Saved in:
Bibliographic Details
Main Authors: Lovelace, Justin, Ray, Soham, Kim, Kwangyoun, Weinberger, Kilian Q., Wu, Felix
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.03717
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916383641567232
author Lovelace, Justin
Ray, Soham
Kim, Kwangyoun
Weinberger, Kilian Q.
Wu, Felix
author_facet Lovelace, Justin
Ray, Soham
Kim, Kwangyoun
Weinberger, Kilian Q.
Wu, Felix
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2409_03717
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Sample-Efficient Diffusion for Text-To-Speech Synthesis
Lovelace, Justin
Ray, Soham
Kim, Kwangyoun
Weinberger, Kilian Q.
Wu, Felix
Sound
Artificial Intelligence
Machine Learning
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.
title Sample-Efficient Diffusion for Text-To-Speech Synthesis
topic Sound
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2409.03717