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 fol-lowup 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.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [33 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01664586
Contributor : Laurent Besacier <>
Submitted on : Friday, December 15, 2017 - 7:34:09 AM
Last modification on : Thursday, April 4, 2019 - 10:18:05 AM

File

main.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01664586, version 1

Collections

Citation

Ewan Dunbar, Xuan Cao, Juan Benjumea, Julien Karadayi, Mathieu Bernard, et al.. THE ZERO RESOURCE SPEECH CHALLENGE 2017. IEEE Automatic Speech Recognition and Understanding (ASRU), Dec 2017, Okinawa, Japan. ⟨hal-01664586⟩

Share

Metrics

Record views

241

Files downloads

135