Speaker: William Fernando López Gavilánez.
Abstract: The deployment process of Keyword Spotting (KWS) models depends on the target hardware, it normally includes merging components in a black box, binarization, quantization, and/or mobile optimization. In addition, while processing a continuous stream of audio in real time, the model normally yields a sequence of posteriors that must be processed. In this work, we make optimization of the feature extraction for making the model work in heterogeneous devices. In addition, we constructed a test to simulate stream processing in to evaluate the model’s real behavior in the end device.