CHiVE: Examples for randomly sampled embeddings

<< Back

This page contains audio samples that go with CHiVE: Varying Prosody in Speech Synthesis with a Linguistically Driven Dynamic Hierarchical Conditional Variational Network, Wan, V., Chan, C.-a., Kenter, T., Vit, J., and Clark, R. A., Proceedings of the Thirty-sixth International Conference on Machine Learning (ICML 2019), 2019, Section 4.2, Figure 4.

Audio for randomly generated log F0 contours

These examples show a random sample of the varied prosodies for the short sentence "That's a super choice".
Held out recorded audio example
Zero (mean) sentence prosody embedding
Random sample sentence prosody embedding
Random sample sentence prosody embedding
Random sample sentence prosody embedding
Random sample sentence prosody embedding
Random sample sentence prosody embedding
Random sample sentence prosody embedding
Random sample sentence prosody embedding
Random sample sentence prosody embedding
Random sample sentence prosody embedding