Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron
Published in
International Conference on Machine Learning(2018)External Links:
TL
TL;DR
An extension to the Tacotron speech synthesis architecture that learns a latent embedding space of prosody, derived from a reference acoustic representation containing the desired prosody results in synthesized audio that matches the prosody of the reference signal with fine time detail.
Abstract
We present an extension to the Tacotron speech synthesis architecture that learns a latent embedding space of prosody, derived from a reference acoustic representation containing the desired prosody. We show that conditioning Tacotron on this learned embedding space results in synthesized audio that matches the prosody of the reference signal with fine time detail even when the reference and synthesis speakers are different. Additionally, we show that a reference prosody embedding can be used to synthesize text that is different from that of the reference utterance. We define several quantitative and subjective metrics for evaluating prosody transfer, and report results with accompanying audio samples from single-speaker and 44-speaker Tacotron models on a prosody transfer task.
References35 items
1
Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
2
On Using Backpropagation for Speech Texture Generation and Voice Conversion
3
Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions
4
Neural Discrete Representation Learning
5