Letter-to-phoneme conversion by inference of rewriting rules - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2009

Letter-to-phoneme conversion by inference of rewriting rules

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.
Fichier principal
Vignette du fichier
Claveau-IS09-vf.pdf (92.55 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00844000 , version 1 (12-07-2013)

Identifiers

  • HAL Id : hal-00844000 , version 1

Cite

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

Share

Gmail Facebook X LinkedIn More