Paper: Reversible Sound-to-Letter/Letter-to-Sound Modeling Based on Syllable Structure

ACL ID N07-2039
Title Reversible Sound-to-Letter/Letter-to-Sound Modeling Based on Syllable Structure
Venue Human Language Technologies
Session Short Paper
Year 2007
Authors

This paper describes a new grapheme-to- phoneme framework, based on a combi- nation of formal linguistic and statisti- cal methods. A context-free grammar is used to parse words into their underly- ing syllable structure, and a set of sub- word “spellneme” units encoding both phonemic and graphemic information can be automatically derived from the parsed words. A statistical a1 -gram model can then be trained on a large lexicon of words represented in terms of these linguistically motivated subword units. The frame- work has potential applications in mod- eling unknown words and in linking spo- ken spellings with spoken pronunciations for fully automatic new-word acquisition via dialogue interaction. Results are re- ported on sound-to-letter experiments for the nouns in the Phonebook c...