Comparing NLP solutions for the disambiguation of French heterophonic homographs for end-to-end TTS systems - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Comparing NLP solutions for the disambiguation of French heterophonic homographs for end-to-end TTS systems

Résumé

This paper presents a study on different NLP solutions for French homographs disambiguation for text-to-speech systems. Solutions are compared using a home-made corpus of 8137 sentences extracted from the Web, comprising roughly one hundred instances of each of 34 pairs of prototypical words. A disambiguation system based on per-case Linear Discriminant Analysis (LDA) classifiers using contextual word embeddings as input features achieves state-of-the-art F-scores superior to 0.96.
Fichier principal
Vignette du fichier
SPECOM2022-4.pdf (890.5 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03858736 , version 1 (17-11-2022)

Identifiants

Citer

Maria-Loulou Hajj, Martin Lenglet, Olivier Perrotin, Gérard Bailly. Comparing NLP solutions for the disambiguation of French heterophonic homographs for end-to-end TTS systems. SPECOM 2022 - 24th International Conference on Speech and Computer (SPECOM), Nov 2022, Kitt Gurugram, India. pp.265-278, ⟨10.1007/978-3-031-20980-2_23⟩. ⟨hal-03858736⟩
62 Consultations
152 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More