CHiVE: Varying Prosody in Speech Synthesis with a Linguistically Driven Dynamic Hierarchical Conditional Variational Network
Tom Kenter · Vincent Wan · Chun-an Chan · Robert Clark · Jakub Vit

Thu Jun 13th 12:15 -- 12:20 PM @ Room 104

The prosodic aspects of speech signals produced by current text-to-speech systems are typically averaged over training material, and as such lack the variety and liveliness found in natural speech. To avoid monotony and averaged prosody contours, it is desirable to have a way of modeling the variation in the prosodic aspects of speech, so audio signals can be synthesized in multiple ways for a given text. We present a new, hierarchically structured conditional variational auto-encoder to generate prosodic features (F0, c0 and duration) suit- able for use with a vocoder or a generative model like WaveNet. At inference time, an embedding representing the prosody of a sentence may be sampled from the variational layer to allow for prosodic variation. To efficiently capture the hierarchical nature of the linguistic input (words, syllables and phones), both the encoder and decoder parts of the auto-encoder are hierarchical, in line with the linguistic structure, with layers being clocked dynamically at the respective rates. We show in our experiments that our dynamic hierarchical network outperforms a non-hierarchical state-of-the-art baseline. Additionally, we show that prosody transfer across sentences is possible by employing the prosody embedding of one sentence to generate the speech signal of another.

Author Information

Tom Kenter (Google UK)
Vincent Wan (Google)
Chun-an Chan (Google)
Rob Clark (Google UK)
Jakub Vit (University of West Bohemia)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors