Automatic Syllabification with Structured SVMs for Letter-to-Phoneme Conversion

We present the first English syllabification system to improve the accuracy of letter-tophoneme conversion. We propose a novel discriminative approach to automatic syllabification based on structured SVMs. In comparison with a state-of-the-art syllabification system, we reduce the syllabification word error rate for English by 33%. Our approach also performs well on other languages, comparing favorably with published results on German and Dutch.

• Type: Conference
• Year: 2008
• Where: ACL
• Authors: Susan Bartlett, Grzegorz Kondrak, Colin Cherry
• Keywords: ACL 2008, Computational Linguistics, English Syllabification, State-of-the-art Syllabification System, Syllabification