ELM based algorithms for acoustic template matching in home automation scenarios: Advancements and performance analysis

Abstract

Speech and sound recognition in home automation scenarios has been gaining an increasing interest in the last decade. One interesting approach addressed in the literature is based on the template matching paradigm, which is characterized by ease of implementation and independence on large datasets for system training. Moving from a recent contribution of some of the authors, where an Extreme Learn-ing Machine algorithm was proposed and evaluated, a wider performance analysis in diverse operating conditions is provided here, together with some relevant improvements. These are allowed by the employment of supervector features as input, for the first time used with ELMs, up to the authors’ knowledge. As already verified in other application contexts and with different learning systems, this ensures a more robust characterization of the speech segment to be classified, also in presence of mismatch between training and testing data. The accomplished computer simulations confirm the effectiveness of the approach, with F1-Measure performance up to 99% in the multicondition case, and a computational time reduction factor close to 4, with respect to the SVM counterpart.