Recent improvements in SRI's keyword detection system for noisy audio
Julien van Hout, Vikramjit Mitra, Yun Lei, Dimitra Vergyri, Martin Graciarena, Arindam Mandal, Horacio Franco · 2014
We present improvements to a keyword spotting (KWS) system that operates in highly adverse channel conditions with very low signal-to-noise ratio levels. We employ a system combination approach by combining the outputs of multiple large vocabulary continuous speech recognition (LVCSR) systems. These systems are complementary thanks to different design decisions across all levels of information: three speech activity detections systems; a wide range of front-end signal processing features (standard cepstral and filter-bank features, noise-robust features and multi-layer perceptron features); three statistical acoustic model types (Gaussian mixtures models, deep and convolutional neural networks); two keyword search strategies (wordbased and phone-based). We explore the scenario where the