Dual learning is a paradigm for semi-supervised machine learning that seeks
to leverage unsupervised data by solving two opposite tasks at once. In this
scheme, each model is used to generate pseudo-labels for unlabeled examples
that are used to train the other model. Dual learning has seen some use in
speech processing by pairing ASR and TTS as dual tasks. However, these results
mostly address only the case of using unpaired examples to compensate for very
small supervised datasets, and mostly on large, non-streaming models. Dual
learning has not yet been proven effective for using unsupervised data to
improve realistic on-device streaming models that are already trained on large
supervised corpora. We provide this missing piece though an analysis of an
on-device-sized streaming conformer trained on the entirety of Librispeech,
showing relative WER improvements of 10.7%/5.2% without an LM and 11.7%/16.4%
with an LM.

通过对一种在 conformer 模型上的 unsupervised 的 dual learning 方法的实验，取得了相对于之前模型的 10.7%/5.2%(没有 LM) 和 11.7%/16.4%(有 LM) 的 WER 提升，该方法对已经在大规模监督语料库上训练过的实时 on-device streaming 模型进行了优化。