La phonétisation comme un problème de translittération

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 : Phonetizing is a crucial step to process oral documents. In this paper, a new word-based phonetization approach is proposed ; it is automatic, simple, portable and efficient. It relies on machine learning ; thus, the system is built from examples of words with their pho- netic representations. More precisely, it makes the most of a technique inferring rewriting rules initially developed for transliteration and translation. In order to evaluate the performances of this approach, we used several datasets from the Pronalsyl Pascal challenge, including different languages. The obtained results equal or outperform those of the best known systems.
Document type :
Conference papers
Complete list of metadatas

Cited literature [10 references]  Display  Hide  Download

https://hal.inria.fr/hal-00843982
Contributor : Patrick Gros <>
Submitted on : Friday, July 12, 2013 - 3:13:18 PM
Last modification on : Friday, November 16, 2018 - 1:21:55 AM
Long-term archiving on : Monday, October 14, 2013 - 11:10:21 AM

File

Claveau-taln09-vf.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00843982, version 1

Citation

Vincent Claveau. La phonétisation comme un problème de translittération. TALN - Conférence sur le traitement automatique des langues naturelles, Jun 2009, Senlis, France. ⟨hal-00843982⟩

Share

Metrics

Record views

250

Files downloads

409