Abstract / Description of output
The paper provides an alternative approach to one of the key steps of speech synthesis – grapheme-to-phoneme conversion. The approach is based on automatic morphological analysis of out-of-vocabulary words into their consitutent morphemes. In contrast to a traditional method of morphological analysis based on finite state transducers (FST), we propose here a solution that makes use of neural networks. Experiments show that morpho-logical analysis with the proposed neural network approach is significantly more effective(accuracy 93.8%) than than morphological analysis with FST (accuracy 75%). The proposed approach allows to speed up the creation of new grapheme-to-phoneme models, as well as making it easier to build and maintain pronunciation dictionaries.
| Translated title of the contribution | Grapheme-to-phoneme conversion with neural networks: Automatic morphological analysis |
|---|---|
| Original language | Russian |
| Pages (from-to) | 121-126 |
| Journal | ВЕСТНИК УФИМСКОГО ГОСУДАРСТВЕННОГО АВИАЦИОННОГО ТЕХНИЧЕСКОГО УНИВЕРСИТЕТА |
| Volume | 23 |
| Issue number | 2(84) |
| Publication status | Published - 4 Jul 2019 |
Keywords / Materials (for Non-textual outputs)
- grapheme-to-phoneme conversion
- morphological analysis
- neural networks