Expressive Speech Synthesis via Modeling Expressions with Variational Autoencoder
Preprint
Abstract
Recent advances in neural autoregressive models have improve the performance of speech synthesis (SS). However, as they lack the ability to model global characteristics of speech (such as speaker individualities or speaking styles), particularly when these characteristics have not been labeled, making neural autoregressive SS systems more expressive is still an open issue. In this paper, we propose to combine VoiceLoop, an autoregressive SS model, with Variational Autoencoder (VAE). This approach, unlike traditional autoregressive SS systems, uses VAE to model the global characteristics explicitly, enabling the expressiveness of the synthesized speech to be controlled in an unsupervised manner. Experiments using the VCTK and Blizzard2012 datasets show the VAE helps VoiceLoop to generate higher quality speech and to control the expressions in its synthesized speech by incorporating global characteristics into the speech generating process.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- Voice Conversion from Unaligned Corpora Using Variational Autoencoding Wasserstein Generative Adversarial Networks2017
- WORLD: A Vocoder-Based High-Quality Speech Synthesis System for Real-Time ApplicationsIEICE Transactions on Information and Systems, 2016
- Integrated Expression Prediction and Speech Synthesis From TextIEEE Journal of Selected Topics in Signal Processing, 2013
- Expressive speech: Production, perception and application to speech synthesisAcoustical Science and Technology, 2005