An Analysis of “Attention” in Sequence-to-Sequence Models

In this paper, we conduct a detailed investigation of attention-based models for automatic speech recognition (ASR). First, we explore different types of attention, including “online” and “full-sequence” attention. Second, we explore different subword units to see how much of the end-to-end ASR process can reasonably be captured by an attention model. In experimental evaluations, we find that although attention is typically focused over a small region of the acoustics during each step of next label prediction, “full-sequence” attention outperforms “online” attention, although this gap can be significantly reduced by increasing the length of the segments over which attention is computed. Furthermore, we find that context-independent phonemes are a reasonable sub-word unit for attention models. When used in the second-pass to rescore N-best hypotheses, these models provide over a 10% relative improvement in word error rate.