Transformer models are powerful sequence-to-sequence architectures that are
capable of directly mapping speech inputs to transcriptions or translations.
However, the mechanism for modeling positions in this model was tailored for
text modeling, and thus is less ideal for acoustic inputs. In this work, we
adapt the relative position encoding scheme to the Speech Transformer, where
the key addition is relative distance between input states in the
self-attention network. As a result, the network can better adapt to the
variable distributions present in speech data. Our experiments show that our
resulting model achieves the best recognition result on the Switchboard
benchmark in the non-augmentation condition, and the best published result in
the MuST-C speech translation benchmark. We also show that this model is able
to better utilize synthetic data than the Transformer, and adapts better to
variable sentence segmentation quality for speech translation.

通过在自注意力网络中采用相对位置编码方案，我们成功地让 Transformer 模型适应了语音数据的分散分布特点，并在 Switchboard 基准测试中获得了最佳识别结果，也在 MuST-C 语音翻译基准测试中获得了最佳出版结果，并且我们的模型能够更好地利用合成数据，并适应语音翻译的变量句子分割质量。