Letter-to-phoneme conversion by inference of rewriting rules

Vincent Claveau 1, *
* Corresponding author
1 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : Phonetization is a crucial step for oral document processing. In this paper, a new letter-to-phoneme conversion approach is pro- posed; it is automatic, simple, portable and efficient. It relies on a machine learning technique initially developed for translit- eration and translation; the system infers rewriting rules from examples of words with their phonetic representations. This approach is evaluated in the framework of the Pronalsyl Pas- cal challenge, which includes several datasets on different lan- guages. The obtained results equal or outperform those of the best known systems. Moreover, thanks to the simplicity of our technique, the inference time of our approach is much lower than those of the best performing state-of-the-art systems. Index Terms : phonetization, inference of rewriting rules, phonemization, grapheme-to-phoneme, Pronalsyl Challenge.
Document type :
Conference papers
Complete list of metadatas

Cited literature [16 references]  Display  Hide  Download

https://hal.inria.fr/hal-00844000
Contributor : Patrick Gros <>
Submitted on : Friday, July 12, 2013 - 3:36:48 PM
Last modification on : Friday, November 16, 2018 - 1:22:26 AM
Long-term archiving on : Monday, October 14, 2013 - 11:10:59 AM

File

Claveau-IS09-vf.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00844000, version 1

Citation

Vincent Claveau. Letter-to-phoneme conversion by inference of rewriting rules. Interspeech, ISCA, Sep 2009, Brighton, United Kingdom. pp.1299-1302. ⟨hal-00844000⟩

Share

Metrics

Record views

262

Files downloads

186