Jointly learning to align and convert graphemes to phonemes with neural attention models
2016pp. 76–82
Citations Over TimeTop 10% of 2016 papers
Abstract
We propose an attention-enabled encoder-decoder model for the problem of grapheme-to-phoneme conversion. Most previous work has tackled the problem via joint sequence models that require explicit alignments for training. In contrast, the attention-enabled encoder-decoder model allows for jointly learning to align and convert characters to phonemes. We explore different types of attention models, including global and local attention, and our best models achieve state-of-the-art results on three standard data sets (CMU-Dict, Pronlex, and NetTalk).
Related Papers
- → Using Reversed Sequences and Grapheme Generation Rules to Extend the Feasibility of a Phoneme Transition Network-Based Grapheme-to-Phoneme Conversion(2016)1 cited
- → Synchronous morphological analysis of grapheme and phoneme for Japanese OCR(2000)1 cited
- A New Approach to the Grapheme-to-Phoneme Conversion(2004)
- → Appendix B: Pedagogically selected lists of phoneme-grapheme and grapheme-phoneme correspondences(2015)
- → Literature Review of Research on Common Methods of Grapheme-To-Phoneme(2023)