Uncovering Latent Style Factors for Expressive Speech Synthesis

Abstract

Prosodic modeling is a core problem in speech synthesis. The key challenge is producing desirable prosody from textual input containing only phonetic information. In this preliminary study, we introduce the concept of "style tokens" in Tacotron, a recently proposed end-to-end neural speech synthesis model. Using style tokens, we aim to extract independent prosodic styles from training data. We show that without annotation data or an explicit supervision signal, our approach can automatically learn a variety of prosodic variations in a purely data-driven way. Importantly, each style token corresponds to a fixed style factor regardless of the given text sequence. As a result, we can control the prosodic style of synthetic speech in a somewhat predictable and globally consistent way.

Submitted to NIPS ML4Audio workshop and ICASSP

Cited by in corpus (9)

• MuSE-SVS: Multi-Singer Emotional Singing Voice Synthesizer that Controls Emotional Intensity
• From Speaker Verification to Multispeaker Speech Synthesis, Deep Transfer with Feedback Constraint
• GraphTTS: graph-to-sequence modelling in neural text-to-speech
• GraphPB: Graphical Representations of Prosody Boundary in Speech Synthesis
• Forward-Backward Decoding for Regularizing End-to-End TTS
• Controllable Emotion Transfer For End-to-End Speech Synthesis
• GANtron: Emotional Speech Synthesis with Generative Adversarial Networks
• A Deep-Bayesian Framework for Adaptive Speech Duration Modification
• Emotional speech synthesis with rich and granularized control