We propose Easy End-to-End Diffusion-based Text to Speech, a simple and efficient end-to-end text-to-speech model based on diffusion. E3 TTS directly takes plain text as input and generates an audio waveform through an iterative refinement process. Unlike many prior work, E3 TTS does not rely on any intermediate representations like spectrogram features or alignment information. Instead, E3 TTS models the temporal structure of the waveform through the diffusion process. Without relying on additional conditioning information, E3 TTS could support flexible latent structure within the given audio. This enables E3 TTS to be easily adapted for zero-shot tasks such as editing without any additional training. Experiments show that E3 TTS can generate high-fidelity audio, approaching the performance of a state-of-the-art neural TTS system. Audio samples are available at https://e3tts.github.io.

翻译：我们提出简易端到端扩散式文本转语音（Easy End-to-End Diffusion-based Text to Speech，简称E3 TTS），这是一种基于扩散过程的简洁高效端到端文本转语音模型。E3 TTS直接以纯文本作为输入，通过迭代精炼过程生成音频波形。与许多先前工作不同，E3 TTS不依赖任何中间表示，例如频谱图特征或对齐信息。相反，E3 TTS通过扩散过程对波形的时间结构进行建模。在无需额外条件信息的情况下，E3 TTS能够支持给定音频内部的灵活潜在结构。这使得E3 TTS可轻松适应零样本任务（如编辑），且无需任何额外训练。实验表明，E3 TTS能够生成高保真音频，其性能接近最先进的神经文本转语音系统。音频样本见https://e3tts.github.io。