E3 TTS: Easy End-to-End Diffusion-based Text to Speech
This addresses speech synthesis for applications requiring flexible audio generation, but it is incremental as it builds on existing diffusion methods.
They tackled text-to-speech synthesis by proposing an end-to-end diffusion model that directly generates audio waveforms from plain text without intermediate representations, achieving high-fidelity audio that approaches state-of-the-art performance.
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.