Rich Prosody Diversity Modelling with Phone-Level Mixture Density Network
By Chenpeng Du, K. Yu. 2021
18 citations recorded by the source corpus.
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.
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
In Signal Processing
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.”
- Phone-Level Prosody Modelling With GMM-Based MDN for Diverse and Controllable Speech Synthesis (2021, unknown): “[33] proposes a GMM-based prosody modelling approach in single-speaker TTS.”
- Unsupervised Word-Level Prosody Tagging for Controllable Speech Synthesis (2022, methodology): “In order to obtain word-level prosody embeddings, we first build a typical FastSpeech2-based TTS model together with a prosody extractor following [19].”