A Feature Extraction Method Based on Discriminative and Adaptive Bottleneck Deep Belief Network in Large Vocabulary Continuous Speech Recognition System

In order to further improve the robustness and recognition rate of bottleneck deep belief network in Large Vocabulary Continuous Speech Recognition system, this paper presented a novel bottleneck deep belief network to extract new features which was based on speaker adaptation and discriminative training. Firstly, a bottleneck deep belief network was adopted to get the feature，thus discriminative training performed on this basis which gave a more distinguished network to improve the recognition accuracy. Simultaneously, a more robust speaker adaptation method was introduced to adjust the network. The proposed method was tested on several public continuous speech databases with strong noise and casual themes and a relative 6.9% promotion of the recognition accuracy was obtained. The result proves the superiority of the proposed method compared to the conventional one.