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|
|Journal||ВЕСТНИК УФИМСКОГО ГОСУДАРСТВЕННОГО АВИАЦИОННОГО ТЕХНИЧЕСКОГО УНИВЕРСИТЕТА|
|Publication status||Published - 4 Jul 2019|
- grapheme-to-phoneme conversion
- morphological analysis
- neural networks