour space, the Self Organizing Map (Kohonen Neural Networks) and Sobel Edge detection.

For more info, go here!

My research project Genetic Wave Shaping (GWS) is now online and finished. GWS is an algorithm I developed based on the concept of Evolutionary Computation and proposes a solution and natural tool for the difficulties in generating large amounts of user specified timbre characteristics in synthesized sound. Although the project needs further development to optimize efficiency and usability the results are promising. GWS proves to be a potential helpful tool for such tasks.

Online Documentation & Paper