A Study on Altering the Latent Space of Pretrained Text to Speech Models for Improved Expressiveness

Mathias Vogel
11/17/2023
cs.CLcs.AI

No confident code implementation found for this paper.

Abstract

This report explores the challenge of enhancing expressiveness control in Text-to-Speech (TTS) models by augmenting a frozen pretrained model with a Diffusion Model that is conditioned on joint semantic audio/text embeddings. The paper identifies the challenges encountered when working with a VAE-based TTS model and evaluates different image-to-image methods for altering latent speech features. Our results offer valuable insights into the complexities of adding expressiveness control to TTS systems and open avenues for future research in this direction.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Seeing What You Say: Expressive Image Generation from Speech

83% match2025

Shared Latent Representation for Joint Text-to-Audio-Visual Synthesis

82% match2025

Interpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders

82% match2026

UniSS: Unified Expressive Speech-to-Speech Translation with Your Voice

82% match1 repo462025

Beyond Speech Captions: Speech-Rewarded Style Planning for Conversational Text-to-Speech

81% match2026

Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model

81% match1 repo1.2k2023

Cite this paper

@article{vogel2023study,
  title  = {A Study on Altering the Latent Space of Pretrained Text to Speech Models for Improved Expressiveness},
  author = {Mathias Vogel},
  year   = {2023},
  eprint = {2311.10804},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2311.10804v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2311.10804.svg)](https://codeofpaper.com/paper/2311.10804)

Discussion