Comparison of Image Transform-Based Features for Visual Speech Recognition in Clean and Corrupted Videos

We present results of a study into the performance of a variety of different image transform-based feature types for speaker-independent visual speech recognition of isolated digits. This includes the first reported use of features extracted using a discrete curvelet transform. The study will show a comparison of some methods for selecting features of each feature type and show the relative benefits of both static and dynamic visual features. The performance of the features will be tested on both clean video data and also video data corrupted in a variety of ways to assess each feature type's robustness to potential real-world conditions. One of the test conditions involves a novel form of video corruption we call jitter which simulates camera and/or head movement during recording.

Full-Scale Marine Exposure Tests on Treated and Untreated Concretes Initial 7-Year Results

An extensive chloride profiling program was undertaken on concrete pier stems erected in the vicinity of the Dornoch Bridge located at the Dornoch Firth in Northeast Scotland. The pier stems were 2 m (6.562 ft) high and octagonal in plan with 0.66 m (2.165 ft) wide faces. The piers were constructed in sets of three with the lowest of each set in the tidal zone and the highest in the atmospheric zone. The pier stems were placed in such a way that they would represent the exposure conditions of the actual bridge piers of the Dornoch Bridge. In all, six of the pier stems were made using plain ordinary portland cement (OPC) concrete (with three of these having the surface treated with silane); the remaining three pier stems had a concrete containing caltite as an additive. Three exposurezones were studied: the tidal zone, the splash zone, and the atmospheric zone. The tidal zone was further subdivided into two levels defined as low-level and high-level. Chloride profiles were obtained from the different regimes over a period of 7 years for all nine pier stems. This paper describes the nature of chloride ingress and the usefulness of diffusion parameters in classifying each exposure regimes. Furthermore, the effectiveness of silane and caltite in protecting concrete from chloride ingress in different exposure zones was studied.

Hidden Conditional Random Fields for Visual Speech Recognition

In this paper we present the application of Hidden Conditional Random Fields (HCRFs) to modelling speech for visual speech recognition. HCRFs may be easily adapted to model long range dependencies across an observation sequence. As a result visual word recognition performance can be improved as the model is able to take more of a contextual approach to generating state sequences. Results are presented from a speaker-dependent, isolated digit, visual speech recognition task using comparisons with a baseline HMM system. We firstly illustrate that word recognition rates on clean video using HCRFs can be improved by increasing the number of past and future observations being taken into account by each state. Secondly we compare model performances using various levels of video compression on the test set. As far as we are aware this is the first attempted use of HCRFs for visual speech recognition.