Electromagnetic Articulography (Ema) For Real-Time Feedback Application: Computational Techniques

The application of state-of-the-art signal processing often differs between offline and online real-time application domains. Offline processing techniques may be used to accurately reduce signal noise and spot errors before analysis. However, without the global signal information available to offline processes, such techniques can be difficult to reproduce in online real-time applications. This paper presented methods that were developed to support a state-of-the-art computer-based speech therapy system. These methods included online head correction and low-pass filtering and aimed to reproduce offline processing data quality when using a real-time clinical feedback application. The adequacy of these methods was evaluated relative to the offline processing gold' standard and in a context of computing a specific kinematic parameter (i.e. articulatory working space). The results showed that the online real-time output values were highly correlated with the offline manually-processed values.