Temporally-Aware Acoustic Unit Discovery for Zerospeech 2019 Challenge

Yusuf, Bolaji; Gok, Alican; Gundogdu, Batuhan; Kose, Oyku Deniz; Saraçlar, Murat

doi:10.21437/interspeech.2019-1430

Cited by 4 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that the topline phone-level language model performs sub-optimally on these files, because they begin with unlikely sequences of phones. [27] no no Ossian LI [28] yes yes Inversion EL [29] no yes FFTnet NA [30] no no Ossian CH (Cho et al) yes yes Direct RA (Rallabandi et al) no no Ossian YU [31] no no Ossian TJ [32] yes yes Inversion…”

Section: Embedding Bitrate and Qualitymentioning

confidence: 99%

The Zero Resource Speech Challenge 2019: TTS without T

Dunbar¹,

Algayres²,

Karadayi³

et al. 2019

Preprint

View full text Add to dashboard Cite

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.

show abstract