A robust speech detection algorithm for speech activated hands-free applications

This paper describes a novel noise robust speech detection algorithm that can operate reliably in severe noisy car conditions. High performance has been obtained with the following techniques: (1) noise suppression based on principal component analysis for pre-processing, (2) robust endpoint detection using dynamic parameters, and (3) speech verification using the periodicity of voiced signals with harmonic enhancement. Noise suppression improves the SNR as compared with nonlinear spectrum subtraction by about 20 dB. This makes the endpoint detection operate reliably in SNRs down to -10 dB. In car environments, road bump noises are problematic for speech detectors causing mis-detection errors. Speech verification helps to remove these errors. This technology is being used in Sony car navigation products.