The DeepZen Speech Synthesis System for Blizzard Challenge 2023

by   Christophe Veaux, et al.

This paper describes the DeepZen text to speech (TTS) system for Blizzard Challenge 2023. The goal of this challenge is to synthesise natural and high-quality speech in French, from a large monospeaker dataset (hub task) and from a smaller dataset by speaker adaptation (spoke task). We participated to both tasks with the same model architecture. Our approach has been to use an auto-regressive model, which retains an advantage for generating natural sounding speech but to improve prosodic control in several ways. Similarly to non-attentive Tacotron, the model uses a duration predictor and gaussian upsampling at inference, but with a simpler unsupervised training. We also model the speaking style at both sentence and word levels by extracting global and local style tokens from the reference speech. At inference, the global and local style tokens are predicted from a BERT model run on text. This BERT model is also used to predict specific pronunciation features like schwa elision and optional liaisons. Finally, a modified version of HifiGAN trained on a large public dataset and fine-tuned on the target voices is used to generate speech waveform. Our team is identified as O in the the Blizzard evaluation and MUSHRA test results show that our system performs second ex aequo in both hub task (median score of 0.75) and spoke task (median score of 0.68), over 18 and 14 participants, respectively.


page 1

page 2

page 3

page 4


Word-Level Style Control for Expressive, Non-attentive Speech Synthesis

This paper presents an expressive speech synthesis architecture for mode...

Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis

In this work, we propose "global style tokens" (GSTs), a bank of embeddi...

Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling

This paper presents Non-Attentive Tacotron based on the Tacotron 2 text-...

The FruitShell French synthesis system at the Blizzard 2023 Challenge

This paper presents a French text-to-speech synthesis system for the Bli...

VRAIN-UPV MLLP's system for the Blizzard Challenge 2021

This paper presents the VRAIN-UPV MLLP's speech synthesis system for the...

Median-Based Generation of Synthetic Speech Durations using a Non-Parametric Approach

This paper proposes a new approach to duration modelling for statistical...

Alzheimer's Dementia Recognition through Spontaneous Speech: The ADReSS Challenge

The ADReSS Challenge at INTERSPEECH 2020 defines a shared task through w...

Please sign up or login with your details

Forgot password? Click here to reset