E1 TTS: Simple and Fast Non-Autoregressive TTS

TL;DR

E1 TTS is a simple, fast, non-autoregressive text-to-speech system that uses diffusion pretraining and distillation, enabling efficient inference without explicit alignment, while maintaining high naturalness and speaker similarity.

Contribution

The paper presents E1 TTS, a novel non-autoregressive TTS model that simplifies training and inference processes while achieving high-quality speech synthesis.

Findings

Achieves naturalness comparable to strong baselines.

Requires only one neural network evaluation per utterance.

Does not need explicit text-audio alignment during training.

Abstract

This paper introduces Easy One-Step Text-to-Speech (E1 TTS), an efficient non-autoregressive zero-shot text-to-speech system based on denoising diffusion pretraining and distribution matching distillation. The training of E1 TTS is straightforward; it does not require explicit monotonic alignment between the text and audio pairs. The inference of E1 TTS is efficient, requiring only one neural network evaluation for each utterance. Despite its sampling efficiency, E1 TTS achieves naturalness and speaker similarity comparable to various strong baseline models. Audio samples are available at http://e1tts.github.io/ .