The Zero Resource Speech Challenge 2017

Abstract : We describe a new challenge aimed at discovering subword and word units from raw speech. This challenge is the followup to the Zero Resource Speech Challenge 2015. It aims at constructing systems that generalize across languages and adapt to new speakers. The design features and evaluation metrics of the challenge are presented and the results of seventeen models are discussed.
Type de document :
Direction d'ouvrage, Proceedings, Dossier
France. IEEE, 2017
Liste complète des métadonnées
Contributeur : Emmanuel Dupoux <>
Soumis le : jeudi 18 janvier 2018 - 15:10:15
Dernière modification le : mardi 12 février 2019 - 01:30:55

Lien texte intégral


  • HAL Id : hal-01687504, version 1
  • ARXIV : 1712.04313


Ewan Dunbar, Xuan-Nga Cao, Juan Benjumea, Julien Karadayi, Mathieu Bernard, et al.. The Zero Resource Speech Challenge 2017. France. IEEE, 2017. 〈hal-01687504〉



Consultations de la notice