Small-footprint Keyword Spotting Using Deep Neural Network and Connectionist Temporal Classifier
This is an incremental improvement for keyword spotting on power-constrained mobile devices.
The paper tackled the lack of keyword-specific data for keyword spotting on mobile devices by proposing a system using DNN and CTC, achieving competitive performance without increasing computational complexity.
Mainly for the sake of solving the lack of keyword-specific data, we propose one Keyword Spotting (KWS) system using Deep Neural Network (DNN) and Connectionist Temporal Classifier (CTC) on power-constrained small-footprint mobile devices, taking full advantage of general corpus from continuous speech recognition which is of great amount. DNN is to directly predict the posterior of phoneme units of any personally customized key-phrase, and CTC to produce a confidence score of the given phoneme sequence as responsive decision-making mechanism. The CTC-KWS has competitive performance in comparison with purely DNN based keyword specific KWS, but not increasing any computational complexity.