Speech recognition system in high noise background based on discriminative learning of environmental features

A robust speech recognition system based on the discriminative learning of environmental features was proposed for the recognition of environmental features in high noise background, and a gradient descent algorithm was adopted for the parameters optimization. Experiments were carried out at different levels of background noise for SNR, basic accuracy, noise-resistance and system environment adaptability. The experimental results show that the system has good recognition performance in high noisy environments. The system can meet different needs of application.