Long short-term memory based convolutional recurrent neural networks for large vocabulary speech recognition

Long short-term memory (LSTM) recurrent neural networks (RNNs) have been shown to give state-of-the-art performance on many speech recognition tasks, as they are able to provide the learned dynamically changing contextual window of all se- quence history. On the other hand, the convolutional neural net- works (CNNs) have brought significant improvements to deep feed-forward neural networks (FFNNs), as they are able to bet- ter reduce spectral variation in the input signal. In this paper, a network architecture called as convolutional recurrent neural network (CRNN) is proposed by combining the CNN and L- STM RNN. In the proposed CRNNs, each speech frame, with- out adjacent context frames, is organized as a number of local feature patches along the frequency axis, and then a LSTM net- work is performed on each feature patch along the time axis. We train and compare FFNNs, LSTM RNNs and the proposed LST- M CRNNs at various number of configurations. Experimental results show that the LSTM CRNNs can exceed state-of-the-art speech recognition performance. Copyright ? 2015 ISCA.EI3219-32232015-Januar