Phone-Level Prosody Modelling With GMM-Based MDN for Diverse and Controllable Speech Synthesis

By Chenpeng Du, K. Yu. 2021

24 citations recorded by the source corpus.

Generating natural speech with a 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 humans. 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 a GMM-based mixture density network(MDN) and then extend it for multi-speaker TTS using speaker adaptation transforms of Gaussian means and variances. Furthermore, we show that we can clone the prosodies from a reference speech by sampling prosodies from the Gaussian components that produce the reference prosodies. Our experiments on LJSpeech and LibriTTS dataset show that the proposed method with GMM-based MDN not only achieves significantly better diversity than using a single Gaussian in both single-speaker and multi-speaker TTS, but also provides better naturalness. The prosody cloning experiments demonstrate that the prosody similarity of the proposed method with GMM-based MDN is comparable to recent proposed fine-grained VAE while the target speaker similarity is better.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yiwei Guo
2. Xie Chen
3. Kai Yu
4. Chenpeng Du
5. Sang-Hoon Lee
6. Seong-Whan Lee
7. Hyung-Seok Oh
8. K. Yu

In Signal Processing

1. Yiwei Guo
2. Xie Chen
3. Kai Yu
4. Chenpeng Du
5. Sang-Hoon Lee
6. Seong-Whan Lee
7. Hyung-Seok Oh
8. K. Yu

Citations in the corpus

• VQTTS: High-Fidelity Text-to-Speech Synthesis with Self-Supervised VQ Acoustic Feature (2022, methodology): “For example, [11, 12, 13] uses phoneme-level prosodies, [14] uses word-level prosodies and [15, 16] uses hierarchical prosodies.”
• Unsupervised Word-Level Prosody Tagging for Controllable Speech Synthesis (2022, background): “Recently, unsupervised prosody clustering with mixture density network is also proposed in [18, 19], enabling richer prosody diversity.”
• DiffProsody: Diffusion-Based Latent Prosody Generation for Expressive Speech Synthesis With Prosody Conditional Adversarial Training (2023, methodology): “Gaussian-mixturemodel-based phone-level prosody modelling [21] is a method for sampling reference prosody from Gaussian components.”