ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1810.07217
88
276
v1v2 (latest)

Hierarchical Generative Modeling for Controllable Speech Synthesis

16 October 2018
Wei-Ning Hsu
Yu Zhang
Ron J. Weiss
Heiga Zen
Yonghui Wu
Yuxuan Wang
Yuan Cao
Ye Jia
Zhiwen Chen
Jonathan Shen
Patrick Nguyen
Ruoming Pang
    BDL
ArXiv (abs)PDFHTML
Abstract

This paper proposes a neural end-to-end text-to-speech (TTS) model which can control latent attributes in the generated speech that are rarely annotated in the training data, such as speaking style, accent, background noise, and recording conditions. The model is formulated as a conditional generative model with two levels of hierarchical latent variables. The first level is a categorical variable, which represents attribute groups (e.g. clean/noisy) and provides interpretability. The second level, conditioned on the first, is a multivariate Gaussian variable, which characterizes specific attribute configurations (e.g. noise level, speaking rate) and enables disentangled fine-grained control over these attributes. This amounts to using a Gaussian mixture model (GMM) for the latent distribution. Extensive evaluation demonstrates its ability to control the aforementioned attributes. In particular, it is capable of consistently synthesizing high-quality clean speech regardless of the quality of the training data for the target speaker.

View on arXiv
Comments on this paper