Deep Transformer based Data Augmentation with Subword Units for Morphologically Rich Online ASR

Recently Deep Transformer models have proven to be particularly powerful in language modeling tasks for ASR. Their high complexity, however, makes them very difficult to apply in the first (single) pass of an online system. Recent studies showed that a considerable part of the knowledge of neural network Language Models (LM) can be transferred to traditional n-grams by using neural text generation based data augmentation. In our paper, we pre-train a GPT-2 Transformer LM on a general text corpus and fine-tune it on our Hungarian conversational call center ASR task. We show that although data augmentation with Transformer-generated text works well for isolating languages, it causes a vocabulary explosion in a morphologically rich language. Therefore, we propose a new method called subword-based neural text augmentation, where we retokenize the generated text into statistically derived subwords. We show that this method can significantly reduce the WER while greatly reducing vocabulary size and memory requirements. Finally, we also show that subword-based neural text augmentation outperforms the word-based approach not only in terms of overall WER but also in recognition of OOV words.