This is a good question. I'm not sure which paper the parent comment is referencing - and in general, DeepFakes is a very general term for a variety of techniques including GANs. The problem you describe is called the alignment problem and it's studied in several areas of applied ml: translation, multi-modal learning, etc.

For example, the canonical way to train deep machine translation systems is to make use of large parallel corpora - large set of translation pairs. In the case where this data may not exist, for structurally similar languages, one approach is to learn unsupervised word embeddings independently (i.e. using word2vec) which only require monolingual data and to find a transformation that aligns the two spaces. In many cases, neural networks still struggle with this task. However, some work in the last few years has demonstrated that a few seed word-translations is all you need to apply simple algorithms that can learn a linear or simple nonlinear transformation that work pretty well!

[1] Here is a method that proposes locally linear transformation maps for alignment: http://nakashole.com/papers/2018-emnlp-norm.pdf

Something like a CycleGAN and/ or weight sharing would do the trick