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

TL;DR

Flowtron is a flow-based autoregressive model for text-to-speech synthesis that achieves high-quality speech, offers controllable variation and style transfer, and simplifies training through likelihood maximization.

Contribution

It introduces Flowtron, a novel invertible flow-based TTS model that enables expressive speech synthesis with controllable attributes and stable training, surpassing prior models in quality.

Findings

Matches state-of-the-art speech quality in MOS scores

Provides controllable speech variation and style transfer

Simplifies training with likelihood maximization

Abstract

In this paper we propose Flowtron: an autoregressive flow-based 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