0

E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS

E2 TTS is a non-autoregressive zero-shot text-to-speech system using flow-matching-based mel spectrogram generation without additional components, achieving state-of-the-art performance.

Year
2024
Venue
arXiv 2024
Authors
13
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2406.18009v2ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

This paper introduces Embarrassingly Easy Text-to-Speech (E2 TTS), a fully non-autoregressive zero-shot text-to-speech system that offers human-level naturalness and state-of-the-art speaker similarity and intelligibility. In the E2 TTS framework, the text input is converted into a character sequence with filler tokens. The flow-matching-based mel spectrogram generator is then trained based on the audio infilling task. Unlike many previous works, it does not require additional components (e.g., duration model, grapheme-to-phoneme) or complex techniques (e.g., monotonic alignment search). Despite its simplicity, E2 TTS achieves state-of-the-art zero-shot TTS capabilities that are comparable to or surpass previous works, including Voicebox and NaturalSpeech 3. The simplicity of E2 TTS also allows for flexibility in the input representation. We propose several variants of E2 TTS to improve usability during inference. See https://aka.ms/e2tts/ for demo samples.

Authors

13