Reverberant Speech Recognition Combining Deep Neural Networks and Deep Autoencoders

We propose an approach to reverberant speech recognition adopting deep learning in front end as well as back end of the system. At the front end, we adopt a deep autoencoder for enhancing the speech feature parameters, and the recognition is performed using a DNN-HMM acoustic models trained on multi-condition data. The system was evaluated through the ASR task in Chime Challenge 2014. The DNN-HMM system trained on the multi-condition training set achieved a conspicuously higher word accuracy compared to the MLLR-adapted GMM-HMM system trained on the same data. Furthermore, feature enhancement with the deep autoencoder contributed to the improvement of recognition accuracy especially in the more adverse conditions. When the DNN-HMM was used without the deep autoencoder front end, it resulted in a better performance than the non-adapted GMM-HMM system, but was not as good as the adapted GMM-HMM system. However, it outperformed the adapted GMM-HMM system when combined with the deep autoencoder.