pith. sign in

arxiv: 1804.02135 · v3 · pith:UVJIO3A5new · submitted 2018-04-06 · 💻 cs.CL · cs.SD· eess.AS

Expressive Speech Synthesis via Modeling Expressions with Variational Autoencoder

classification 💻 cs.CL cs.SDeess.AS
keywords speechautoregressivecharacteristicsglobalmodelautoencoderexpressionsexpressive
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Fine-grained robust prosody transfer for single-speaker neural text-to-speech

    eess.AS 2019-07 unverdicted novelty 6.0

    Decouples prosody alignment via pre-computed phoneme timestamps and adds VAE to achieve robust fine-grained prosody transfer in single-speaker neural TTS from unseen speakers.

  2. A Methodology for Controlling the Emotional Expressiveness in Synthetic Speech -- a Deep Learning approach

    eess.AS 2019-07 unverdicted novelty 3.0

    A methodology is proposed for emotional text-to-speech using emotional data collection, transfer-learning-based annotation of expressiveness features, and fine-tuning of a neutral TTS model.