On the Semantic Latent Space of Diffusion-Based Text-To-Speech Models

Miri Varshavsky-Hassid, Roy Hirsch, Regev Cohen, Tomer Golany, Daniel Freedman, Ehud Rivlin


Abstract
The incorporation of Denoising Diffusion Models (DDMs) in the Text-to-Speech (TTS) domain is rising, providing great value in synthesizing high quality speech. Although they exhibit impressive audio quality, the extent of their semantic capabilities is unknown, and controlling their synthesized speech’s vocal properties remains a challenge. Inspired by recent advances in image synthesis, we explore the latent space of frozen TTS models, which is composed of the latent bottleneck activations of the DDM’s denoiser. We identify that this space contains rich semantic information, and outline several novel methods for finding semantic directions within it, both supervised and unsupervised. We then demonstrate how these enable off-the-shelf audio editing, without any further training, architectural changes or data requirements. We present evidence of the semantic and acoustic qualities of the edited audio, and provide supplemental samples: https://latent-analysis-grad-tts.github.io/speech-samples/.
Anthology ID:
2024.acl-short.24
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
246–255
Language:
URL:
https://aclanthology.org/2024.acl-short.24
DOI:
10.18653/v1/2024.acl-short.24
Bibkey:
Cite (ACL):
Miri Varshavsky-Hassid, Roy Hirsch, Regev Cohen, Tomer Golany, Daniel Freedman, and Ehud Rivlin. 2024. On the Semantic Latent Space of Diffusion-Based Text-To-Speech Models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 246–255, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
On the Semantic Latent Space of Diffusion-Based Text-To-Speech Models (Varshavsky-Hassid et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-short.24.pdf