Incorporating alignments into Conditional Random Fields for grapheme to phoneme conversion

Citations Over Time

Abstract

Conditional Random Fields (CRFs) are a state-of-the-art approach to natural language processing tasks like grapheme-to phoneme (g2p) conversion which is used to produce pronunciations or pronunciation variants for almost all ASR pronunciation lexica. One drawback of CRFs is that for training, an alignment is needed between graphemes and phonemes, usually even 1-to-l. The quality of the g2p result heavily depends on this alignment. Since these alignments are usually not annotated within the corpora, external models have to be used to produce such an alignment in a preprocessing step. In this work, we propose two approaches to integrate the alignment generation directly and efficiently into the CRF training process. Whereas the first approach relies on linear segmentation as starting point, the second approach considers all possible alignments given certain constraints. Both methods have been evaluated on two English g2p tasks, namely NETtalk and Celex, on which state-of-the-art results have been reported in the literature. The proposed approaches lead to results comparable to the state-of-the art.

Related Papers

• Chinese Named Entity Recognition with Conditional Random Fields(2006)
• → Gradual transition detection with conditional random fields(2007)7 cited
• → Result identification for biomedical abstracts using Conditional Random Fields(2008)6 cited
• Named entity recognition in Chinese medical records based on cascaded conditional random field(2014)
• → Biomedical Named Entity Recognition Using Second-Order Conditional Random Fields(2011)