Skip to Main content Skip to Navigation
Conference papers

Grapheme to phoneme conversion using an SMT system

Abstract : This paper presents an automatic grapheme to phoneme conversion system that uses statistical machine transla- tion techniques provided by the Moses Toolkit. The gen- erated word pronunciations are employed in the dictio- nary of an automatic speech recognition system and eval- uated using the ESTER 2 French broadcast news cor- pus. Grapheme to phoneme conversion based on Moses is compared to two other methods: G2P, and a dictionary look-up method supplemented by a rule-based tool for phonetic transcriptions of words unavailable in the dictionary. Moses gives better results than G2P, and have performance comparable to the dictionary look-up strat- egy.
Document type :
Conference papers
Complete list of metadata

Cited literature [9 references]  Display  Hide  Download
Contributor : Hakim Amokrane <>
Submitted on : Wednesday, March 22, 2017 - 11:33:18 PM
Last modification on : Thursday, April 6, 2017 - 10:15:54 AM
Long-term archiving on: : Friday, June 23, 2017 - 2:39:04 PM


Files produced by the author(s)


  • HAL Id : hal-01451534, version 1



Antoine Laurent, Paul Deléglise, Sylvain Meignier. Grapheme to phoneme conversion using an SMT system. 10th Annual Conference of the International Speech Communication Association 2009 (INTERSPEECH 2009) , Sep 2009, Brighton, United Kingdom. pp.716-719. ⟨hal-01451534⟩



Record views


Files downloads