Multi-microphone speech recognition in everyday environments

摘要

Multi-microphone signal processing techniques have the potential to greatly improve the robustness of speech recognition (ASR) in distant microphone settings. However, in everyday environments, typified by complex non-stationary noise backgrounds, designing effective multi-microphone speech recognition systems is nontrivial. In particular, optimal performance requires the tight integration of the front-end signal processing and the back-end statistical speech and noise source modeling. The best way to achieve this in a modern deep learning speech recognition framework remains unclear. Further, variability in microphone array design - and consequent lack of real training data for any particular configuration - may mean that systems have to be able to generalize from audio captured using mismatched microphone geometries or produced using simulation.