The Zero Resource Speech Challenge 2017

12/12/2017

∙

by   Ewan Dunbar, et al.

∙

0

∙

share

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.