Wake-up-word spotting for mobile systems
Andreas Zehetner, Martín Hagmüller, Franz Pernkopf · 2014
Wake-up-word (WUW) spotting for mobile devices has at-tracted much attention recently. The aim is to detect the oc-currence of very few or only one personalized keyword in a continuous potentially noisy audio signal. The application in personal mobile devices is to activate the device or to trigger an alarm in hazardous situations by voice. In this paper, we present a low-resource approach and results for WUW spot-ting based on template matching using dynamic time warp-ing and other measures. The recognition of the WUW is per-formed by a combination of distance measures based on a simple background noise level classification. For evaluation we recorded a WUW spotting database with three different background noise levels, four different speaker distances to the microphone, and ten different speakers. It consists of 480 keywords embedded in continuous audio data.