Using Dual-Element Microphone Arrays for Automatic Keyword Recognition

摘要

This paper proposes a practical acoustic keyword recognition technique for robust automatic speech recognition, suitable for use under various interference conditions. This technique consists of a dual microphone array and an algorithm for processing their signals. A first-order microphone array consists of two closely spaced omnidirectional microphones. The microphone array is placed in the workplace of the target speaker. Signal processing algorithms allow to detect the target speaker's speech and extract it in a noisy environment. Experiments with real recordings demonstrate the reduction of speech recognition errors for the target speaker due to suppression of diffuse noise. The main advantage of the proposed technique is simplicity of its use in a wide range of practical situations.