English

Sample-Efficient Diffusion for Text-To-Speech Synthesis

Sound 2024-09-06 v1 Artificial Intelligence Machine Learning

Abstract

This work introduces Sample-Efficient Speech Diffusion (SESD), an algorithm for effective speech synthesis in modest data regimes through latent diffusion. It is based on a novel diffusion architecture, that we call U-Audio Transformer (U-AT), that efficiently scales to long sequences and operates in the latent space of a pre-trained audio autoencoder. Conditioned on character-aware language model representations, SESD achieves impressive results despite training on less than 1k hours of speech - far less than current state-of-the-art systems. In fact, it synthesizes more intelligible speech than the state-of-the-art auto-regressive model, VALL-E, while using less than 2% the training data.

Keywords

Cite

@article{arxiv.2409.03717,
  title  = {Sample-Efficient Diffusion for Text-To-Speech Synthesis},
  author = {Justin Lovelace and Soham Ray and Kwangyoun Kim and Kilian Q. Weinberger and Felix Wu},
  journal= {arXiv preprint arXiv:2409.03717},
  year   = {2024}
}

Comments

Interspeech 2024

R2 v1 2026-06-28T18:35:37.581Z