Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis

05/12/2020
by   Rafael Valle, et al.
0

generative network for text-to-speech synthesis with control over speech variation and style transfer. Flowtron borrows insights from IAF and revamps Tacotron in order to provide high-quality and expressive mel-spectrogram synthesis. Flowtron is optimized by maximizing the likelihood of the training data, which makes training simple and stable. Flowtron learns an invertible mapping of data to a latent space that can be manipulated to control many aspects of speech synthesis (pitch, tone, speech rate, cadence, accent). Our mean opinion scores (MOS) show that Flowtron matches state-of-the-art TTS models in terms of speech quality. In addition, we provide results on control of speech variation, interpolation between samples and style transfer between speakers seen and unseen during training. Code and pre-trained models will be made publicly available at https://github.com/NVIDIA/flowtron

READ FULL TEXT

page 5

page 7

research
10/31/2018

WaveGlow: A Flow-based Generative Network for Speech Synthesis

In this paper we propose WaveGlow: a flow-based network capable of gener...
research
09/14/2021

fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit

This paper presents fairseq S^2, a fairseq extension for speech synthesi...
research
03/17/2021

STYLER: Style Factor Modeling with Rapidity and Robustness via Speech Decomposition for Expressive and Controllable Neural Text to Speech

Previous works on neural text-to-speech (TTS) have been addressed on lim...
research
10/28/2020

Speech Synthesis and Control Using Differentiable DSP

Modern text-to-speech systems are able to produce natural and high-quali...
research
02/27/2023

Varianceflow: High-Quality and Controllable Text-to-Speech using Variance Information via Normalizing Flow

There are two types of methods for non-autoregressive text-to-speech mod...
research
10/06/2020

Neural Speech Synthesis for Estonian

This technical report describes the results of a collaboration between t...
research
07/04/2023

Disentanglement in a GAN for Unconditional Speech Synthesis

Can we develop a model that can synthesize realistic speech directly fro...

Please sign up or login with your details

Forgot password? Click here to reset