Publication at Faculty of Mathematics and Physics |
2021
Abstract
End-to-end neural automatic speech recognition systems achieved recently state-of-the-art results but they require large datasets and extensive computing resources. Transfer learning has been proposed to overcome these difficulties even across languages, e.g., German ASR trained from an English model.
We experiment with much less related languages, reusing an English model for Czech ASR. To simplify the transfer, we propose to use an intermediate alphabet, Czech without accents, and we document that it is a highly effective strategy.
The technique is also useful on Czech data alone, in the style of "coarse-to-fine" training. We achieve substantial reductions in training time as well as word error rate (WER).