We present the Zero Resource Speech Challenge 2019, which proposes to build a speech synthesizer without any text or phonetic labels: hence, TTS without T (text-to-speech without text). We provide raw audio for a target voice in an unknown language (the Voice dataset), but no alignment, text or labels. Participants must discover subword units in an unsupervised way (using the Unit Discovery dataset) and align them to the voice recordings in a way that works best for the purpose of synthesizing novel utterances from novel speakers, similar to the target speaker's voice. We describe the metrics used for evaluation, a baseline system consisting of unsupervised subword unit discovery plus a standard TTS system, and a topline TTS using gold phoneme transcriptions. We present an overview of the 19 submitted systems from 10 teams and discuss the main results.
@article{arxiv.1904.11469,
title = {The Zero Resource Speech Challenge 2019: TTS without T},
author = {Ewan Dunbar and Robin Algayres and Julien Karadayi and Mathieu Bernard and Juan Benjumea and Xuan-Nga Cao and Lucie Miskic and Charlotte Dugrain and Lucas Ondel and Alan W. Black and Laurent Besacier and Sakriani Sakti and Emmanuel Dupoux},
journal= {arXiv preprint arXiv:1904.11469},
year = {2019}
}