About Me

I am a Mechatronic Engineer, currently working for Cyber Technology WA designing industry leading UAVs and drones. I completed my PhD at Curtin University of Technology in Perth, Western Australia in 2013. I completed my Bachelor of Engineering in Mechatronics with honours in 2005.

Research

This is a summary of research I performed in the area of visual speech recognition, as part of my PhD.

PhD Thesis

The title of my PhD is "Disproving Visemes As The Basic Visual Unit Of Speech".

Visemes are groups of phonemes that are considered visually indistinguishable, but there are many doubts regarding their use in visual speech recognition. In this thesis, a visual speech recogniser is constructed to test the validity of visemes. Examining the phoneme output of the recogniser shows that it is not possible to construct a viseme grouping that exhibits the required phoneme confusion characteristics. This thesis proves that phonemes, not visemes, are the basic visual unit of speech.

Electronic copies of my thesis and supplementary material are available.

Wrapping Snakes

I have developed a technique known as wrapping snakes to extract the lip shape from video frames. The sequence of lip shapes can then be used to recognise the words being spoken.

Wrapping snakes are an adaptation of traditional snakes, where the image forces are modified based on the snakes location and orientation. This modification encourages wrapping snakes to continue along features they have already partially found, overcoming one of the problems of traditional snakes.

More detailed information and animations explaining wrapping snakes is available.

I presented a paper on wrapping snakes at the ICASSP 2009 conference in Taiwan.

Publications

  • Ramage, M 2013, Disproving Visemes As The Basic Visual Unit Of Speech, PhD Thesis, Curtin University (PDF ~5.5 MB).
  • Ramage, M & Lindsay, E 2009, Wrapping Snakes for Improved Lip Segmentation, Proceedings of ICASSP 2009. (PDF ~720 KB).
  • Hearn, L & Ramage, M 2005, Animatronic Puppetry, Unpublished Thesis (B.Eng.), Curtin University of Technology. (PDF ~1.9 MB)