Rich Prosody Diversity Modelling with Phone-level Mixture Density Network

Abstract

Generating natural speech with diverse and smooth prosody pattern is a challenging task. Although random sampling with phone-level prosody distribution has been investigated to generate different prosody patterns, the diversity of the generated speech is still very limited and far from what can be achieved by human. This is largely due to the use of uni-modal distribution, such as single Gaussian, in the prior works of phone-level prosody modelling. In this work, we propose a novel approach that models phone-level prosodies with GMM based mixture density network (GMM-MDN). Experiments on the LJSpeech dataset demonstrate that phone-level prosodies can precisely control the synthetic speech and GMM-MDN can generate more natural and smooth prosody pattern than a single Gaussian. Subjective evaluations further show that the proposed approach not only achieves better naturalness, but also significantly improves the prosody diversity in synthetic speech without the need of manual control.

arXiv commentAccepted to Interspeech 2021

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
• FastSpeech: Fast, Robust and Controllable Text to Speech
• Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
• FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
• Generating diverse and natural text-to-speech samples using a quantized fine-grained VAE and auto-regressive prosody prior

Cited by in corpus (2)

• Phone-Level Prosody Modelling with GMM-Based MDN for Diverse and Controllable Speech Synthesis
• Controllable speech synthesis by learning discrete phoneme-level prosodic representations