A TIME-RESTRICTED SELF-ATTENTION LAYER FOR ASR

Self-attention - an attention mechanism where the input and output sequence lengths are the same - has recently been successfully applied to machine translation, caption generation, and phoneme recognition. In this paper we apply a restricted self-attention mechanism (with multiple heads) to speech recognition. By "restricted" we mean that the mechanism at a particular frame only sees input from a limited number of frames to the left and right. Restricting the context makes it easier to encode the position of the input - we use a 1-hot encoding of the frame offset. We try introducing attention layers into TDNN architectures, and replacing LSTM layers with attention layers in TDNN+LSTM architectures. We show experiments on a number of ASR setups. We observe improvements compared to the TDNN and TDNN+LSTM baselines. Attention layers are also faster than LSTM layers in test time, since they lack recurrence.