# Rich Prosody Diversity Modelling with Phone-level Mixture Density Network

arXiv: https://arxiv.org/abs/2102.00851 · HTML: https://mlsanity.com/paper/2102.00851/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Feb 2021.

## Built on by (most cited first, 5 of 5)

- [Unsupervised word-level prosody tagging for controllable speech synthesis](https://mlsanity.com/paper/2202.07200/) (2022)
- [SC VALL-E: Style-Controllable Zero-Shot Text to Speech Synthesizer](https://mlsanity.com/paper/2307.10550/) (2023)
- [DSE-TTS: Dual Speaker Embedding for Cross-Lingual Text-to-Speech](https://mlsanity.com/paper/2306.14145/) (2023)
- [Controllable speech synthesis by learning discrete phoneme-level prosodic representations](https://mlsanity.com/paper/2211.16307/) (2022)
- [StoryTTS: A Highly Expressive Text-to-Speech Dataset with Rich Textual Expressiveness Annotations](https://mlsanity.com/paper/2404.14946/) (2024)

## Abstract (arXiv)

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.