Transformer has shown promising results in many sequence to sequence
transformation tasks recently. It utilizes a number of feed-forward
self-attention layers to replace the recurrent neural networks (RNN) in
attention-based encoder decoder (AED) architecture. Self-attention layer learns
temporal dependence by incorporating sinusoidal positional embedding of tokens
in a sequence for parallel computing. Quicker iteration speed in training than
sequential operation of RNN can be obtained. Deeper layers of the transformer
also make it perform better than RNN-based AED. However, this parallelization
ability is lost when applying scheduled sampling training. Self-attention with
sinusoidal positional embedding may cause performance degradations for longer
sequences that have similar acoustic or semantic information at different
positions as well. To address these problems, we propose to use parallel
scheduled sampling (PSS) and relative positional embedding (RPE) to help the
transformer generalize to unseen data. Our proposed methods achieve a 7%
relative improvement for short utterances and a 70% relative gain for long
utterances on a 10,000-hour Mandarin ASR task.

本文中，我们提出了一种采用 parallel scheduling sampling (PSS) 和 relative positional embedding (RPE) 来帮助 Transformer 泛化到看不见的数据的方法。我们的方法在 10,000 小时普通话自动语音识别任务上，对于短语音有 7% 的相对改进和对于长语音有 70% 的相对改进。