The Zero Resource Speech Challenge 2019: TTS without T - Archive ouverte HAL Access content directly
Conference Papers Year : 2019

The Zero Resource Speech Challenge 2019: TTS without T

Lucas Ondel

Abstract

We present the Zero Resource Speech Challenge 2019, which proposes to build a speech synthesizer without any text or pho-netic 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.
Fichier principal
Vignette du fichier
1904.11469.pdf (800.7 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-02274112 , version 1 (29-08-2019)

Identifiers

  • HAL Id : hal-02274112 , version 1

Cite

Ewan Dunbar, Robin Algayres, Julien Karadayi, Mathieu Bernard, Juan Benjumea, et al.. The Zero Resource Speech Challenge 2019: TTS without T. Interspeech 2019 - 20th Annual Conference of the International Speech Communication Association, Sep 2019, Graz, Austria. ⟨hal-02274112⟩
253 View
99 Download

Share

Gmail Mastodon Facebook X LinkedIn More