German Phoneme Recognition with Text-to-Phoneme Data Augmentation
This work addresses phoneme recognition for German, but it is incremental as it explores a specific data augmentation tweak with mixed results.
The study investigated the impact of adding frequent phoneme bigrams via text-to-phoneme data augmentation on German phoneme recognition, finding that some models increased BLEU scores by over 1 point while one decreased by more than 20 points, indicating variable effects on performance.
In this study, we experimented to examine the effect of adding the most frequent n phoneme bigrams to the basic vocabulary on the German phoneme recognition model using the text-to-phoneme data augmentation strategy. As a result, compared to the baseline model, the vowel30 model and the const20 model showed an increased BLEU score of more than 1 point, and the total30 model showed a significant decrease in the BLEU score of more than 20 points, showing that the phoneme bigrams could have a positive or negative effect on the model performance. In addition, we identified the types of errors that the models repeatedly showed through error analysis.